Description:RESERVATION OF RIGHTS
[0001] A portion of the disclosure of this patent document contains material which is subject to intellectual property rights such as, but are not limited to, copyright, design, trademark, integrated circuit (IC) layout design, and/or trade dress protection, belonging to Jio Platforms Limited (JPL) or its affiliates (hereinafter referred as owner). The owner has no objection to the facsimile reproduction by anyone of the patent document or the patent disclosure, as it appears in the Patent and Trademark Office patent files or records, but otherwise reserves all rights whatsoever. All rights to such intellectual property are fully reserved by the owner.

TECHNICAL FIELD
[0002] The present disclosure generally relates to telecommunication networks. In particular, the present disclosure relates to a system and a method for exposing radio access network (RAN) entities to artificial intelligence entities.

BACKGROUND
[0003] The following description of 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 be used only to enhance the understanding of the reader with respect to the present disclosure, and not as admissions of prior art.
[0004] A rapid evolution from Fourth Generation (4G) to Fifth Generation (5G) communication technology has introduced significant advancements in data speeds, latency reduction, and network reliability. As the deployment of 5G continues, a forthcoming Sixth Generation (6G) wireless system is expected to be deployed. Anticipated to leverage artificial intelligence (AI) extensively, 6G aims to resolve key challenges posed by 5G and expand capabilities in terms of system capacity, data rates, latency minimization, and quality of service (QoS).
[0005] The current transition to 5G has showcased advancements such as the 5G Core Network’s Network Data Analytics Function (NWDAF), enhancing network automation, and service orchestration through real-time insights and predictive analytics. Additionally, the open-Radio Access Network (RAN) intelligent controller (RIC), developed by the O-RAN consortium, introduces the AI and the machine learning (ML) into radio resource management, enabling dynamic and efficient network operations. Currently, integrating AI with 6G, across various network nodes is crucial. Also, various privacy concerns related to AI data processing and affordability challenges in deploying highly intelligent networks are among the pivotal issues that need to be addressed. The evolving standards within Third Generation Partnership Project (3GPP) highlight a need for robust AI/ML model transfer mechanisms within the telecommunication networks for emphasizing distributed learning and inference capabilities. Currently, there is a need for RANs that embeds AI functionalities across network nodes/entities/functions, and/or make AI functionality accessible to all network nodes/entities/functions through an interface. Existing solutions are unable to process data seamlessly and unable to interact among multiple AI elements. Further, existing networks also do not provide an end-to-end solution for receiving, storing, and processing RAN data for training and using AI entities for inference in real-time.
[0006] There is, therefore, a need for a system and a method for enabling RAN entities to use and leverage the capabilities of AI entities, and overcome the deficiencies in the prior art(s).

OBJECTS OF THE PRESENT DISCLOSURE
[0007] Some of the objects of the present disclosure, which at least one embodiment herein satisfies are listed below.
[0008] An object of the present disclosure is to provide a system and a method for an artificial intelligence (AI) driven data processing in a radio access network (RAN).
[0009] Another object of the present disclosure is to provide a system and method that is able to process data seamlessly and interact with multiple AI elements.
[0010] Another object of the present disclosure is to provide a system that masks/hides sensitive information for training AI entities, and using AI entities for inference.
[0011] Another object of the present disclosure is to provide a system that allows for distributed or federated computation.
[0012] Another object of the present disclosure is to provide a system that enables interaction with third-party applications functions.

SUMMARY
[0013] 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.
[0014] In an aspect, the present disclosure relates to a system for exposing radio access network (RAN) entities to artificial intelligence (AI) entities. The system includes one or more processors and a memory. The memory is operatively coupled with the processors. The memory stores instructions which, when executed by the processors, cause the processors to retrieve a RAN event report from a RAN data repository (RDR). The RAN event report includes at least one of, RAN data, or RAN analytics data subscribed by the RAN entities. The RAN analytics data is generated by an AI entity based on the RAN data stored in RDR. The processors also transmit the RAN event report to the RAN entities.
[0015] In an embodiment, the RAN entities may be at least one of, one or more RAN nodes, one or more network functions, or a third-party application function. The RAN nodes may be at least one of, a radio unit (RU), distributed unit (DU), and central unit (CU).
[0016] In an embodiment, the RDR may be configured to store the RAN data received from the one or more RAN nodes through a RAN data management (RDM) entity.
[0017] In an embodiment, the processors may be configured to retrieve and transmit the RAN event report from the RDR in response to a request from the one or more RAN entities.
[0018] In an embodiment, the processors may be configured to receive the request from the one or more RAN entities to subscribe to at least one of, the RAN data or the RAN analytics data. The processors may also configured to authorize the one or more RAN entities, and associate the one or more RAN entities with a trigger event and a requester identity. Further, the processors may be configured to transmit a data subscription request to the RDM entity. The data subscription request includes the request received from the one or more RAN entities. The processors may be configured to transmit a response to the one or more RAN entities to acknowledge the request on receiving a data subscription response from the RDM entity. The data subscription response may be received when the RDM entity subscribes to the one or more RAN nodes that are configured to transmit the RAN data to the RDM entity on occurrence of the trigger event. The RDM entity may be configured to process, filter, and/or store the RDM data in the RDR.
[0019] In an embodiment, the RAN event report may be received from the RDM entity after the RDM entity stores the RAN event report in the RDR.
[0020] In an embodiment, the AI entity may be implemented within at least one of: the RDR, a third-party application function, or an external federation entity.
[0021] In an embodiment, the RAN event report may be transmitted to any or a combination of, the RAN entities, a third-party application function, and an external federation entity, where the third-party application function and the external federation entity may be configured to process the RAN event report and transmit the processed RAN event report to the one or more RAN entities.
[0022] In an aspect, the RAN event report is transmitted through a meta data structure.
[0023] In an aspect, the processor may be configured to mask network sensitive and/or user sensitive data from the RAN event report.
[0024] In an aspect, the present disclosure relates to a method for exposing RAN entities to AI entities. The method includes retrieving, a RAN event report from a RDR, wherein the RAN event report includes at least one of, RAN data, or RAN analytics data. The RAN analytics data may be generated by an AI entity based on the RAN data stored in the RDR. The method also includes transmitting, the RAN event report to one or more RAN entities. The RAN entities are application functions corresponding to one or more RAN nodes.

BRIEF DESCRIPTION OF DRAWINGS
[0025] The accompanying drawings, which are incorporated herein, and constitute a part of the present disclosure, illustrate exemplary embodiments of the disclosed methods and systems in 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 the disclosure of such drawings includes the disclosure of electrical components, electronic components, or circuitry commonly used to implement such components.
[0026] FIGs. 1A-1B illustrate example architectures implementing a system in a radio access network (RAN), in accordance with an embodiment of the present disclosure.
[0027] FIG. 2 illustrates an example block diagram of the system, in accordance with an embodiment of the present disclosure.
[0028] FIG. 3 illustrates a flow diagram for implementing a method for exposing RAN entities to artificial intelligence (AI) entities, in accordance with an embodiment of the present disclosure.
[0029] FIG. 4 illustrates an example block diagram representing a RAN, in accordance with the embodiments of the present disclosure.
[0030] FIG. 5 illustrates an exemplary computer system in which or with which embodiments of the present disclosure may be implemented, in accordance with embodiments of the present disclosure.
[0031] The foregoing shall be more apparent from the following more detailed description of the disclosure.

DETAILED DESCRIPTION
[0032] 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.
[0033] 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 scope of the disclosure as set forth.
[0034] 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.
[0035] 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.
[0036] 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.
[0037] 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.
[0038] 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.
[0039] In an aspect, the present disclosure provides a method and a system that incorporates a framework to support artificial intelligence (AI) and machine learning (ML) models in a Radio Access Network (RAN). The system and the method include retrieving a RAN event report from a RAN data repository (RDR), where the RAN event report includes at least one of a timestamp, RAN data, or RAN analytics data. The RAN analytics data may be generated by an AI entity based on the RAN data stored in RDR. The method also includes transmitting, the RAN event report to one or more RAN entities.
[0040] Various embodiments of the present disclosure will be explained in detail with reference to FIGs. 1A-5.
[0041] FIGs. 1A-1B illustrate example architectures (100A, 100B) that implements a system (110), in accordance with an embodiment of the present disclosure. As shown, the architecture (100A, 100B) may include a RAN (102) being configured to provide services to one or more user equipment (UEs) (not shown). The RAN (102) may include a plurality of RAN entities such as RAN entities (302) shown in FIG. 3. The RAN entities (302) may include application functions or network functions/entities (hereafter used interchangeably), but not be limited thereto. Each of the RAN entities (302) may include a corresponding processor configured to execute processor-executable instructions that cause the RAN entities (302) to perform a predetermined function. In some embodiments, the RAN entities (302) may be disposed within the RAN (102), or communicatively coupled to the RAN (102). The RAN entities (302) may be configured to interact with each other (such as through use of Application Programming Interfaces (APIs), for example) either directly or through the system (110), and provide services to the UEs in an efficient and/or optimal manner.
[0042] In some embodiments, the RAN (102) may be configured to have network exposure functions configured to communicate with one or more of the RAN entities (302). The RAN entities (302) may include or network entities/functions, such as one or more RAN nodes, network functions associated with a core network (such as core network (124)), Enhanced Data rates for Global System for Mobile Communications (GSM) Evolution (EDGE) (120), third party application functions (122), RAN data repository (RDR) (126), and the like, but not limited thereto. In an embodiment, the one or more RAN nodes may be at least one of a radio unit (RU) (118), distributed unit (DU) (116), and central unit (CU) (114). In some embodiments, the RAN entities (302) may be consumers of RAN data. In other embodiments, the RAN entities (302) may be producers of the RAN data. In further embodiments, the RAN entities (302) may be both consumers and producers of RAN data (such as the RAN nodes as described below).
[0043] The RAN (102) may also include the system (110) configured to aggregate and facilitate exchange of data between components associated with the RAN (102). In some embodiments, the system (110) may be implemented as a standalone network exposure function/entity, as shown in FIG. 1A. In other embodiments, the system (110) may be implemented in a distributed manner, as shown in FIG. 1B. In such embodiments, each of the RAN nodes may include a corresponding exposure function associated therewith, such as CU exposure function (CEF) (130), DU exposure function (DEF) (134), and RU exposure function (RUEF) (138). In some embodiments, the system (110) may be implemented within a network entity, such as those associated with the core network (124).
[0044] In some embodiments, the system (110) may be configured to communicate with different RAN entities (302). For example, the system (110) may be configured to communicate with application function, such as CU application function (CUAF) (128), DU application function (DUAF) (132), and RU application function (hereafter referred to as L1AF) (136), but not limited thereto. In other embodiments, the system (110) may be configured to serve as a hub for facilitating communication between multiple RAN entities (302).
[0045] In some embodiments, the CEF (130) may be configured to operate as an exposure function in relation to CU (114), which may or may not co-located with CU (114). In an embodiment, the CEF (130) may expose the capabilities of the CU (114) to the CUAF (128). The CEF (130) may enable both the CU (114) and the CUAF (128) to retrieve/generate/process relevant RAN data, and inferences from the RAN data generated by AI entities, for optimizing like application functions corresponding to a Self-Orchestrating Network (SON) Application Function, a Radio Resource Management (RRM), and/or other intelligent functionalities. In an embodiment, one or more application functions may be integrated with the CU (114) dynamically via the CEF (130). In an embodiment, the CEF (130) may allow the CUAF (128) to offload RAN data processing or computation to external application functions, such as the third-party application function (122) or federation entities (not shown). The federation entities may be external computing entities to which computation of the application functions of the RAN entities or the AI entities may be offloaded. In another embodiment, the CU (114) may be configured to dynamically switch between the optimal usage of the CUAF (128) and the third-party application function (122) via the CEF (130).
[0046] Similarly, in other embodiments, the DEF (134) may function as an exposure function, which may or may not be co-located with DU (116). For exposing the capabilities of the DU (116) to the DUAF (132), both the DU (116) and the DUAF (132) may facilitate the exchange of relevant RAN data and inferences therefrom related to various functionalities such as layer 2 RRM (L2 RRM), massive multiple-input and multiple-output (MIMO), Intelligent Reflective Surface (IRS), Medium Access Control (MAC) Scheduler, sensing and other intelligent functionalities, and the like, but not limited thereto. Further, any third party application functions, such as the third-party application function (122) or the federation entities may be integrated with the DU (116) dynamically via the DEF (134). In an embodiment, the DU (116) may dynamically switch between the DUAF (132) via the DEF (134) for optimization of the usage and performance of the DU (116).
[0047] In another embodiment, the RUEF (138) may function as an exposure function, which may or may not be co-located with RU (118). The RUEF (138) may expose the capabilities of the RU (118) to the L1AF (136). The RUEF (138) may enable the L1AF (136) to exchange the RAN data and inferences therefrom related to functionalities such as including, but not limited to, Layer 1 (L1) signal functions, MIMO, IRS, sensing, RF control functions, various intelligence functionalities, and the like. In some embodiments, the application functions may be integrated with the RU (118) dynamically via the RUEF (138). In some embodiments, the RU (118) may dynamically switch between use of L1AF (126) and the third party application functions (122) or federation entities via the RUEF (138), for optimal usage thereof.
[0048] In some embodiments, the system (110) may be implemented as a distributed set of exposure functions, as described above in reference to RUEF (138), DEF (134) and CEF (130). In some embodiments, the system (110) may also include exposure functions implemented outside the RAN (102). In an embodiment, an EDGE Exposure Function (EDEF) (142) may be implemented to operate as an exposure function for the EDGE (120). The EDEF (142) may or may not co-located with the EDGE (120). Here, the EDEF (142) may expose the capabilities of the EDGE (120) to an EDGE server-related Application functions (EDAF) (140). In an embodiment, both the EDGE (142) and the EDAF (140) may be configured to exchange the RAN data and inferences therefrom related to functionalities such as including, but not limited to, enhanced ultra reliable low latency communication (eURLLC) applications. The eURLLC may include latency sensitive public safety applications, smart health services, smart automobile services, various intelligent functionalities, and the like. In an embodiment, the third-party application functions (122) may be integrated with the EDGE server (120) dynamically via the EDEF (142). Further, in an embodiment, the EDGE server (120) may dynamically switch between the optimal usage of the EDAF (140) and the third party application functions (122) via the EDEF (142).
[0049] The RAN (102) may allow the system (110) to be involved in data collection from all RAN nodes (or generally all RAN entities) and from the UEs, among other entities. In an embodiment, the RAN (102) may also include a RAN Data Management (RDM) entity (112) configured to enable storage and retrieval of data to and from the RDR (126). In some embodiments, the RDM (112) may be configured to determine if a data includes necessary information required for a specific use case, filter such data, and accordingly store the data into the RDR (126), for example. The RDM (112) may be configured to collect one or more UEs specific data as per the requests from the application functions corresponding to RAN entities (302), like SON/RRM for example. In an embodiment, the RDM (112) may also be configured to determine if any UE specific information is to be extracted from the RAN entities or if such information may be retrieved from the UEs, based on the requirements.
[0050] In some embodiments, the RAN node (102) may store data locally. In some embodiments, the RAN (102) includes the RDR (126), which stores the RAN data generated from the operation of the RAN (102). In some embodiments, RAN data may be any data which may be used for operating and/or optimizing operation of the RAN (102), or the RAN entities (302) thereof. Examples of RAN data may include, but not be limited to, subscriber data, cell unit data, policy data, UE data, session data, structure data for exposure, RAN application data, log data, and the like. In some embodiments, the RDR (126) may include a database/data lake (108) configured to store the RAN data. In some embodiments, the data lake (108) may be configured to store the RAN data in any or a combination of structured form, semi-structured form, or unstructured or raw form. The data lake (108) may be implemented as a centralized or distributed repository configured to store the RAN data. The data lake (108) may be implemented to include functionalities provided by “big data” storage providers, as may be known to those skilled in the art. In some embodiments, the RDR (126) may include a data access provider (104), which may be configured to operate as an interface between the data lake (108) and the RDM (112). In an embodiment, the data access provider (104) is configured to access specific data sets by the RAN data consumers from the RDR (126), as well as operator specific data for each data set, based on requirements. By collecting and storing RAN data from all the RAN entities (302), the RDR (126) may be able to aggregate and provide a comprehensive RAN-level data (i.e. RAN data associated with the operation of the entire RAN (102)) to the AI entities, thereby allowing the AI entities to process and generate RAN-level optimizations (through RAN analytics data) instead of focusing on RAN data from individual RAN entities (302) only.
[0051] In some embodiments, the RAN (102) may be configured to communicate with a plurality of AI entities. The AI entities may be AI models that are configured to generate an output based on a set of inputs. The AI models may be any one or a combination of regression models, decision trees, expert systems, symbolic AI, neural networks, transformer models, and the like, but not limited thereto. In some embodiments, the AI entities may be implemented within the RAN entities (302). In other embodiments, the RAN entities (302) may be configured to communicate with the AI entities using the system (110) (i.e. the corresponding exposure functions in the RAN (102)). In some embodiments, the AI entities may be trained/adapted to process the RAN data to generate RAN analytics data, which may be used for optimizing operation of the RAN (102).
[0052] In some embodiments, the AI entities may be provided in the RDR (126). The RDR (126) may include a RDR AI control function (AICF) (106). In some embodiments, the RDR AICF (106) may be an entity configured to execute predefined processor-executable instructions to pre-train, re-train, and/or finetune other AI entities when the data lake (108) is updated. In other embodiments, the AI entities may be implemented in other RAN entities, such as DU-AICF, CU-AICF, and RU-AICF within DU (116), CU (114), and RU (118), respectively. Such AI entities may be configured to at least partially process the RAN data for meeting/satisfying specific optimization objectives.
[0053] In other embodiments, the RAN nodes may be configured to update the collected data to the RDR (126) via the RDM entity (112), with which the RDR (126) may be successfully registered. The RDR (126) may accumulate data from the RAN nodes for a time duration as specified in a policy, and/or in a pre-processing entity (not shown) in the RDR (126) as configured by operators of the RAN (102) and/or as indicated by application functions associated with SON and/or RRM.
[0054] In an embodiment, the RAN entities (302) may be configured to initiate a registration procedure with RDR (126) via the system (110), to allow the RAN entities (302) to store and/or retrieve RAN data from the RDR (126). The system (110), being implemented as exposure functions, may be configured to authenticate and share RAN network capabilities to the RAN entities (302). In some embodiments, the RAN entities (302) may request the RDR (126) for specific RAN data via the system (110). In such embodiments, system (110) may be configured to retrieve the specific RAN data from the RDR (126) and respond back to the requested RAN entities (302). In other embodiments, any RAN entities (302), including the RAN nodes, may also request the system (110) for the specific RAN data.
[0055] In an embodiment, the RDR (126) may be configured to offer a plurality of services via an interface (represented using Nrdr). In some embodiments, the interface may be implemented as APIs. In some embodiments, the interface may allow the RDR (126) to operate as a network function service producer having multiple network function service consumers such as including, but not limited to, the RDM (112), the system (110), the RAN nodes, the third party application function (122), and the EDGE server (120). In an embodiment, the interface may allow the RAN entities to perform service operations including, but not limited to, querying, creating, deleting, updating, subscribing, unsubscribing, notifying, data restoration, notification, and the like, the RAN data stored in the RDR (126).
[0056] FIG. 2 illustrates an example block diagram (200) of the proposed system (110), in accordance with an embodiment of the present disclosure.
[0057] In an embodiment, and as shown in FIG. 2, the system (110) may include one or more processors (202). The one or more processors (202) 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 one or more processor(s) (202) may be configured to fetch and execute computer-readable instructions stored in a memory (204) of the system (110). The memory (204) may store one or more computer-readable instructions or routines, which may be fetched and executed to create or share the data units over a network service. The memory (204) may include any non-transitory storage device including, for example, volatile memory such as a Random-Access Memory (RAM), or a non-volatile memory such as an Erasable Programmable Read-Only Memory (EPROM), a flash memory, and the like.
[0058] In an embodiment, the system (110) may also include an interface(s) (206). The interface(s) (206) may include 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) (206) may facilitate communication of the system (110) with various devices coupled thereto. The interface(s) (206) may also provide a communication pathway for one or more components of the system (110). Examples of such components include, but are not limited to, processing engine(s) (208) and a database (210).
[0059] In an embodiment, the processing engine(s) (208) may be implemented as a combination of hardware and software/programming (for example, programmable instructions) to implement one or more functionalities of the processing engine(s) (208). In examples, described herein, such combinations of hardware and software/programming may be implemented in several different ways. For example, the software/programming for the processing engine(s) (208) may be processor-executable instructions stored on a non-transitory machine-readable storage medium and the hardware for the one or more processors (202) may include 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) (208). In such examples, the system (110) 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 (110) and the processing resource. In other examples, the processing engine(s) (208) may be implemented by an electronic circuitry.
[0060] In an embodiment, the database (210) may include data that may be either stored or generated as a result of functionalities implemented by any of the components of the processor(s) (202) or the processing engine(s) (208) or the system (110).
[0061] In an exemplary embodiment, the processing engine(s) (208) may include one or more engines, such as a data exchange engine (212) and other units/engines (214). The other units/engines (214) may include, but are not limited to, a data acquisition engine, a monitoring engine, a notification engine, and the like.
[0062] In some embodiments, the data exchange engine (212) may be configured to retrieve a RAN event report from the RDR (126). The RAN event report may include at least one of a timestamp, RAN data, or RAN analytics data, but not limited thereto. The RAN event report may be subscribed by one or more of the RAN entities (302), such as the CU (114), the DU (116), and the RU (118), among other application functions. The RAN analytics data may be generated by an AI entity based on the RAN data stored in RDR (126). The data exchange engine (212) may also be configured to transmit the RAN event report to the RAN entities (302). The system (110) may be configured to use the data exchange engine (212) to perform other operations and allow the RAN entities (302) to access the AI entities for processing RAN data, based on which the operation of the RAN entities (302) may be optimized.
[0063] Although FIG. 2 shows exemplary components of the system (110), in other embodiments, the system (110) may include fewer components, different components, differently arranged components, or additional functional components than depicted in FIG. 2. Additionally, or alternatively, one or more components of the system (110) may perform functions described as being performed by one or more other components of the system (110).
[0064] FIG. 3 illustrates an example flow diagram of a method (300) for exposing RAN entities to AI entities, in accordance with an embodiment of the present disclosure.
[0065] At step (312), the RAN entity (302) may generate a request to acquire RAN data and/or RAN analytics data. At step (314), the RAN entity (302) may be configured to transmit the request to the system (110). The RAN entity (302) may transmit the request through a “Nraf_EventExposure_SubscribeRequest”. In some embodiments, the request may be for specific RAN data or RAN analytics data, which may be used for operation and/or optimizing performance thereof. In other embodiments, the request may be transmitted to subscribe to the RAN data and/or the RAN analytics data, where the requested RAN data and/or the RAN analytics data may be transmitted to the RAN entities (302) each time the RDR (126) is updated, or each time when a set of AI entities process the RAN data to generate the RAN analytics data.
[0066] At step (316), the system (110) may authorize the requesting RAN entity (302). In some embodiments, the system (110) may also be configured to associate the requested RAN data and/or the RAN analytics data to an event trigger and a requester identity. The system (110) may be configured to transmit a subscription request to the RDM (112) by sending a Nrdm_ EventExposure_SubscribeRequest message having the RAN Data and RAN analytics data request therein, at step (318).
[0067] At step (320), the RDM (112) may be configured to authorize the requesting system (110), and at step (322), the RDM (112) may be configured to associate the event trigger and the requester identity with the request. The RDM (112) analyses the data request and identifies the possible RAN entities (302) (such as any of the RAN nodes), from which the RAN data may be acquired.
[0068] At step (324), the RDM (112) may be configured to transmit a subscription request to the RAN entities (302), such as the RAN nodes including the CU (114), the DU (116) and the RU (118). The subscription message may be sent sing Ncu/Ndu/Nru_ EventExposure_SubscribeRequest having a request for the RAN data and/or the RAN analytics data. At step (326), respective RAN entities may be configured to acknowledge the received request by sending a message (such as Ncu/Ndu/Nru_ EventExposure_SubscribeResponse) back to RDM (112). At step (328), the RDM (112) may be configured to transmit another message (such as Nrdm_EventExposure_SubscribeResponse to the system (110)) to acknowledge receipt of the Ncu/Ndu/Nru_ EventExposure_SubscribeResponse. At step (332), the system (110) may be configured to forward the Nraf_EventExposure_SubscribeResponse to acknowledge the receipt of the Nrdm_EventExposure_SubscribeResponse.
[0069] At step (330), the RAN entities (302) (such as the CU (114), the DU (116), and the RU (118)) may start monitoring for the event trigger. At step (334), the RAN entities (302) may detect the occurrence of the trigger event. In response to the occurrence of the event, at step (336), the RAN entities (302) may be configured to transmit a notification (such as a Ncu/Ndu/Nru_EventExposure_Notify) to RDM (112). The notification may include the RAN event report having the requested RAN data and RAN analytics data, and also the timestamp of event occurrence.
[0070] In some embodiments, the RDM (112) may store the RAN event report (or create an entry therefor) in the RDR (126) along with the time stamp, and if the data in the report is a first-time data using Nrdr_DM_Create, at step (338). In other embodiments, the RDM (112) may be configured to update an existing entry in the RDR (126), such as using Nudr_DM_Update, at step (340). At step (342), the RDR (126) may be configured to update the data lake (108) with the received RAN data and RAN analytics data. In some embodiments, the RAN event report may only include the RAN data, and the RAN analytics data may be generated based on the RAN data at an external AI entity or the federated entities. In other embodiments, the RAN event report may include the RAN analytics data, the RAN analytics data being generated by an AI entity either at the RDR (126) (such as the RDR AICF (106)) or at the RAN entities (302) (such as the CU AICF, DU AICF, RU AICF, or any other AI entity associated with the RAN entity (302) from which the RAN event report is received).
[0071] At step (344), the RDM (112) may be configured to forward the event report to the system (110) by sending Nrdm_EventExposure_Notify, which includes the requested RAN data and/or RAN analytics data and also the timestamp of event occurrence.
[0072] At step (346), the system (110) may be configured to forward the RAN event report to the RAN entity (302), such as by transmitting Nraf_EventExposure_Notify messages thereto which may include the requested RAN data and RAN analytics data, and also the timestamp of event occurrence.
[0073] At step (348), the RAN entity (302) may utilize the data from the RAN event report, and optimize operation thereof based on the RAN data and/or RAN analytics data provided in the RAN event report.
[0074] FIG. 4 illustrates an example block diagram (400) representing the RAN (102), in accordance with the embodiments of the present disclosure. In some embodiments, the RAN entities (302) may include a plurality of application functions and or network functions/entities, which may be the RAN related control plane functions, applicable within the RAN domain. Each of the RAN entities (302) may be implemented as an application server that provide support for specific RAN application functionalities. The RAN entities (302) may influence the decisions made for functionalities such as including, but not limited to, SON functionalities, RRM functionalities, EDGE (120), radio, Physical layer functionalities, and the like.
[0075] For example, a call admission control application function (CAC AF) may be a critical functionality of Layer 3 (L3) RRM, which aids the CU (114) to decide whether to admit new RRC connections. Further, a MAC Schedular AF may also be a critical functionality of Layer 2 (L2) RRM, which aids the DU (116) to optimally decide on the dynamic radio resources for each and every active UEs, to maintain the requested quality of service and quality of experience (QoS/QoE), among other functionalities.
[0076] In further examples, an intelligent reflective surface (IRS) AF may aid both the DU (116) and the RU (118) to optimally identify the location of the UEs, detect channel conditions being experienced by UEs, divert the signals towards the needed UEs to enhance their signal-to-interference-plus-noise (SINR), and the like. In an embodiment, the third party application functions (122), both trusted and untrusted, may interact with the relevant RAN nodes via the system (110). The CU (114), the DU (116), the RU (118), and the EDGE (120) capabilities and events may be securely exposed by the system (110). The events and capabilities may include the third-party application functions (122), edge computing, and the like.
[0077] In another embodiment, the system (110) may be configured to stores and retrieve information as structured data using a standardized interface (such as Nrdr) to the RDR (126). The system (110) may provide a means for the RAN entities (302) to securely provide information and/or retrieve data to and from the RAN nodes. Consider examples of the information/data may include an optimized resource allocation, an optimized handover parameter values, an optimized energy saving decisions, accurate prediction of cell outages and cell management, and the like. In such examples, the system (110) may authenticate, authorize, and/or assist in throttling the RAN entities (302).
[0078] In some embodiments, the system (110) may be configured to mask network and user sensitive information to external AI entities or the third-party application functions (122), according to the RAN policy. The data provided by the external AI entities, the RAN entities (302), and/or the third-party application functions (122) may be collected by the RDM (112) entity via the system (110), which may be for the RAN analytics data generation purposes. The system (110) may be configured to handle and forward requests and notifications between the RDM (112) and RAN entities (302).
[0079] In an embodiment, the RDR (126) may be used to store the RAN data received from the RAN nodes through the RDM (112). The RDR (126) may also receive the RAN data through the system (110). Further, the RDR (126) may also be configured to store a RAN policy data, among other data required for the RAN (102) to operate. In some embodiments, the RDR (126) may be implemented to be dedicated to a specific RAN entities (302), rather than shared by the system (110) and the RDM (112). In an embodiment, a new Nrdr interface may be defined for the RAN functions, such as RDM (112) and the system (110), to access a particular set of the data stored and to read, update including add, modify, delete, and subscribe to notification of relevant data changes in the RDR (126). The RDR (126) may be configured to authorize the RAN entities (302), the RDM (112), and/or the system (110) to execute any one or a combination of add, modify, update or delete operations. The authorization may be performed by the RDR (126) on a per data set and RAN service consumer basis, a per UE, per cell, and/or per resource granularity. The data in the RDR (126) may be exposed via Nrdr to the respective RAN service consumer and storage thereof may be standardized.
[0080] The service-based Nrdr interface may define a meta-data structure through which the data may be exchanged with the RAN entities (302), the RDM (112), and/or the system (110). In an embodiment, the RDM (112) may be a RAN control plane function within the RAN (102). In some embodiments, the RDR (126) may also provide RAN data analytics functionality, and may house the AI/ML modelling functionalities, like training and inferences, to provide the RAN data analytics functionality. In some embodiments, the RDM (112) may be implemented to be dedicated to a specific RAN functional entity, rather than shared by the RAN nodes, unlike the embodiment shown in FIG. 4. In an embodiment, the RDM (112), as used by the system (110), may allow for “AI as a service platform” to the RAN entities (302).
[0081] The system (110) may be implemented in a computer system. FIG. 5 illustrates an example computer system (500) in which or with which embodiments of the present disclosure may be implemented, in accordance with embodiments of the present disclosure.
[0082] As shown in FIG. 5, the computer system (500) may include an external storage device (510), a bus (520), a main memory (530), a read-only memory (540), a mass storage device (550), communication port(s) (560), and a processor (570). A person skilled in the art will appreciate that the computer system (500) may include more than one processor and communication ports. The communication port(s) (560) may be any of an RS-232 port for use with a modem-based dialup connection, a 10/100 Ethernet port, a Gigabit or 10 Gigabit port using copper or fibre, a serial port, a parallel port, or other existing or future ports. The communication port(s) (560) may be chosen depending on a network, such a Local Area Network (LAN), Wide Area Network (WAN), or any network to which the computer system (500) connects. The main memory (530) may be a random-access memory (RAM), or any other dynamic storage device commonly known in the art. The read-only memory (540) may be any static storage device(s) including, but not limited to, Programmable Read Only Memory (PROM) chips for storing static information e.g., start-up or basic input/output system (BIOS) instructions for the processor (570). The mass storage device (550) may be any current or future mass storage solution, which may be used to store information and/or instructions.
[0083] The bus (520) communicatively couples the processor (570) with the other memory, storage, and communication blocks. The bus (520) can be, e.g. a Peripheral Component Interconnect (PCI) Extended (PCI-X) bus, a Small Computer System Interface (SCSI), a universal serial bus (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 (570) to the computer system (500).
[0084] Optionally, operator and administrative interfaces, e.g. a display, keyboard, and a cursor control device, may also be coupled to the bus (520) to support direct operator interaction with the computer system (500). Other operator and administrative interfaces may be provided through network connections connected through the communication port(s) (560). In no way should the aforementioned exemplary computer system (500) limit the scope of the present disclosure.
[0085] 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 present disclosure. These and other changes in the preferred embodiments of the present 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 to be implemented merely as illustrative of the present disclosure and not as limitation.

ADVANTAGES OF THE PRESENT DISCLOSURE
[0086] The present disclosure provides a system and a method for an artificial intelligence (AI) driven data processing in a radio access network (RAN).
[0087] The present disclosure enables to process data seamlessly and interact with multiple AI elements.
[0088] The present disclosure masks/hides sensitive information for training AI entities, and using AI entities during inference.
[0089] The present disclosure allows for distributed or federated computation.
[0090] The present disclosure enables interaction with third-party applications functions.
, Claims:1. A system (110) for exposing radio access network (RAN) entities (302) to artificial intelligence (AI) entities, the system (110) comprising:
one or more processors (202); and
a memory (204) operatively coupled with the one or more processors (202), wherein the memory (204) stores instructions which, when executed by the one or more processors (202), cause the one or more processors (202) to:
retrieve a RAN event report from a RAN data repository (RDR) (126), wherein the RAN event report comprises at least one of: RAN data, or RAN analytics data subscribed by one or more RAN entities (302), and wherein the RAN analytics data is generated by an AI entity based on the RAN data stored in the RDR (126); and
transmit the RAN event report to the one or more RAN entities (302).
2. The system (110) as claimed in claim 1, wherein the one or more RAN entities (302) are at least one of: one or more RAN nodes, one or more network functions, or a third-party application function (122), and wherein the one or more RAN nodes are at least one of: a radio unit (RU) (118), a distributed unit (DU) (116), and a central unit (CU) (114).
3. The system (110) as claimed in claim 1, wherein the RDR (126) is configured to store the RAN data received from the one or more RAN entities (302) through a RAN data management (RDM) entity (112).
4. The system (110) as claimed in claim 1, wherein the one or more processors (202) are configured to retrieve and transmit the RAN event report from the RDR (126) in response to a request from the one or more RAN entities (302).
5. The system (110) as claimed in claim 1, wherein the one or more processors (202) are configured to:
receive a request from the one or more RAN entities (302) to subscribe to at least one of: the RAN data or the RAN analytics data;
authorize the one or more RAN entities (302), and associate the one or more RAN entities (302) with a trigger event and a requester identity;
transmit a data subscription request to a RAN data management (RDM) entity (112), wherein the data subscription request comprises the request received from the one or more RAN entities (302); and
in response to receiving a data subscription response from the RDM entity (112), transmit a response to the one or more RAN entities (302) to acknowledge the request,
wherein the data subscription response is received when the RDM entity (112) subscribes to one or more RAN nodes that are configured to transmit the RAN data to the RDM entity (112) on occurrence of the trigger event, and
wherein the RDM entity (112) is configured to perform any or a combination of: processing, filtering, and/or storing the RAN data in the RDR (126).
6. The system (110) as claimed in claim 5, wherein the RAN event report is received from the RDM entity (112) after the RDM entity (112) stores the RAN event report in the RDR (126).
7. The system (110) as claimed in claim 1, wherein the AI entity is implemented within at least one of: the RDR (126), a third-party application function (122), or an external federation entity.
8. The system (110) as claimed in claim 1, wherein the RAN event report is transmitted to any or a combination of: the one or more RAN entities (302), a third-party application function (122), and an external federation entity, and wherein the third-party application function (122) and the external federation entity are configured to process the RAN event report and transmit the processed RAN event report to the one or more RAN entities (302).
9. The system (110) as claimed in claim 1, wherein the RAN event report is transmitted through a meta data structure.
10. The system (110) as claimed in claim 1, wherein the one or more processors (202) are configured to mask network sensitive and user sensitive data from the RAN event report.
11. A method (300) for exposing radio access network (RAN) entities (302) to artificial intelligence (AI) entities, the method (300) comprising:
retrieving (344), by one or more processors (202), a RAN event report from a RAN data repository (RDR) (126), wherein the RAN event report comprises at least one of: RAN data, or RAN analytics data, and wherein the RAN analytics data is generated by an AI entity based on the RAN data stored in the RDR (126); and
transmitting (346), by the one or more processors (202), the RAN event report to the one or more RAN entities (302).