Description:FIELD OF PRESENT DISCLOSURE
[0001] The embodiments of the present disclosure generally relate to a field of wireless communication, and specifically to a device and a method for managing power consumption in a network.

BACKGROUND OF PRESENT DISCLOSURE
[0002] The following description of the related art is intended to provide background information pertaining to the field of the disclosure. This section may include certain aspects of the art that may be related to various features of the present disclosure. However, it should be appreciated that this section is used only to enhance the understanding of the reader with respect to the present disclosure, and not as admissions of the prior art.
[0003] Efficient use of energy is a major challenge in modern wireless networks, especially in systems like 5th Generation (5G) and 6th Generation (6G). Emerging technologies demand higher data rates and lower latency, which significantly increase energy consumption across the network. Currently, energy management approaches primarily focus on individual components, such as base stations or user devices, without taking into account the entire path involved in delivering a service.
[0004] Each service, such as voice communication or data streaming, relies on a combination of network infrastructure and user device functions. Accurate measurement of energy usage at the level of each specific service is necessary for effective optimization. However, current methods have several limitations. Energy usage is not measured at the service level, and simple models are often employed that fail to represent the complex and dynamic nature of network conditions. Additionally, power usage in network infrastructure and user devices is managed separately, which results in suboptimal energy efficiency. Further, existing base station selection methods tend to ignore the impact of energy consumption, potentially lowering service quality.
[0005] Therefore, there is a need to address at least the above-mentioned drawbacks and any other shortcomings, or at the very least, provide a valuable alternative to the existing methods and systems.

OBJECTS OF THE PRESENT DISCLOSURE
[0006] Some of the objects of the present disclosure, which at least one embodiment herein satisfies are listed herein below.
[0007] An object of the present disclosure is to provide a system and a method for managing power consumption in a network, thereby enabling service-level energy optimization and improving overall efficiency and sustainability of network operations.
[0008] Another object of the present disclosure is to provide a system and a method for dynamically adjusting uplink and downlink power values for User Equipment (UE) and base stations (gNB) based on real-time network conditions, service requirements, and mobility events, thereby reducing overall network energy usage while maintaining desired Quality of Service (QoS).

SUMMARY
[0009] This section is provided to introduce certain objects and aspects of the present disclosure in a simplified form that are further described below in the detailed description. This summary is not intended to identify the key features or the scope of the claimed subject matter.
[0010] In an aspect, the present disclosure relates to a system for establishing communication between a user equipment and a base station at a boot-up stage of the user equipment. The system may comprise a processor and a memory operatively coupled to the processor. The memory may include processor-executable instructions, which on execution, may cause the processor to receive user equipment-related parameters from the user equipment via an initial base station from which the user equipment may receive beamforming signals after the boot-up stage. The processor may simultaneously receive base station-related parameters from the initial base station. The processor may determine historical information associated with the user equipment and current power-related information associated with the user equipment based on the user equipment-related parameters. The processor may predict a target power value for the user equipment and for the initial base station based on the historical information, the current power-related information, and the user equipment-related parameters. The processor may select at least one base station from a list of candidate base stations based on the predicted target power value. The processor may transmit a power configuration request message to the at least one base station. The processor may receive a positive acknowledgement message from the at least one base station in response to the transmission of the power configuration request message. The processor may establish communication between the user equipment and the at least one base station in real time for data transmission in response to the reception of the positive acknowledgement message.
[0011] In an embodiment, the historical information may comprise at least one of: information of a power consumption corresponding to each base station previously connected to the user equipment, information of a type of content involved in data transmission with each previously connected base station, information of a power mode, information of a service type, information of a subscription type, information of an updated path loss profile, information of an energy profile, information of a quality of service threshold, information of uplink power, information of a transport block size, information of a network load, information of a modulation and coding scheme, information of an updated channel quality indicator, information of a location of the user equipment with respect to the base station, and information of a user equipment aggregate maximum bit rate.
[0012] In an embodiment, to predict the target power value, the processor may be configured to predict an uplink power weight for the user equipment and a downlink power weight for the initial base station using an artificial intelligence model based on the user equipment-related parameters, the historical information, the current power-related information, and the base station-related parameters associated with the initial base station. The artificial intelligence model may be configured in the processor. The processor may predict a total power consumption corresponding to each service of the user equipment based on the predicted uplink power weight and downlink power weight. The processor may predict the target power value based on the total power consumption.
[0013] In an embodiment, to transmit the power configuration request message, the processor may be configured to determine that the predicted target power value does not exceed a power threshold corresponding to each service and may simultaneously determine that the predicted target power value is above a quality of service threshold corresponding to each service. The processor may transmit the power configuration request message to the at least one base station when the target power value does not exceed the power threshold and may simultaneously transmit the power configuration request message when the target power value is above the quality of service threshold.
[0014] In an embodiment, to select the at least one base station, the processor may be configured to fetch the list of candidate base stations from a database. The list of candidate base stations may include the initial base station. The processor may compare the user equipment-related parameters with base station-related parameters associated with the initial base station upon fetching the list. The processor may determine the at least one base station from among the list based on the comparison. The processor may determine that a power consumption may be dynamically adjusted in the at least one base station with respect to the target power value. The processor may select the at least one base station based on the determination.
[0015] In an embodiment, upon transmitting the power configuration request message to the at least one base station, the processor may be configured to determine whether a positive acknowledgement message is received from the at least one base station or a negative acknowledgement message is received. The processor may perform one of: determine at least one subsequent base station from among the list based on the comparison when the negative acknowledgement message is received and transmit the power configuration request message to the at least one subsequent base station to establish communication or establish the communication when the positive acknowledgement message is received, and the processor may check for at least one other subsequent base station based on the comparison until the positive acknowledgement message is received.
[0016] In an embodiment, a system may be provided for establishing communication between a user equipment and a base station at a boot-up stage. The system may comprise a processor and a memory operatively coupled to the processor. The memory may include processor-executable instructions, which on execution, may cause the processor to receive user equipment-related parameters after the boot-up stage upon transmitting beamforming signals. The processor may fetch historical information and current power-related information from an external database in response to the reception of the parameters. The processor may predict a target power value based on the historical information, current power-related information, and parameters. The processor may select at least one base station from a list of candidate base stations. The list may include the system. The processor may transmit a power configuration request message. The processor may receive a positive acknowledgement. The processor may establish communication in real time based on the reception of the acknowledgement.
[0017] In an embodiment, a system may be provided for managing power consumption in a network. The system may comprise a processor and a memory operatively coupled to the processor. The memory may include processor-executable instructions, which on execution, may cause the processor to receive a change in service request from the user equipment while the user equipment may be communicating with a base station. The processor may predict a target power value based on tracked power consumption data corresponding to a data transmission. The processor may transmit a power configuration request to at least one candidate base station. The processor may receive a positive acknowledgement from the at least one candidate base station. The processor may establish the communication in real time for data transmission.
[0018] In an embodiment, to track power consumption data, the processor may be configured to track data transmission based on user equipment-related parameters and base station-related parameters. The processor may determine the power consumption data with respect to the user equipment-related and base station-related parameters.
[0019] In an embodiment, to predict the target power value, the processor may be configured to predict an uplink power weight for the user equipment and a downlink power weight for the base station using an artificial intelligence model. The model may be configured in the processor. The processor may predict a total power consumption for each service and may predict the target power value based on the total power consumption.
[0020] In an embodiment, the user equipment-related parameters may include at least one of: an identity of the user equipment, a type of content, a power mode, a service type, a subscription type, a path loss profile, an energy profile, a quality of service threshold, uplink power, a transport block size, a network load, a modulation and coding scheme, a channel quality indicator, a location, and a user equipment aggregate maximum bit rate.
[0021] In an embodiment, the base station-related parameters may include at least one of: an identity of the base station, a type of base station, historical power usage patterns, a power mode, downlink power, a transport block size, a modulation and coding scheme, a location, a network load, a current power level, a number of resource elements, and information related to whether the base station may be operating in micro sleep mode.
[0022] In an embodiment, the processor may be configured to dynamically update the predicted uplink power weight with respect to user equipment-related parameters and the predicted downlink power weight with respect to base station-related parameters in real time.
[0023] In an embodiment, to transmit the power configuration request message, the processor may be configured to determine that the predicted target power value does not exceed a power threshold and may simultaneously determine that the predicted target power value is above a quality of service threshold. The processor may transmit the power configuration request message based on the determination.
[0024] In an embodiment, to transmit the power configuration request message, the processor may be configured to fetch a list of candidate base stations from a database. The list may include the base station. The processor may compare the user equipment-related parameters with the base station-related parameters. The processor may determine at least one candidate base station. The processor may determine that a power consumption may be dynamically adjusted. The processor may transmit the message based on the determination.
[0025] In an embodiment, upon transmitting the message, the processor may determine whether a positive acknowledgement or a negative acknowledgement may be received. The processor may perform one of: determine a subsequent candidate base station based on the comparison and transmit the message or establish communication with a base station, checking for others until a positive acknowledgement may be received.
[0026] In an embodiment, to establish communication, the processor may transmit a handover request to the candidate base station. The processor may simultaneously transmit a handover command to halt communication. The processor may receive an acknowledgement indicating successful communication. The processor may transmit a context release command and may receive a context release complete message indicating a successful release.
[0027] In an embodiment, a method may be provided for managing power consumption. The method may include receiving a change in service request message. The method may include predicting a target power value. The method may include transmitting a power configuration request. The method may include receiving a positive acknowledgement. The method may include establishing real-time communication.
[0028] In an embodiment, for predicting the target power value, the method may include predicting an uplink and downlink power weight using an artificial intelligence model. The model may be configured in the processor. The method may include predicting a total power consumption for each service. The method may include predicting the target power value based on the total power consumption.
[0029] Various objects, features, aspects, and advantages of the inventive subject matter will become more apparent from the following detailed description of preferred embodiments, along with the accompanying drawing figures in which like numerals represent components.

BRIEF DESCRIPTION OF DRAWINGS
[0030] The accompanying drawings, which are incorporated herein, and constitute a part of this disclosure, illustrate exemplary embodiments of the disclosed methods and systems which like reference numerals refer to the same parts throughout the different drawings. Components in the drawings are not necessarily to scale, emphasis instead being placed upon clearly illustrating the principles of the present disclosure. Some drawings may indicate the components using block diagrams and may not represent the internal circuitry of each component. It will be appreciated by those skilled in the art that disclosure of such drawings includes the disclosure of electrical components, electronic components, or circuitry commonly used to implement such components.
[0031] FIG. 1 illustrates a network architecture of communication between a User Equipment (UE), a base station (gNB), a core network, and a system, in accordance with an embodiment of the present disclosure.
[0032] FIG. 2 illustrates an example block diagram of a system for managing power consumption in a network, in accordance with an embodiment of the present disclosure.
[0033] FIG. 3 illustrates an example flow chart depicting a step-by-step energy-efficient UE-to-gNB assignment and scheduling procedure using an Artificial Intelligence AI/ Machine Learning (ML)-based power optimization in the network, in accordance with an embodiment of the present disclosure.
[0034] FIG. 4 illustrates an example sequential diagram depicting the energy information exchange flow between a gNB (e.g., the base station) and an Energy Control Function (ECF), in accordance with an embodiment of the present disclosure.
[0035] FIG. 5 illustrates an example sequential diagram depicting an interaction between the ECF and an Energy Database Manager (EDM), in accordance with an embodiment of the present disclosure.
[0036] FIG. 6 illustrates a flow chart of an example method of an initial attach procedure for the UE during a boot-up stage, in accordance with an embodiment of the present disclosure.
[0037] FIG. 7 illustrates an exemplary flow diagram for implementing a method for managing the power consumption in the network, in accordance with embodiments of the present disclosure.
[0038] FIG. 8 illustrates an exemplary computer system in which or with which embodiments of the present disclosure may be utilized in accordance with embodiments of the present disclosure.

DETAILED DESCRIPTION
[0039] In the following description, for the purposes of explanation, various specific details are set forth in order to provide a thorough understanding of embodiments of the present disclosure. It will be apparent, however, that embodiments of the present disclosure may be practiced without these specific details. Several features described hereafter can each be used independently of one another or with any combination of other features. An individual feature may not address all of the problems discussed above or might address only some of the problems discussed above. Some of the problems discussed above might not be fully addressed by any of the features described herein.
[0040] The ensuing description provides exemplary embodiments only and is not intended to limit the scope, applicability, or configuration of the disclosure. Rather, the ensuing description of the exemplary embodiments will provide those skilled in the art with an enabling description for implementing an exemplary embodiment. It should be understood that various changes may be made in the function and arrangement of elements without departing from the spirit and scope of the disclosure as set forth.
[0041] Specific details are given in the following description to provide a thorough understanding of the embodiments. However, it will be understood by one of ordinary skill in the art that the embodiments may be practiced without these specific details. For example, circuits, systems, networks, processes, and other components may be shown as components in block diagram form in order not to obscure the embodiments in unnecessary detail. In other instances, well-known circuits, processes, algorithms, structures, and techniques may be shown without unnecessary detail to avoid obscuring the embodiments.
[0042] Also, it is noted that individual embodiments may be described as a process that is depicted as a flowchart, a flow diagram, a data flow diagram, a structure diagram, or a block diagram. Although a flowchart may describe the operations as a sequential process, many of the operations can be performed in parallel or concurrently. In addition, the order of the operations may be re-arranged. A process is terminated when its operations are completed but could have additional steps not included in a figure. A process may correspond to a method, a function, a procedure, a subroutine, a subprogram, etc. When a process corresponds to a function, its termination can correspond to a return of the function to the calling function or the main function.
[0043] The word “exemplary” and/or “demonstrative” is used herein to mean serving as an example, instance, or illustration. For the avoidance of doubt, the subject matter disclosed herein is not limited by such examples. In addition, any aspect or design described herein as “exemplary” and/or “demonstrative” is not necessarily to be construed as preferred or advantageous over other aspects or designs, nor is it meant to preclude equivalent exemplary structures and techniques known to those of ordinary skill in the art. Furthermore, to the extent that the terms “includes,” “has,” “contains,” and other similar words are used in either the detailed description or the claims, such terms are intended to be inclusive in a manner similar to the term “comprising” as an open transition word without precluding any additional or other elements.
[0044] Reference throughout this specification to “one embodiment” or “an embodiment” or “an instance” or “one instance” means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the present disclosure. Thus, the appearances of the phrases “in one embodiment” or “in an embodiment” in various places throughout this specification are not necessarily all referring to the same embodiment. Furthermore, the particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.
[0045] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the disclosure. As used herein, the singular forms “a”, “an”, and “the” are intended to include the plural forms as well, unless the context indicates otherwise. It will be further understood that the terms “comprises” and/or “comprising,” when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof. As used herein, the term “and/or” includes any and all combinations of one or more of the associated listed items.
[0046] The terms “base station” and “gNB” are interchangeably mentioned throughout the specification.
[0047] FIG. 1 illustrates a network architecture 100 of communication between a User Equipment (UE) (106-1 to 106-N), a base station (gNB) 104-1 to 104-N, a core network, and a system 102, in accordance with an embodiment of the present disclosure.
[0048] Referring to FIG. 1, a 5th Generation (5G) core network 102 (e.g., the system 102) may serve as the central control system responsible for managing signalling, mobility, policy enforcement, session handling, and overall energy efficiency across the wireless infrastructure. The 5G core network 102 may communicate with multiple base stations such as gNB 1 104-1, gNB 2 104-2, gNB 3 104-3, …. gNB n 104-N using the N2 interface 118B, which may facilitate functions such as registration, authentication, and mobility management handled by AMF (112). Each gNB 1 104-1, gNB 2 104-2, gNB 3 104-3, … gNB n 104-N may serve one or more UEs, such as UE 1 106-1, UE 2 106-2, UE 3 106-3, UE 4 106-4, …. UE n 106-N, enabling wireless data transmission. The UE 1 106-1, UE 2 106-2, UE 3 106-3, UE 4 106-4, …. UE n 106-N may be collectively referred to as UE 106. The gNB 1 104-1, gNB 2 104-2, gNB 3 104-3, …. gNB n 104-N may be collectively referred to as base stations 104.
[0049] The 5G core network 102 may include a Session Management Function (SMF) 108, a Policy Control Function (PCF) 110, an Access and Mobility Management Function (AMF) 112, an Energy Control Function (ECF) 114, and Other Network Functions (other NFs) 116. Further, the SMF 108 may be responsible for establishing, maintaining, and terminating user data sessions. The SMF 108 may interact with the User Plane Function (UPF) to ensure that data packets for services such as video streaming or web browsing are routed efficiently with proper session-level Quality of Service (QoS). Further, the PCF 110 may be configured to determine and apply policies related to QoS, service charging, and access rules. For instance, the PCF 110 may enforce premium service policies when a high-priority user initiates a video call.
[0050] Further, the AMF 112 may control functions such as user registration, mobility, access authentication, and UE reachability. The AMF 112 may communicate with the Next Generation Node B (gNB) units using the N2 Interface 118A, especially for operations like handovers between cells. The ECF 114 may manage service-level energy efficiency throughout the network. The ECF 114 may determine power control policies per service based on input received from multiple gNBs via dedicated Energy Monitoring Units (EMUs). The ECF 114 may reside in the core network 102 or may alternatively be deployed in the Service Management and Orchestration (SMO) layer. Further, Within ECF 114, an Energy Database Manager (EDM) (e.g., the database 212 as represented in FIG. 2) may be tasked with collecting and storing both real-time and historical energy metrics associated with different services and the gNBs 104-1 to 104-N. The EDM may maintain a local repository that includes workload patterns, energy consumption records, and service performance requirements. Further, a Machine Learning (ML) model configured in the system 102 may analyse dynamic network data to predict optimal Downlink (DL) transmission power for gNBs and Uplink (UL) transmission power for UEs. The ML model may assist ECF 114 in proactively determining power settings that conserve energy while meeting QoS demands. The ML Model decisions may directly influence actions taken by AMF 112 and gNB components. Further, the Other NFs 116 may include entities such as the Authentication Server Function (AUSF), Network Repository Function (NRF), Network Slice Selection Function (NSSF), and the UPF, which may collectively support control plane authentication, network function discovery, user data forwarding, and slicing.
[0051] The gNBs may represent distributed base stations within the Radio Access Network. The gNB 1 104-1 may serve multiple UEs such as UE 1 106-1, UE 2 106-2 … UE n 106-N. An Energy Monitoring Unit 1 (EMU 1) 120-1, may be integrated with gNB 1 104-1 and may continuously monitor power consumed by the base station 104, optionally on a per service. The EMU 1 120-1 may transmit real-time energy data to ECF 114 via the Nx Interface 118A, which may be a dedicated energy reporting interface. The gNB 2 104-2 and gNB 3 104-3 may be similarly configured to support their respective UEs UE 4 106-4 and other UEs and may each include EMU 2 120-2 and EMU 3 120-3, which may perform identical monitoring and reporting functions as EMU 1 120-1. An extended deployment may involve gNB n 104-N serving UE n 106-N, with associated EMU n 120-N supporting energy tracking operations. Each EMU, such as EMU 1 120-1, EMU 2 120-2, EMU 3 120-3, and EMU n 120-N, may operate in close synchronization with ECF 114, providing telemetry required to adjust power dynamically. The EMU 1 120-1, EMU 2 120-2, EMU 3 120-3, and EMU n 120-N may be collectively referred to as EMU 120. The Nx interface 118A may be implemented for structured and low-latency energy information exchange between EMUs 120-1 to 120-N, and ECF 114.
[0052] Further, the UE 1 106-1, UE 2 106-2, UE 3 106-3, UE 4 106-4, and UE n 106-N may connect to the network through corresponding gNBs (104-1-104-N) and may each consume uplink transmission power based on session demand. The uplink power of each UE may be continuously adjusted based on predictions made by ML model to align with the energy optimization policy enforced by ECF 114, ensuring that energy use remains efficient without compromising service quality.
[0053] FIG. 2 illustrates an example block diagram 200 of the system 202 (e.g., the system 102 or the ECF 114 as represented in FIG. 1) for managing the power consumption in the network, in accordance with an embodiment of the present disclosure.
[0054] Referring to FIG. 2, the system 202 may include a processor 204, a memory 206, and an interface(s) 208. The processor 204 may be implemented as one or more microprocessors, microcomputers, microcontrollers, digital signal processors, central processing units, logic circuitries, and/or any devices that manipulate data based on operational instructions. Among other capabilities, the processor 204 may be configured to fetch and execute computer-readable instructions stored in the memory 206 of the system 202. The memory 206 may store one or more computer-readable instructions or routines, which may be fetched and executed to perform the operations. The memory 206 may include any non-transitory storage device, including, for example, volatile memory such as Random-Access Memory (RAM), or non-volatile memory such as Erasable Programmable Read-Only Memory (EPROM), flash memory, and the like. The interface(s) 208 may comprise a variety of interfaces, for example, interfaces for data input and output devices, referred to as I/O devices, storage devices, and the like. The interface(s) 208 may facilitate communication of the system 202 with various devices coupled to it. The interface(s) 208 may also provide a communication pathway for one or more components of the system 202. Examples of such components include, but are not limited to, processing engine(s) 210 and a database 212. The database 212 may include data that is either stored or generated as a result of functionalities implemented by any of the components of the processing engine(s) 210. In an embodiment, the processing engine(s) 220 may correspond to an AI engine that may be configured with the AL or ML model.
[0055] In an embodiment, the processing engine(s) 210 may be implemented as a combination of hardware and programming (for example, programmable instructions) to implement one or more functionalities of the processing engine(s) 210. In the examples described herein, such combinations of hardware and programming may be implemented in several different ways. For example, the programming for the processing engine(s) 210 may be processor-executable instructions stored on a non-transitory machine-readable storage medium, and the hardware for the processor 204 may comprise a processing resource (for example, one or more processors), to execute such instructions. In the present examples, the machine-readable storage medium may store instructions that, when executed by the processing resource, implement the processing engine(s) 210. In such examples, the system 202 may comprise the machine-readable storage medium storing the instructions and the processing resource to execute the instructions, or the machine-readable storage medium may be separate but accessible to the system 202 and the processing resource. In other examples, the processing engine(s) 210 may be implemented by electronic circuitry. The processing engine(s) 210 may include a parameter reception module 214, a historical information determination module 216, a prediction module 218, a base station selection module 220, a communication establishment module 222, and other module(s) 224. The other module(s) 224 may implement functionalities that supplement applications/functions performed by the processing engine(s) 210.
[0056] For establishing communication between the UE 106 and the base station at a boot-up stage of the UE (e.g., 106 as represented in FIG. 1). Further, the parameter reception module 214 may receive UE-related parameters from the UE 106, via an initial base station (e.g., 104-1 as represented in FIG. 1), from which the UE 106 receives beamforming signals, after the boot-up stage of the UE 106, and simultaneously receive base station-related parameters from the initial base station 104-1. In an embodiment, the boot-up stage may refer to any type of initialization process associated with the UE 106. For example, the boot-up may include, but may not be limited to, an initial boot-up when the UE is powered on for the first time, a rebooting scenario where the UE restarts due to manual or UE-triggered events, a recovery from airplane mode where network connectivity is re-established, or any other alternative process that may initiate network reattachment or service configuration. In some cases, the boot-up may be triggered by a software update, a reset operation, or a network re-registration event caused by coverage loss or roaming conditions. Regardless of the specific boot-up condition, the boot-up stage may represent the starting point for a new attach or registration process by the UE within the network. Further, the historical information determination module 216 may determine historical information associated with the UE 106 and current power-related information associated with the UE 106 based on the UE-related parameters.
[0057] In an embodiment, the historical information may include information of a power consumption corresponding to each base station 104 previously connected to the UE 106, information of a type of content involved in the data transmission with each previously connected base station, information of a power mode, information of a service type, information of a subscription type, information of a updated path loss profile, information of an energy profile, information of a QoS threshold, information of uplink power, information of a transport block size, information of a network load, information of a modulation and coding scheme, information of a updated channel quality indicator, information of a location of the UE 106 with respect to the base station, and information of a UE aggregate maximum bit rate. In an embodiment, the periodicity of updating historical information may be configured in accordance with the Third Generation Partnership Project (3GPP) 5G core standards.
[0058] Further, the prediction module 218 may predict a target power value for the UE 106 and for the initial base station 104-1 based on the historical information, the current power-related information, and the UE-related parameters. In an embodiment, to predict the target power value, the prediction module 218 may predict an uplink power weight for the UE 106 and a downlink power weight for the initial base station 104-1 using an Artificial Intelligence (AI) model (e.g., the ML model) based on the UE-related parameters, the historical information, the current power-related information, the base station-related parameters associated with the initial base station 106-1. In an embodiment, the AI model may be configured in the processor 204. Further, the prediction module 218 may predict a total power consumption corresponding to each service of the UE 106 based on the predicted uplink power weight and downlink power weight, and predict the target power value based on the total power consumption.
[0059] Further, the base station selection module 220 may select at least one base station (e.g., 104-2 as represented in FIG. 1) from a list of candidate base stations 104-1 to 104-N based on the predicted target power value. Further, the communication establishment module 222 may transmit a power configuration request message to the at least one base station 104-2 and receive a positive acknowledgement message from the at least one base station 104-2 in response to the transmission of the power configuration request message. Further, the communication establishment module 222 may establish the communication between the UE 106 and the at least one base station 104-2 in real time for the data transmission in response to the reception of the positive acknowledgement message.
[0060] In an embodiment, to establish the communication between the UE 106 and the at least one base station 104-2, the communication establishment module 222 may transmit a UE-related parameter request message to the UE 106, via the initial base station 104-1 and simultaneously transmit a base station-related parameter request message to the at least one base station 104-2. Further, the communication establishment module 222 may receive UE-related parameters from the UE, upon transmitting the UE-related parameter request message to the UE 106, and simultaneously receive base station-related parameters from the at least one base station 104-2, upon transmitting the base station-related parameter request message to the base station 104-2. Further, the communication establishment module 222 may establish the communication between the UE 106 and the at least one base station 104-2 based on the historical information fetched from the database 212, the UE-related parameters, and the base station-related parameters.
[0061] In an embodiment, to select the at least one base station 104-2, the base station selection module 220 may fetch the list of candidate base stations 104-1 to 104-N from the database 212. In an embodiment, the list of candidate base stations 104-1 to 104-N may include the initial base station (104-1) and compare the UE-related parameters with base station-related parameters associated with the initial base station 104-1 upon fetching the list of candidate base stations 104-1 to 104-N. Further, the base station selection module 220 may determine the at least one base station 104-2 from among the list of candidate base stations 104-1 to 104-N based on the comparison and determine that a power consumption is dynamically adjusted in the at least one base station 104-2 with respect to the target power value. Further, the base station selection module 220 may select the at least one base station 104-2 based on the determination that the power consumption is dynamically adjusted in the at least one base station 104-2.
[0062] In an embodiment, the communication establishment module 222 may determine whether the predicted target power value does not exceed a power threshold corresponding to each service or not and simultaneously determine whether the predicted target power value is above a QoS threshold corresponding to each service or not. If the target power value does not exceed the power threshold, the communication establishment module 222 may transmit the power configuration request message to the at least one base station. Simultaneously, if the target power value is above the QoS threshold, the communication establishment module 222 may transmit the power configuration request message to the at least one base station.
[0063] In an embodiment, upon transmitting the power configuration request message to the at least one base station 104-2, the system 202 may determine whether the positive acknowledgement message is received from the at least one base station 104-2 or a negative acknowledgement message is received from the at least one base station 104-2 or not. If the negative acknowledgement message is received from the at least one base station 104-2, the system 202 may determine at least one subsequent base station (e.g., 104-3 as represented in FIG. 1) from among the list of candidate base stations 104-1 to 104-N based on the comparison. If the positive acknowledgement message is received from the at least one base station 104-2, the system 202 may establish the communication between the UE 106 and the at least one base station 104-2. In an embodiment, the system 202 may be configured to check for at least one other subsequent base station (e.g., 104-4) from among the list of candidate base stations 104-1 to 104-N based on the comparison until the positive acknowledgement message is received from any one of the base stations among the list of candidate base stations 104-1 to 104-N.
[0064] In an embodiment, the initial base station 104-1 may act as the system 202 to establish communication between the UE 106 and the base station 104 at the boot-up stage of the UE 106. In an embodiment, for establishing the communication between the UE 106 and the base station 104 at the boot-up stage of the UE 106, the parameter reception module 214 configured in the initial base station 104-1 may receive the UE-related parameters from the UE 106, after the boot-up stage of the UE 106, upon transmitting beamforming signals. Further, the historical information determination module 216 configured in the initial base station 104-1 may fetch historical information associated with the UE 106 and current power-related information associated with the UE 106 from an external database, in response to the reception of the UE-related parameters. Further, the prediction module 218 configured in the initial base station 104-1 may predict the target power value for the UE and for the initial base station 104-1 based on the historical information, the current power-related information, and the UE-related parameters. Further, the base station selection module 220 configured in the initial base station 104-1 may select the at least one base station 104-2 from the list of candidate base stations 104-1 to 104-N based on the predicted target power value. In an embodiment, the list of candidate base stations 104-1 to 104-N may include the initial base station 104-1. In an embodiment, the communication establishment module 222 configured in the initial base station 104-1may transmit the power configuration request message to the at least one base station 104-2 and receive the positive acknowledgement message from the at least one base station 104-2 in response to the transmission of the power configuration request message. Further, the communication establishment module 222 may establish the communication between the UE 106 and the at least one base station 104-2 in real time for the data transmission in response to the reception of the positive acknowledgement message.
[0065] For managing power consumption in a network, the system 102 may receive a change in service request message from the UE 106 while the UE 106 is in communicating with a base station (e.g., the at least one base station 104-2).Further, the prediction module 218 may predict the target power value for the UE 106 and the base station 104-2 based on tracked power consumption data corresponding to a data transmission between the UE 106 and the base station 104-2, in response to the reception of the change in service request message. In an embodiment, to track the power consumption data, the prediction module 218 may track the data transmission between the UE and the base station based on UE-related parameters and base station-related parameters and determine the power consumption data, corresponding to the data transmission, with respect to the UE-related parameters and the base station-related parameters.
[0066] In an embodiment, to predict the target power value for the UE 106 and the base station 104, the prediction module 218 may predict the uplink power weight for the UE 106 and the downlink power weight for the base station 104-2 using the AI model based on UE-related parameters, base station-related parameters, and the power consumption data. In an embodiment, the AI model may be configured in the processor 204. Further, the prediction module 218 may predict the total power consumption corresponding to each service based on the predicted uplink power weight and downlink power weight, and predict the target power value based on the total power consumption. In an embodiment, the UE-related parameters may include, but not limited to an identity of the UE 106, a type of content involved in the data transmission, a power mode, a service type, a subscription type, a path loss profile, an energy profile, a QoS threshold, uplink power, a transport block size, a network load, a modulation and coding scheme, a channel quality indicator, a location of the UE 106 with respect to the base station, a UE aggregate maximum bit rate, and the like. In an embodiment, the base station-related parameters may include an identity of the base station, a type of the base station, historical power usage patterns, a power mode, downlink power, a transport block size, a modulation and coding scheme, a location of the base station with respect to the UE 106, a network load, a current power level of the base station during the data transmission, a number of resource elements allocated to the UE 106, information related to whether the base station is operating in micro sleep mode to conserve energy, and the like.
[0067] Further, the communication establishment module 222 may transmit the power configuration request message to at least one candidate base station (e.g., 104-5) based on the prediction and receive the positive acknowledgement message from the at least one candidate base station 104-5 in response to the transmission of the power configuration request message. Further, the communication establishment module 222 may establish the communication between the UE 106 and the at least one candidate base station 104-5 in real time for the data transmission in response to the reception of the positive acknowledgement message.
[0068] In an embodiment, the prediction module 218 may be configured to dynamically update the predicted uplink power weight with respect to UE-related parameters and the predicted downlink power weight with respect to the base station-related parameters in real time. In an embodiment, to transmit the power configuration request message, the communication establishment module 222 may be configured to determine whether the predicted target power value does not exceed a power threshold corresponding to each service or not, and simultaneously determine whether the predicted target power value is above a QoS threshold corresponding to each service or not. If the target power value does not exceed the power threshold, the communication establishment module 222 may transmit the power configuration request message to the at least one candidate base station (e.g., 104-5). Simultaneously, if the target power value is above the QoS threshold, the communication establishment module 222 may transmit the power configuration request message to the at least one candidate base station (e.g., 104-5).
[0069] Table 1 may illustrate the functioning of an AI/ML-based prediction framework managed by the Energy Control Function (ECF 114) for optimizing network power usage on a per-service basis. The ECF (114) may determine optimal power weights, referred to as X and Y, by minimizing the total energy consumed by both the gNB (104) and the UE (106) during active service sessions. The calculation may follow the expression: Total_power_per_service = Total_power_tx_gNB × X + Total_power_tx_UE × Y, where X may represent the weight applied to the gNB downlink power, and Y may represent the weight applied to the UE uplink power.

Table 1
[0070] To derive these optimal weights, the ECF 114 may utilize a machine learning model trained using real-time and historical network parameters. The input features for the model may include gNB transmit power, UE transmit power, gNB power mode, UE power mode, QoS metrics such as latency, jitter, throughput, and packet loss, along with service type classifications like voice, video, or data. Additional input parameters may include the type of gNB 104, whether macro, micro, or small cell, network load conditions, UE 106 mobility behavior, location context, and Channel Quality Indicators (CQI).
[0071] Table 1 may represent the structured collection and application of all these parameters during both the data collection and prediction phases. The Energy Control Function 114 may gather UE ID, gNB ID, 5QI (indicating the service class), UE-AMBR , Transport Block Size (TBS), Modulation and Coding Scheme (MCS), and user type information, which may all serve as contributing factors in determining energy-optimized power allocations. Based on these diverse inputs, the ECF 114 may employ a random forest regressor model, selected due to its ability to manage complex, non-linear relationships and accommodate varied data types. Two separate models may be trained, one model may be dedicated to predicting the optimal downlink power weight X for the gNB (104), and another model may be focused on the uplink power weight Y for the UE (106).
[0072] The performance of the prediction process may be evaluated using metrics such as prediction accuracy, model latency, Quality of Experience (QoE) scores, and Mean Squared Error (MSE) for both X and Y. Once the models are deployed, the prediction and application of X and Y may be carried out dynamically, allowing the ECF 114 to adapt to changing network conditions, user movement, and service demands. This adaptive mechanism may ensure that the total power used per service is kept at a minimum while continuing to meet expected quality standards for each session managed between the gNB (104) and the UE (106).
[0073] In one scenario, during the UE active phase, dynamic power control operations may be performed in coordination among UE 106, gNB 104, AMF 112, and ECF 114. The gNB 104 may monitor the power mode of the UE 106 and may report any changes to the AMF 112. In parallel, the AMF 112 may monitor the mobility status of the UE 106 to evaluate possible handover requirements or network reconfiguration opportunities.
[0074] The AI/ML model may be deployed by the ECF 114. The ECF 114 may use Physical Uplink Shared Channel (PUSCH) transmission power as an uplink signal strength indicator from the UE 106. The AI/ML model may consider multiple parameters such as the power mode of the UE 106, transmission activity, quality of service requirements, prevailing network load conditions, and the gNB 104 characteristics. Based on these inputs, the AI/ML model may predict optimal power weights X and Y. When the UE 106 may operate in a low power mode, the prediction mechanism may prioritize optimization of the uplink weight Y. The predicted weights may be forwarded by the AMF 112 to both the gNB 104 and the UE 106. The AMF 112 may instruct gNB 104 and UE 106 to update transmission power levels according to the received weights X and Y. The power configuration applied in real time may reflect the most efficient settings based on ongoing service and load conditions. The ECF 114 may continue to observe power-related parameters and service behaviour in real time. Adjustments to weights X and Y may be triggered whenever changes in mobility, signal quality, or service demand may be detected. The continuous adaptation may be to maintain an optimal balance between power efficiency and service performance throughout the active session of the UE 106.
[0075] In another scenario, when the UE 106 may be in the active phase and the gNB 104 may enter a low power mode, a downlink-focused power weight optimization process may be triggered. The gNB 104 may signal the transition to low power mode to AMF 112, while UE 106 may continue operating in an active state. Upon receiving the signal, the AMF 112 may notify the ECF 114 to initiate power optimization. The ECF 114 may activate the AI/ML-based prediction model that may take into account PUSCH power from the UE 106, the low power status of the gNB 104, context data related to the UE 106, the QoS parameters, and the current network load conditions. The AI/ML model may prioritize optimization of the downlink power weight X to reduce gNB 104 energy consumption, while a conservative adjustment may be applied to uplink power weight Y associated with UE 106.
[0076] The AMF 112 may distribute the predicted power weights by transmitting X to gNB 104 and Y to UE 106. Following this distribution, the AMF 112 may instruct the gNB 104 and the UE 106 to apply the updated power values in real time. The adjustment may ensure service continuity while targeting energy savings in the gNB 104. The ECF 114 may continue to observe network conditions and may dynamically re-optimize X and Y as changes in service demand, load, or mobility patterns may occur.
[0077] In an embodiment, to transmit the power configuration request message, the communication establishment module 222 may fetch the list of candidate base stations 104-1 to 104-N from the database 212 associated with the system 202. In an embodiment, the list of candidate base stations 104-1 to 104-N may include the base station 104-2. Further, the communication establishment module 222 may compare the UE-related parameters with the base station-related parameters associated with each candidate base station upon fetching the list of candidate base stations 104-1 to 104-N and determine the at least one candidate base station (e.g., 104-5) from among the list of candidate base stations 104-1 to 104-N based on the comparison. Further, the communication establishment module 222 may determine whether a power consumption is dynamically adjusted in the at least one candidate base station (e.g., 104-5) with respect to the target power value and transmit the power configuration request message to the at least one candidate base station (e.g., 104-5) based on the determination that the power consumption is dynamically adjusted in the at least one candidate base station (e.g., 104-5).
[0078] In an embodiment, upon transmitting the power configuration request message to the at least one candidate base station 104-5, the communication establishment module 222 may determine whether the positive acknowledgement message is received from the at least one candidate base station 104-5 or a negative acknowledgement message is received from the at least one candidate base station 104-5. If the negative acknowledgement message is received from the at least one candidate base station 104-5, the communication establishment module 222 may determine at least one subsequent candidate base station 104-6 from among the list of candidate base stations 104-1 to 104-N based on the comparison and transmit the power configuration request message to the at least one subsequent candidate base station 104-6 to establish the communication between the UE 106 and the at least one subsequent candidate base station 104-6. If the positive acknowledgement message is received from the at least one candidate base station 104-5, the communication establishment module 222 may establish the communication between the UE 106 and the at least one candidate base station 104-5.
[0079] In an embodiment, the communication establishment module 222 may be configured to check for at least one other subsequent candidate base station 104-7 from among the list of candidate base stations 104-1 to 104-N based on the comparison until the positive acknowledgement message is received from any one of the base stations among the list of candidate base stations 104-1 to 104-N. In an embodiment, to establish the communication between the UE and the at least one candidate base station 104-5, the communication establishment module 222 may transmit a handover request message to the at least one candidate base station 104-5, requesting the at least one candidate base station 104-5 to allocate resources for the UE 106 and simultaneously transmit a handover command to the base station 104-2 to halt the communication with the UE 106, upon transmitting the handover request message. Further, the communication establishment module 222 may receive an acknowledgement handover notification from the at least one candidate base station 104-5, indicating successful communication establishment between the UE 106 and the at least one candidate base station 104-5, in response to the transmission of the handover request message and transmit a context release command to the base station 104-2 to release a context of the UE 106 and resources associated with the UE 106, upon receiving the acknowledgement handover notification from the at least one candidate base station 104-5. Further, the communication establishment module 222 may receive a context release complete message from the base station 104-2, in response to the transmission of the context release command. In an embodiment, the context release complete message indicates successful release of the context of the UE 106 and the resources.
[0080] The gNB 104 may perform a feasibility check to evaluate whether a UE 106 can be scheduled using the power configuration provided by the AMF 112. The evaluation may rely on dynamic Energy Per Resource Element (EPRE)-based power optimization. The system 202 may be designed to allow the gNB 104 to dynamically adjust EPRE values per UE 106, ensuring service quality while minimizing total transmission power. In an embodiment, a power optimizer module within the gNB 104 may drive this adaptation using real-time input and optimized weights received from external control functions.
[0081] Initially, the gNB 104 may initiate dynamic EPRE allocation for each UE 106. The EPRE may serve as the fundamental unit of power allocation per resource element. Instead of relying on static EPRE levels, the gNB 104 may dynamically update the EPRE for each UE 106 by using current link conditions and optimization feedback generated internally. The adjustments may help balance energy savings with consistent quality of service. During the EPRE calculation process, the initialization procedure may assume that all UEs 106 are scheduled during the first Orthogonal Frequency-Division Multiplexing (OFDM) symbol of a time slot. The maximum transmit power per symbol may be considered as 24 dBm, and the total number of resource elements in a single symbol may be 273. The EPRE for all UEs 106 may be calculated using the formula: EPRE_all UEs = 24 dBm – 10 log (273) = − 0.36 dBm.
[0082] After the EPRE baseline is computed, the gNB 104 may use input from the AMF 112 to refine the scheduling decision. The AMF 112 may provide optimized power weights X and Y, which may be calculated by the ECF 114 using the AI/ML-based prediction models. The gNB 104 may then validate whether the UE 106 can be scheduled within the allowed power envelope using the dynamically computed EPRE values. For power optimization using Signal-to-Interference-Plus-Noise Ratio (SINR) thresholds, the gNB 104 may rely on data provided by a monitoring unit associated with the system 202, which may track real-time EPRE values, path loss for each UE 106, receiver sensitivity, and the current allocation of resources. Using this information, the Power Optimizer may estimate the SINR by applying the formula: SINR = current EPRE − path loss − receiver sensitivity. This estimation may enable the gNB 104 to determine whether the EPRE can be reduced or increased for a specific UE 106 without degrading the Channel Quality Indicator (CQI). In one example, for UE 106 classified as UE A with a CQI of 15, the Power Optimizer may determine that a reduction of up to 1.7 dB in the EPRE may still preserve the same CQI level. Such optimization may allow gNB 104 to reduce transmission power for UE A by 1.7 dB, achieving energy savings without affecting performance.
[0083] In the power scheduling decision phase, the gNB 104 may evaluate whether the power value provided by the AMF 112 lies within the permissible EPRE range derived through the dynamic optimization. If the EPRE value may be acceptable, the UE 106 may be scheduled for transmission using the adjusted EPRE settings. If the EPRE value may fall outside the acceptable range, the gNB 104 may recalculate scheduling priorities or may initiate a handover request to the AMF 112, suggesting reassignment of the UE 106 to a more suitable gNB 104. This method may enable intelligent, energy-efficient downlink scheduling and resource management within the radio access network, aligning real-time transmission conditions with predictive energy control strategies from the ECF 114.
[0084] In an embodiment, uplink power validation through the Transmit Power Control (TPC) mechanism may be used by the gNB 104 as part of the power control process to evaluate and adjust the uplink transmit power of the UE 106 based on the power value received from the AMF 112. The validation process may consist of several steps designed to ensure uplink energy efficiency and real-time transmission reliability. Initially, during UE uplink power comparison, the gNB 104 may receive a target uplink power value for the UE 106 from AMF 112. The gNB 104 may then compare the received target power with the current uplink transmit power measured at the receiver side for the UE 106.
[0085] During the TPC command range check, the gNB 104 may compute the difference between the current uplink power level and the target uplink power received from the AMF 112. The calculated power difference may be compared against the predefined TPC command range. If the difference may lie within the allowed range, the gNB 104 may proceed with further validation steps. If the difference may exceed the TPC threshold, the gNB 104 may trigger alternate handling procedures, which may include initiating a power re-optimization routine or rejecting the configuration as non-compliant.
[0086] After the uplink comparison, a downlink power feasibility check may be performed. The gNB 104 may validate the feasibility of applying the downlink power weight X provided by the AMF 112 or predicted by the ECF 114. The feasibility check may ensure that the downlink transmission for the UE 106 may be supported under the existing power budget of the gNB 104. If the downlink power weight X may be acceptable, both uplink and downlink power settings may be marked as valid by the gNB 104.
[0087] During the final acknowledgment and TPC command transmission stage, if both power configurations may be found valid, the gNB 104 may transmit an ACK message to the AMF 112 to confirm successful validation. In the next transmission cycle, the gNB 104 may include a TPC command within the Downlink Control Information (DCI) to instruct the UE 106 to adjust uplink transmission power to the validated level. The TPC-based validation method may provide a precise and efficient mechanism to manage uplink power behaviour, enabling the network to enhance link reliability while reducing unnecessary power consumption. In an embodiment, coordination between the gNB 104, the AMF 112, and the ECF 114 may enable dynamic power alignment under varying network conditions, contributing to a sustainable and high-performance 5G environment.
[0088] In an embodiment, the AI/ML-based uplink and downlink power feasibility assessment may be performed at the gNB 104 in scenarios where conventional power validation approaches, such as dynamic EPRE allocation for downlink or TPC-based control for uplink—may be insufficient or unavailable. The gNB 104 may execute an embedded AI/ML model trained using a mix of historical and real-time network data to evaluate whether communication with the UE 106 may be sustained within the power constraints provided by the AMF 112 for both uplink and downlink transmissions. The AI/ML model may utilize a variety of input parameters including mobility characteristics and location context of the UE 106, link degradation and path loss metrics, CQI values, service classification and QoS parameters such as delay and throughput, the gNB’s 104 current traffic load and resource utilization, and UE’s 106 power mode which may include normal or low-power modes.
[0089] For uplink power feasibility evaluation, if TPC-based control may not accommodate the difference between the UE’s 106 existing uplink transmit power and the target value suggested by the AMF 112, the gNB 104 may invoke the AI/ML model to estimate whether the UE 106 may still effectively transmit under the power configuration. The estimation may consider interference expectations, link stability, and service-level importance.
[0090] For downlink power feasibility, if dynamic EPRE allocation may not accommodate the downlink power weight X received from the AMF 112 (or derived from the ECF 114), the AI/ML model at the gNB 104 may determine whether service continuity for the UE 106 may be possible under the assigned power configuration. In an embodiment, considerations may include scheduling flexibility, supported modulation formats, and (SINR under the constrained power envelope. If the AI/ML model may predict that both uplink and downlink operations may be feasible, the gNB 104 may transmit an ACK to the AMF 112 and proceed with scheduling the UE 106 using the optimized power configuration. If the prediction outcome may indicate infeasibility, the gNB 104 may trigger a handover recommendation to the AMF 112 or request updated power weights from the AMF 112 or the ECF 114. Such an AI/ML-driven fallback mechanism may support intelligent, autonomous decision-making under fluctuating radio and resource conditions, allowing energy-efficient yet quality-aware operation at the gNB 104.
[0091] Therefore, the AI/ML model may be provided to understand the intricate relationships between network behaviour and energy use. The AI/ML-based approaches can create detailed energy profiles for each service, enable coordinated energy optimization between network elements and user devices, and improve base station selection by including energy considerations. Such advancements support proactive energy management and pave the way for more efficient and sustainable 5G and 6G wireless networks.
[0092] FIG. 3 illustrates an example flow chart 300 depicting a step-by-step energy-efficient UE-to-gNB assignment and scheduling procedure using an Artificial Intelligence AI/ Machine Learning (ML)-based power optimization in the network, in accordance with an embodiment of the present disclosure.
[0093] Referring to FIG. 3, at 302, the Energy Control Function (ECF) 114 may collect and may store power consumption values for both gNB (104, for downlink) and UE (106, for uplink) for each active service. This data may be recorded continuously to reflect real-time network usage and user activity. At 304, the ECF 114 may use the ML model to determine optimal power weights for each gNB 104 and UE 106. The ML model may predict these values by minimizing the total power usage across the network on a per-service basis, while ensuring the Quality of Service (QoS) may be maintained. At 306, the ECF 114 may transmit the optimal power values to the Access and Mobility Management Function (AMF 112). These values may correspond to the specific UE 106 and the candidate gNBs 104 that may be capable of handling the session based on energy efficiency. At 308, AMF 112 may transmit an N2 message request (e.g., 108B) to all base stations listed in the candidate set 104-1 to 104-N. This message may include the power values (uplink and downlink) computed by ECF 114, including the originally targeted gNB 104. At 310, each gNB 104 may evaluate whether the proposed power levels from the N2 message 108B may be adjusted within the current energy constraints and operating conditions of the gNB 104. At 312, if the gNB 104 may adjust to the given power levels, the gNB 104 may transmit an Acknowledgment (ACK) back to AMF 112. Further, at 312, upon receiving the ACK, the AMF 112 may attach the UE 106 to the current gNB 104 that may have confirmed its capability to operate with the given power configuration.
[0094] At 314, if the gNB 104 may not meet the power constraints, the gNB 104 may transmit a Negative Acknowledgment (NACK) to the AMF 112. At 316, the AMF 112 may invoke AI/ML models to evaluate alternate candidate gNBs 104. The decision may be based on the path loss profile and historical or real-time energy profile of the UE 106 with respect to different gNBs 104. AMF 112 may then transmit a new N2 message 108B to the next optimal gNB 104 based on this updated analysis. At 318, if any gNB 104 may respond with a positive ACK from the earlier requests (step 308), AMF 112 may consider those gNBs 104 as viable candidates. At 320, the AMF 112 may schedule the UE 106 using one of the gNBs 104 that may have responded with a positive ACK. This selection may be made based on the most energy-efficient and performance-optimized option available from the ACK-responding gNBs 104. At 322, if no gNB 104 may transmit a positive ACK, the AMF 112 may switch to a traditional base station assignment method. The AMF 112 may then assign the UE 106 to a gNB 104 based on legacy criteria such as, but not limited to signal strength, network traffic conditions, existing load, or similar factors, without considering AI-based power optimization.
[0095] FIG. 4 illustrates an example sequential diagram 400 depicting the energy information exchange flow between the gNB 104 (Next Generation NodeB) and the ECF 114, in accordance with an embodiment of the present disclosure.
[0096] Referring to FIG. 4, at 402, the gNB 104 may estimate energy consumed per service based on parameters such as current traffic load, transmission power, user profile, QoS metrics, and per-UE service activity. This estimation may include collecting gNB- and UE-specific values such as gNB ID, UE ID, power modes, 5G QoS Identifier (5QI), Modulation and Coding Scheme (MCS), a Transport Block Size (TBS), and more. At 404, the gNB 104 may transmit an energy information request message to the ECF 114. This message may initiate the communication and may include a request for energy optimization parameters or permission to upload energy data per service.
[0097] At 406, the ECF 114 may respond with an energy information response message, which may contain either an ACK if the energy information is acceptable or a NACK if the parameters may need modification or the request is rejected. The ACK may confirm that the ECF 114 is ready to receive or process configuration, whereas a NACK may indicate missing or inconsistent data.
[0098] At 408, after a successful ACK, the ECF 114 may transmit a parameter configuration request message to the gNB 104. This parameter configuration request message may contain optimized parameters calculated based on the ML model and policy rules stored within the ECF 114. The parameters may include optimal values for gNB downlink (DL) power, UE uplink (UL) power, Aggregate Maximum Bit Rate (AMBR) settings, or new QoS configurations. At 410, the gNB 104 may respond with a parameter response message. At 412, the gNB 104 may transmit a notify message to the ECF 114, indicating that one or more parameters may have been successfully changed in the gNB for energy optimization. This message may act as a final report before activation of the new configurations. At 414, the ECF 114 may acknowledge the notification by transmitting an ACK message.
[0099] In an embodiment, an HTTP-based interface may be used for energy data reporting from a gNB (gNodeB, 104) to the ECF 114. This procedure may support periodic transmission of energy and traffic parameters using a secure and reliable Transmission Control Protocol (TCP) connection. Each POST request may be formatted in JavaScript Object Notation (JSON) and may contain detailed per-UE 106 energy metrics measured during a specific reporting interval. As per the HTTP protocol-based interface, the gNB 104 and ECF may establish a TCP session. Within this session, the gNB 104 may periodically transmit energy usage reports to the ECF using HTTP POST messages. Each message may include parameters such as gNB-ID, UE-ID, gNB downlink power, UE uplink power, gNB type, power modes, 5QI, Transport Block Size (TBS), a Modulation and Coding Scheme (MCS), UE-Aggregated Maximum Bit Rate (AMBR), user-type, and the reporting time interval. The ECF 114 may receive and parse these POST requests to update its internal energy database and to inform AI-based optimization processes.
[00100] Further, the TCP session may be established between the gNB 104 and the ECF 114. This may provide a reliable connection channel for subsequent HTTP-based communication. Furthermore, the gNB 104 may enter a loop where periodic energy reporting may be scheduled based on a preconfigured interval. Further, the gNB 104 may transmit a POST energy-data HTTP/1.1 request to the ECF 114. This request may include an Internet Protocol (IP) address of the ECF 114 server. Further, the HTTP header may include the target Host field populated with the ECF's 114 IP address. Further, the content-type may be declared as application/JSON, indicating that the body of the request may be formatted in JSON. The JSON payload may begin. Further, the gNB-ID may be transmitted, uniquely identifying the base station (gNB 104) generating the report.
[00101] Table 2 may represent a structured view of energy and traffic parameters that may be exchanged between a gNB 104 and the ECF 114 to support energy-efficient operation in the network. Each row in the table may correspond to a unique reporting instance for a particular UE 106 and the data may be collected by the EMU 120 embedded within the gNB 104. The parameters may be periodically transmitted to the ECF 114, where the EDM 212 may store the parameters for analysis and optimization. The gNB ID may uniquely identify each gNB 104 in the network. The UE ID may serve as a unique reference to the UE 106 connected to the gNB 104. The 5QI value may indicate the type of quality of service associated with the service flow for the UE 106. The gNB type may describe the deployment scenario of the gNB 104, such as macro, micro, or small cell configurations. The gNB DL power may indicate the power level used by the gNB 104 to transmit data to the UE 106, whereas the UE uplink power may represent the power used by the UE 106 to transmit data to the gNB 104. The gNB Power Mode may reflect whether the gNB 104 is in an active or sleep state, and the UE Power Mode may classify the UE’s 106 energy operation level as low, medium, or normal.
[00102] The TBS may represent the data volume transmitted in a single scheduling unit, and a Modulation and Coding Scheme (MCS) may specify the modulation format and coding rate used for transmission, which may affect both spectral efficiency and power consumption. The UE AMBR may define the maximum data rate allocated to the UE 106 across its active flows, and the user type may identify the category of the user, such as premium, regular, or IoT-based, which may influence scheduling and power policies. The EMU 120 may measure all such parameters continuously and may forward them to the ECF114 for centralized processing. Within the ECF 114, the EDM 212 may collect and organize the data for use in AI-based models that may predict optimal power configurations and enforce energy-saving decisions. Table 2 may represent the structured format in which the EDM 212 may store the collected information to support learning and policy management processes.

Table 2
[00103] FIG. 5 illustrates an example sequential diagram 500 depicting an interaction between the ECF and the EDM (e.g., 212 as represented in FIG. 2), in accordance with an embodiment of the present disclosure.
[00104] Referring to FIG. 5, for retrieving and updating service-specific energy parameters, the interaction between the ECF 114 and the EDM 212 supports real-time and historical energy policy decisions for optimizing power usage across gNBs 104 and UEs 106. At 502, the ECF 114 may initiate a query message to the EDM 212. The query message may contain identifying parameters such as UE ID, gNB ID, and 5QI. The parameters included in the message may uniquely define the user equipment, the serving base station, and the associated quality of service level for which energy-related data may be requested. At 504, EDM 212 may respond with a data message. The data message may contain relevant energy parameters associated with the specified combination of UE 106, gNB 104, and 5QI. The energy parameters in the response may include power modes, historical energy usage patterns, base station and user equipment power levels, and other statistics related to service-level consumption. At 506, the ECF 114 may transmit an update/notify message to EDM 212. The update/notify message may indicate that energy parameters may have been updated based on outputs from ML inference, revisions in power policy, or feedback observed from live network operation. EDM 212 may use this message to synchronize the internal energy database with the latest optimized parameters. At 508, the EDM 212 may ACK to confirm successful receipt and storage of the updated energy parameters, thereby maintaining consistency between the decision-making functionality provided by ECF 114 and the historical energy dataset stored in the EDM 212.
[00105] FIG. 6 illustrates a flow chart of an example method 600 of an initial attach procedure for the UE 106 during the boot-up stage, in accordance with an embodiment of the present disclosure.
[00106] Referring to FIG. 6, at 602, the UE 106 may initiate the attach procedure. During the initial attach phase, the UE 106 may provide context information to the network, which may include the UE power mode (such as low, medium, or high), subscription type (such as premium, normal, or best effort), and previous gNB information (such as the last connected gNB (e.g., 104-2 as represented in FIG. 1) before power-off or handover). This information may be forwarded to the Access and Mobility Management Function (AMF 112) for context processing.
[00107] At 604, the AMF 112 may process the UE context and may forward the information received from the UE 106 to the ECF 114. This transfer of context information may allow the ECF 114 to begin preparing power optimization strategies based on historical or real-time data associated with the UE 106 and gNB 104-2. At 606, the ECF 114 may execute an AI/ML-based power optimization model. The model may use the Physical Random Access Channel (PRACH) power from the UE 106 as an indicator of uplink signal strength. Based on this and other contextual inputs, the model may predict: X, which may be the optimal gNB (e.g., 104-5 as represented in FIG. 1) downlink power weight, and Y, which may be the optimal UE (106) uplink power weight. Both weights may be estimated on a per-service basis, minimizing energy consumption while maintaining the required QoS and the user classification.
[00108] At 608, the ECF 114 may distribute the predicted power weights. The X value may be transmitted to the corresponding gNB 104-2 for configuring the downlink transmission power. The Y value may be transmitted to the UE 106 via the AMF 112, guiding the uplink power level. The AMF 112 may also be updated with both values to support coordinated scheduling and mobility decision-making.
[00109] At 610, the gNB 104 may evaluate the received power configuration. If the gNB 104 may be capable of operating with the predicted power levels based on current load, interference, and hardware availability, the ACK may be returned to the AMF 112. If the configuration may not be supported, the NACK may be transmitted to the AMF 112, indicating that power constraints may prevent continued service corresponding to the parameters.
[00110] At 612, upon receiving an ACK from the gNB 104, the AMF 112 may proceed to schedule the UE 106 with that gNB 104-2, applying the energy-optimized configuration provided by the ECF 114. The UE 106 may then begin standard network operations under the adjusted power profile. At 614, if the NACK may be received from the gNB 104-2, a handover request may be initiated. The gNB 104 may transmit the request to the AMF 112, indicating that energy and performance constraints may prevent continued support for the UE 106 under the settings. At 616, the AMF 112 may select an alternative gNB 104-5 to serve the UE 106. The decision may be based on real-time load conditions at candidate gNBs 104-5, the type of service being requested by the UE 106 (such as voice, video, or URLLC), and the predicted power weights X and Y calculated by the ECF 114. Once an optimal gNB 104-5 is identified, the AMF 112 may forward scheduling instructions to the new gNB 104-5 and may notify the UE 106 accordingly.
[00111] FIG. 7 illustrates an exemplary flow diagram for implementing a method 700 for managing the power consumption in the network, in accordance with embodiments of the present disclosure.
[00112] Referring to FIG. 7, at 702, the method 700 may include receiving, by the processor (e.g., 204 as represented in FIG. 2 associated with the system 202 as represented in FIG. 2), the change in service request message from the UE 106 while the UE 106 is in communicating with a base station 104. At 704, the method 700 may include predicting, by the processor 204, the target power value for the UE 106 and the base station 104 based on tracked power consumption data corresponding to the data transmission between the UE 106 and the base station 104, in response to the reception of the change in service request message.
[00113] For predicting, by the processor 204, the target power value for the UE 106 and the base station 104, the method 700 may include predicting, by the processor 204, an uplink power weight for the UE 106 and a downlink power weight for the base station 104 using an Artificial Intelligence (AI) model based on UE-related parameters, base station-related parameters, and the power consumption data, wherein the AI model is configured in the processor 204 and predicting, by the processor 204, a total power consumption corresponding to each service based on the predicted uplink power weight and downlink power weight. Further, the method 700 may include predicting, by the processor 204, the target power value based on the total power consumption.
[00114] At 706, the method 700 may include transmitting, by the processor 204, the power configuration request message to at least one candidate base station 104 (e.g., 104-5 as represented in FIG. 1) based on the prediction. At 708, the method 700 may include receiving, by the processor 204, the positive acknowledgement message from the at least one candidate base station 104-5 in response to the transmission of the power configuration request message. At 710, the method 700 may include establishing, by the processor 204, the communication between the UE 106 and the at least one candidate base station 104 in real time for the data transmission in response to the reception of the positive acknowledgement message.
[00115] FIG. 8 illustrates an exemplary computer system 800 in which or with which embodiments of the present disclosure may be utilized in accordance with embodiments of the present disclosure.
[00116] As shown in FIG. 8, the computer system 800 may include an external storage device 810, a bus 820, a main memory 830, a read-only memory 840, a mass storage device 850, a communication port(s) 860, and a processor 870. A person skilled in the art will appreciate that the computer system 800 may include more than one processor 870 and communication ports 860. The processor 870 may include various modules associated with embodiments of the present disclosure. The communication port(s) 860 may be any of an RS-232 port for use with a modem-based dial-up connection, a 10/100 Ethernet port, a Gigabit or 10 Gigabit port using copper or fiber, a serial port, a parallel port, or other existing or future ports. The communication ports(s) 860 may be chosen depending on a network, such as a Local Area Network (LAN), Wide Area Network (WAN), or any network to which the computer system 800 connects.
[00117] In an embodiment, the main memory 830 may be a Random Access Memory (RAM), or any other dynamic storage device commonly known in the art. The read-only memory 840 may be any static storage device(s) e.g., but not limited to, a Programmable Read Only Memory (PROM) chip for storing static information e.g., start-up or basic input/output system (BIOS) instructions for the processor 870. The mass storage device 850 may be any current or future mass storage solution, which can be used to store information and/or instructions. Exemplary mass storage solutions include, but are not limited to, Parallel Advanced Technology Attachment (PATA) or Serial Advanced Technology Attachment (SATA) hard disk drives or solid-state drives (internal or external, e.g., having Universal Serial Bus (USB) and/or Firewire interfaces).
[00118] In an embodiment, the bus 820 may communicatively couple the processor(s) 870 with the other memory, storage, and communication blocks. The bus 820 may be, e.g., a Peripheral Component Interconnect PCI)/PCI Extended (PCI-X) bus, Small Computer System Interface (SCSI), USB, or the like, for connecting expansion cards, drives, and other subsystems as well as other buses, such a front side bus (FSB), which connects the processor 870 to the computer system 800.
[00119] In another embodiment, operator and administrative interfaces, e.g., a display, keyboard, and cursor control device may also be coupled to the bus 820 to support direct operator interaction with the computer system 800. Other operator and administrative interfaces can be provided through network connections connected through the communication port(s) 860. Components described above are meant only to exemplify various possibilities. In no way should the aforementioned exemplary computer system 800 limit the scope of the present disclosure.
[00120] While considerable emphasis has been placed herein on the preferred embodiments, it will be appreciated that many embodiments can be made and that many changes can be made in the preferred embodiments without departing from the principles of the disclosure. These and other changes in the preferred embodiments of the disclosure will be apparent to those skilled in the art from the disclosure herein, whereby it is to be distinctly understood that the foregoing descriptive matter is to be implemented merely as illustrative of the disclosure and not as a limitation.

ADVANTAGES OF THE PRESENT DISCLOSURE
[00121] The present disclosure provides an energy-aware gNB selection and handover mechanism that minimizes power consumption while maintaining service quality.
[00122] The present disclosure enables intelligent UE attachment by predicting optimal uplink and downlink power values using Artificial Intelligence (AI)/Machine Learning (ML) models.
[00123] The present disclosure ensures efficient and seamless handovers by leveraging energy profiles to select suitable base stations.
, Claims:1. A system (202) for establishing communication between a User Equipment (UE) and a base station at a boot-up stage of the UE, comprising:
a processor (204); and
a memory (206) operatively coupled to the processor (204), wherein the memory (206) comprises processor-executable instructions, which on execution, cause the processor (204) to:
receive UE-related parameters from the UE, via an initial base station, from which the UE receives beamforming signals, after the boot-up stage of the UE, and simultaneously receive base station-related parameters from the initial base station;
determine historical information associated with the UE and current power-related information associated with the UE based on the UE-related parameters;
predict a target power value for the UE and for the initial base station based on the historical information, the current power-related information, and the UE-related parameters;
select at least one base station from a list of candidate base stations based on the predicted target power value;
transmit a power configuration request message to the at least one base station;
receive a positive acknowledgement message from the at least one base station in response to the transmission of the power configuration request message; and
establish the communication between the UE and the at least one base station in real time for the data transmission in response to the reception of the positive acknowledgement message.

2. The system (202) as claimed in claim 1, wherein the historical information comprises at least one of: information of a power consumption corresponding to each base station previously connected to the UE, information of a type of content involved in the data transmission with each previously connected base station, information of a power mode, information of a service type, information of a subscription type, information of a updated path loss profile, information of an energy profile, information of a Quality of Service (QoS) threshold, information of uplink power, information of a transport block size, information of a network load, information of a modulation and coding scheme, information of a updated channel quality indicator, information of a location of the UE with respect to the base station, and information of a UE aggregate maximum bit rate.

3. The system (202) as claimed in claim 1, wherein to predict the target power value, the processor (204) is configured to:
predict an uplink power weight for the UE and a downlink power weight for the initial base station using an Artificial Intelligence (AI) model based on the UE-related parameters, the historical information, the current power-related information, the base station-related parameters associated with the initial base station, and wherein the AI model is configured in the processor (204);
predict a total power consumption corresponding to each service of the UE based on the predicted uplink power weight and downlink power weight; and
predict the target power value based on the total power consumption.

4. The system (202) as claimed in claim 3, wherein to transmit the power configuration request message, the processor (204) is configured to:
determine that the predicted target power value does not exceed a power threshold corresponding to each service and simultaneously determine that the predicted target power value is above a Quality of Service (QoS) threshold corresponding to each service; and
transmit the power configuration request message to the at least one base station when the target power value does not exceed the power threshold and simultaneously transmit the power configuration request message to the at least one base station when the target power value is above the QoS threshold.

5. The system (202) as claimed in claim 1, wherein to select the at least one base station, the processor (204) is configured to:
fetch the list of candidate base stations from the database, wherein the list of candidate base stations comprises the initial base station;
compare the UE-related parameters with base station-related parameters associated with the initial base station upon fetching the list of candidate base stations;
determine the at least one base station from among the list of candidate base stations based on the comparison;
determine that a power consumption is dynamically adjusted in the at least one base station with respect to the target power value; and
select the at least one base station based on the determination that the power consumption is dynamically adjusted in the at least one base station.

6. The system (202) as claimed in claim 1, wherein upon transmitting the power configuration request message to the at least one base station, the processor (204) is configured to:
determine whether the positive acknowledgement message is received from the at least one base station or a negative acknowledgement message is received from the at least one base station; and
perform one of:
determine at least one subsequent base station from among the list of candidate base stations based on the comparison when the negative acknowledgement message is received from the at least one base station and transmit the power configuration request message to the at least one subsequent base station to establish the communication between the UE and the at least one subsequent base station; or
establish the communication between the UE and the at least one base station when the positive acknowledgement message is received from the at least one base station, wherein the processor (204) is configured to check for at least one other subsequent base station from among the list of candidate base stations based on the comparison until the positive acknowledgement message is received from any one of the base stations among the list of candidate base stations.

7. A system (202) for establishing communication between a User Equipment (UE) and a base station at a boot-up stage of the UE, comprising:
a processor (204); and
a memory (206) operatively coupled to the processor (204), wherein the memory (206) comprises processor-executable instructions, which on execution, cause the processor (204) to:
receive UE-related parameters from the UE, after the boot-up stage of the UE, upon transmitting beamforming signals;
fetch historical information associated with the UE and current power-related information associated with the UE from an external database, in response to the reception of the UE-related parameters;
predict a target power value for the UE and for the system (202) based on the historical information, the current power-related information, and the UE-related parameters;
select at least one base station from a list of candidate base stations based on the predicted target power value, wherein the list of candidate base stations comprises the system (202);
transmit a power configuration request message to the at least one base station;
receive a positive acknowledgement message from the at least one base station in response to the transmission of the power configuration request message; and
establish the communication between the UE and the at least one base station in real time for the data transmission in response to the reception of the positive acknowledgement message.

8. A system (202) for managing power consumption in a network, comprising:
a processor (204); and
a memory (206) operatively coupled to the processor (204), wherein the memory (206) comprises processor-executable instructions, which on execution, cause the processor (204) to:
receive a change in service request message from the UE while the UE is in communicating with a base station;
predict a target power value for the UE and the base station based on tracked power consumption data corresponding to a data transmission between the UE and the base station, in response to the reception of the change in service request message;
transmit a power configuration request message to at least one candidate base station based on the prediction;
receive a positive acknowledgement message from the at least one candidate base station in response to the transmission of the power configuration request message; and
establish the communication between the UE and the at least one candidate base station in real time for the data transmission in response to the reception of the positive acknowledgement message.

9. The system (202) as claimed in claim 8, wherein to track the power consumption data, the processor (204) is configured to:
track the data transmission between the UE and the base station based on UE-related parameters and base station-related parameters; and
determine the power consumption data, corresponding to the data transmission, with respect to the UE-related parameters and the base station-related parameters.

10. The system (202) as claimed in claim 8, wherein to predict the target power value for the UE and the base station, the processor (204) is configured to:
predict an uplink power weight for the UE and a downlink power weight for the base station using an Artificial Intelligence (AI) model based on UE-related parameters, base station-related parameters, and the power consumption data, wherein the AI model is configured in the processor (204);
predict a total power consumption corresponding to each service based on the predicted uplink power weight and downlink power weight; and
predict the target power value based on the total power consumption.

11. The system (202) as claimed in claim 9, wherein the UE-related parameters comprise at least one of: an identity of the UE, a type of content involved in the data transmission, a power mode, a service type, a subscription type, a path loss profile, an energy profile, a Quality of Service (QoS) threshold, uplink power, a transport block size, a network load, a modulation and coding scheme, a channel quality indicator, a location of the UE with respect to the base station, and a UE aggregate maximum bit rate.

12. The system (202) as claimed in claim 9, wherein the base station-related parameters comprise at least one of: an identity of the base station, a type of the base station, historical power usage patterns, a power mode, downlink power, a transport block size, a modulation and coding scheme, a location of the base station with respect to the UE, a network load, a current power level of the base station during the data transmission, a number of resource elements allocated to the UE, and information related to whether the base station is operating in micro sleep mode to conserve energy.

13. The system (202) as claimed in claim 10, wherein the processor (204) is configured to dynamically update the predicted uplink power weight with respect to UE-related parameters and the predicted downlink power weight with respect to the base station-related parameters in real time.

14. The system (202) as claimed in claim 10, wherein to transmit the power configuration request message, the processor (204) is configured to:
determine that the predicted target power value does not exceed a power threshold corresponding to each service and simultaneously determine that the predicted target power value is above a Quality of Service (QoS) threshold corresponding to each service; and
transmit the power configuration request message to the at least one candidate base station when the target power value does not exceed the power threshold and simultaneously transmit the power configuration request message to the at least one candidate base station when the target power value is above the QoS threshold.

15. The system (202) as claimed in claim 8, wherein to transmit the power configuration request message, the processor (204) is configured to:
fetch a list of candidate base stations from a database associated with the system (202), wherein the list of candidate base stations comprises the base station;
compare the UE-related parameters with the base station-related parameters associated with each candidate base station upon fetching the list of candidate base stations;
determine the at least one candidate base station from among the list of candidate base stations based on the comparison;
determine that a power consumption is dynamically adjusted in the at least one candidate base station with respect to the target power value; and
transmit the power configuration request message to the at least one candidate base station based on the determination that the power consumption is dynamically adjusted in the at least one candidate base station.

16. The system (202) as claimed in claim 15, wherein upon transmitting the power configuration request message to the at least one candidate base station, the processor (204) is configured to:
determine whether the positive acknowledgement message is received from the at least one candidate base station or a negative acknowledgement message is received from the at least one candidate base station; and
perform one of:
determine at least one subsequent candidate base station from among the list of candidate base stations based on the comparison when the negative acknowledgement message is received from the at least one candidate base station and transmit the power configuration request message to the at least one subsequent candidate base station to establish the communication between the UE and the at least one subsequent candidate base station; or
establish the communication between the UE and the at least one candidate base station when the positive acknowledgement message is received from the at least one candidate base station, wherein the processor (204) is configured to check for at least one other subsequent candidate base station from among the list of candidate base stations based on the comparison until the positive acknowledgement message is received from any one of the base stations among the list of candidate base stations.

17. The system (202) as claimed in claim 16, wherein to establish the communication between the UE and the at least one candidate base station, the processor (204) is configured to:
transmit a handover request message to the at least one candidate base station, requesting the at least one candidate base station to allocate resources for the UE;
simultaneously transmit a handover command to the base station to halt the communication with the UE, upon transmitting the handover request message;
receive an acknowledgement handover notification from the at least one candidate base station, indicating successful communication establishment between the UE and the at least one candidate base station, in response to the transmission of the handover request message;
transmit a context release command to the base station to release a context of the UE and resources associated with the UE, upon receiving the acknowledgement handover notification from the at least one candidate base station; and
receive a context release complete message from the base station, in response to the transmission of the context release command, wherein the context release complete message indicates successful release of the context of the UE and the resources.

18. A method (700) for managing power consumption in a network, comprising:
receiving (702), by a processor (204) associated with a system (202), a change in service request message from the UE while the UE is in communicating with a base station;
predicting (704), by the processor (204), a target power value for the UE and the base station based on tracked power consumption data corresponding to a data transmission between the UE and the base station, in response to the reception of the change in service request message;
transmitting (706), by the processor (204), a power configuration request message to at least one candidate base station based on the prediction;
receiving (708), by the processor (204), a positive acknowledgement message from the at least one candidate base station in response to the transmission of the power configuration request message; and
establishing (710), by the processor (204), the communication between the UE and the at least one candidate base station in real time for the data transmission in response to the reception of the positive acknowledgement message.

19. The method (700) as claimed in claim 18, wherein for predicting (704), by the processor (204), the target power value for the UE and the base station, the method (700) includes:
predicting, by the processor (204), an uplink power weight for the UE and a downlink power weight for the base station using an Artificial Intelligence (AI) model based on UE-related parameters, base station-related parameters, and the power consumption data, wherein the AI model is configured in the processor (204);
predicting, by the processor (204), a total power consumption corresponding to each service based on the predicted uplink power weight and downlink power weight; and
predicting, by the processor (204), the target power value based on the total power consumption.