DESC:
FORM 2
THE PATENTS ACT, 1970
(39 of 1970)
&
THE PATENTS RULES, 2003

COMPLETE SPECIFICATION
(See section 10 and rule 13)
1. TITLE OF THE INVENTION
METHOD AND SYSTEM FOR MANAGING RESOURCES IN A COMMUNICATION NETWORK
2. APPLICANT(S)
Name Nationality Address
JIO PLATFORMS LIMITED INDIAN OFFICE-101, SAFFRON, NR. CENTRE POINT, PANCHWATI 5 RASTA, AMBAWADI, AHMEDABAD 380006, GUJARAT, INDIA
3. PREAMBLE TO THE DESCRIPTION

THE FOLLOWING SPECIFICATION PARTICULARLY DESCRIBES THE NATURE OF THIS INVENTION AND THE MANNER IN WHICH IT IS TO BE PERFORMED.

FIELD OF THE INVENTION
[0001] The present invention relates to wireless communications, more particularly relates to a method and a system for managing resources in a communication network.
BACKGROUND OF THE INVENTION
[0002] In the cellular world, network slicing allows businesses to control traffic resources on a more granular level. The network slicing enables the multiplexing of virtualized and independent logical networks on the same physical network infrastructure.
[0003] The Network Data Analytics Function (NWDAF) collects the data from the consumers and provides analytical information about the network data. The NWDAF also provides slice load analytics.
[0004] Generally, resources such as network engineers may have to check the slice load analytics data to ascertain traffic in a communication network. In some situations, the load/traffic in the communication network may be higher than usual. To analyse the slice load analytics data during high traffic in the communication network, more resources may have to be allocated. Furthermore, number of network slice instances may to be provided to the resources in order to ascertain traffic in the communication network. On the other hand, if the traffic is much lower than usual in the communication network, then a smaller number of resources and a smaller number of the network slice instances may be required or the extra number of resources and the network slice instances allocated already may have to be removed. The task of allocating the resources for analysing the slice load analytics data depending on the load may consume more time as these tasks are typically managed manually. The manual process is labour intensive and time consuming. The manual interaction further can potentially result in operational inefficiencies and delays in obtaining critical network data. This may cause a delay in the analysing slice load analytics data.
[0005] In view of the above, there is a dire need for a system and method for managing resources depending on the load in the communication network, which ensures optimal usage of the resources.
SUMMARY OF THE INVENTION
[0006] One or more embodiments of the present disclosure provide a method and system for managing resources in a communication network.
[0007] In one aspect of the present invention, the system for managing resources in the communication network is disclosed. The system includes a data integration unit, configured to collect from a plurality of sources, one or more types of data pertaining to load in the communication network. The system further includes a model training unit, configured to train, a model with the collected data. The system further includes a prediction unit, configured to dynamically predict a number of resources required to manage the current load in the communication network using the trained model. The system further includes a detection unit, configured to detect, a breach pertaining to the collected data if at least one of the current load or the one or more pre-defined policies crosses a pre-defined threshold. The system further includes a recommendation unit, configured to suggest remedial actions, when the breach is detected pertaining to the collected data.
[0008] In an embodiment, the resources include at least one of a network slices.
[0009] In an embodiment, the plurality of sources includes at least one of a database, network functions, network application program interfaces and network management systems.
[0010] In an embodiment, the collected data includes at least one of, historical data, one or more consumer defined policies and current load in the communication network.
[0011] In an embodiment, the data integration unit is further configured to, preprocess, the collected data by at least one of the data normalizing, the data cleaning and removing null values from the collected data.
[0012] In an embodiment, the prediction unit is further configured to, depict, the predicted data and the actual value on a display device; wherein the predicted data is depicted in multiple network operator defined formats.
[0013] In an embodiment, a reporting unit is configured to report in real time, to a network operator, the detected breach pertaining to the collected data.
[0014] In an embodiment, the remedial actions include at least one of, scale-in and/or scale-out the one or more resources to/from the communication network.
[0015] In an embodiment, the prediction unit, dynamically predicts, a number of resources required to manage a current load in the communication network using the trained model, by comparing, at least one of, the current load and the one or more pre-defined policies with the historical data and in response to detecting, a deviation in at least one of, the current load and the one or more pre-defined policies in comparison to the historical data, predicting the number of resources required to manage the current load in the communication network.
[0016] In an embodiment, the historical data is the data learnt by the model during training.
[0017] In an embodiment, the one or more processors continuously monitors the data to detect breach pertaining to the collected data.
[0018] In an embodiment, the trained model continuously receives feedback from the one or more processors, wherein the model adapts and evolves based on the received feedback.
[0019] In another aspect of the present invention, the method for managing resources in a communication network is disclosed. The method includes the step of collecting, by one or more processors, from a plurality of sources, one or more types of data pertaining to load in the communication network. The method further includes the step of training, by the one or more processors, a model with the collected data. The method further includes the step of dynamically predicting, by the one or more processors, a number of resources required to manage current load in the communication network using the trained model. The method further includes the step of detecting, by the one or more processors, a breach pertaining to the collected data if at least one of, the current load or the one or more pre-defined policies crosses a pre-defined threshold. The method further includes the step of suggesting remedial actions, by the one or more processors, when the breach is detected pertaining to the collected data.
[0020] In another aspect of the invention, a non-transitory computer-readable medium having stored thereon computer-readable instructions is disclosed. The computer-readable instructions are executed by a processor. The processor is configured to collect from a plurality of sources, one or more types of data pertaining to the load in the communication network. The processor is configured to train, the model with the collected data. The processor is configured to dynamically predict the number of resources required to manage the current load in the communication network using the trained model. The processor is configured to detect the breach pertaining to the collected data if at least one of, the current load or the one or more pre-defined policies crosses the pre-defined threshold. The processor is configured to suggest remedial actions, when the breach is detected pertaining to the collected data.
[0021] In another aspect of invention, network operator equipment is disclosed. The network operator equipment includes one or more primary processors communicatively coupled to one or more processors, the one or more primary processors coupled with a memory. The processor causes the network operator equipment to transmit, network operator defined formats to depict predicted data.
[0022] Other features and aspects of this invention will be apparent from the following description and the accompanying drawings. The features and advantages described in this summary and in the following detailed description are not all-inclusive, and particularly, many additional features and advantages will be apparent to one of ordinary skill in the relevant art, in view of the drawings, specification, and claims hereof. Moreover, it should be noted that the language used in the specification has been principally selected for readability and instructional purposes and may not have been selected to delineate or circumscribe the inventive subject matter, resort to the claims being necessary to determine such inventive subject matter.
BRIEF DESCRIPTION OF THE DRAWINGS
[0023] The accompanying drawings, which are incorporated herein, and constitute a part of this 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 disclosure of such drawings includes disclosure of electrical components, electronic components or circuitry commonly used to implement such components.
[0024] FIG. 1 is an exemplary block diagram of an environment for managing resources in a communication network, according to one or more embodiments of the present invention;
[0025] FIG. 2 is an exemplary block diagram of a system for managing resources in the communication network, according to one or more embodiments of the present invention;
[0026] FIG. 3 is a schematic representation of a workflow of the system of FIG. 1, according to the one or more embodiments of the present invention;
[0027] FIG. 4 is an exemplary block diagram of an architecture implemented in the system of the FIG. 2, according to one or more embodiments of the present invention;
[0028] FIG. 5 is a signal flow diagram for managing resources in the communication network according to one or more embodiments of the present invention; and
[0029] FIG. 6 is a schematic representation of a method of managing resources in the communication network according to one or more embodiments of the present invention.
[0030] The foregoing shall be more apparent from the following detailed description of the invention.
DETAILED DESCRIPTION OF THE INVENTION
[0031] Some embodiments of the present disclosure, illustrating all its features, will now be discussed in detail. It must also be noted that as used herein and in the appended claims, the singular forms "a", "an" and "the" include plural references unless the context clearly dictates otherwise.
[0032] Various modifications to the embodiment will be readily apparent to those skilled in the art and the generic principles herein may be applied to other embodiments. However, one of ordinary skill in the art will readily recognize that the present disclosure including the definitions listed here below are not intended to be limited to the embodiments illustrated but is to be accorded the widest scope consistent with the principles and features described herein.
[0033] A person of ordinary skill in the art will readily ascertain that the illustrated steps detailed in the figures and here below are set out to explain the exemplary embodiments shown, and it should be anticipated that ongoing technological development will change the manner in which particular functions are performed. These examples are presented herein for purposes of illustration, and not limitation. Further, the boundaries of the functional building blocks have been arbitrarily defined herein for the convenience of the description. Alternative boundaries can be defined so long as the specified functions and relationships thereof are appropriately performed. Alternatives (including equivalents, extensions, variations, deviations, etc., of those described herein) will be apparent to persons skilled in the relevant art(s) based on the teachings contained herein. Such alternatives fall within the scope and spirit of the disclosed embodiments.
[0034] FIG. 1 illustrates an exemplary block diagram of an environment 100 for managing resources in a communication network 105, according to one or more embodiments of the present disclosure. In this regard, the environment 100 includes a network operator equipment 110, a server 115, the communication network 105 and a system 120 communicably coupled to each other for managing the resources in the communication network 105. The resources refer to at least one of a network slice. The network slice is a significant technology in the telecommunications system in which multiple virtual networks are created within a physical network infrastructure. Each of the network slice operates independently to serve the specific requirements for which each of the network slice is configured.
[0035] As per the illustrated embodiment and for the purpose of description and illustration, the network operator equipment 110 includes, but not limited to, a first network operator equipment 110a, a second network operator equipment 110b, and a third network operator equipment 110c, and should nowhere be construed as limiting the scope of the present disclosure. In alternate embodiments, the network operator equipment 110 may include a plurality of network operator equipment as per the requirement. For ease of reference, each of the first network operator equipment 110a, the second network operator equipment 110b, and the third network operator equipment 110c, will hereinafter be collectively and individually referred to as the “network operator equipment 110”.
[0036] In an embodiment, the network operator equipment 110 is one of, but not limited to, any electrical, electronic, electro-mechanical or an equipment and a combination of one or more of the above devices such as a smartphone, virtual reality (VR) devices, augmented reality (AR) devices, laptop, a general-purpose computer, desktop, personal digital assistant, tablet computer, mainframe computer, or any other computing device.
[0037] The environment 100 includes the server 115 accessible via the network 105. The server 115 may include, by way of example but not limitation, one or more of a standalone server, a server blade, a server rack, a bank of servers, a server farm, hardware supporting a part of a cloud service or system, a home server, hardware running a virtualized server, one or more processors executing code to function as a server, one or more machines performing server-side functionality as described herein, at least a portion of any of the above, some combination thereof. In an embodiment, the entity may include, but is not limited to, a vendor, a network operator, a company, an organization, a university, a lab facility, a business enterprise side, a defense facility side, or any other facility that provides service.
[0038] The communication network 105 includes, by way of example but not limitation, one or more of a wireless network, a wired network, an internet, an intranet, a public network, a private network, a packet-switched network, a circuit-switched network, an ad hoc network, an infrastructure network, a Public-Switched Telephone Network (PSTN), a cable network, a cellular network, a satellite network, a fiber optic network, or some combination thereof. The communication network 105 may include, but is not limited to, a Third Generation (3G), a Fourth Generation (4G), a Fifth Generation (5G), a Sixth Generation (6G), a New Radio (NR), a Narrow Band Internet of Things (NB-IoT), an Open Radio Access Network (O-RAN), and the like.
[0039] The communication network 105 may also include, by way of example but not limitation, at least a portion of one or more networks having one or more nodes that transmit, receive, forward, generate, buffer, store, route, switch, process, or a combination thereof, etc. one or more messages, packets, signals, waves, voltage or current levels, some combination thereof, or so forth. The communication network 105 may also include, by way of example but not limitation, one or more of a wireless network, a wired network, an internet, an intranet, a public network, a private network, a packet-switched network, a circuit-switched network, an ad hoc network, an infrastructure network, a Public-Switched Telephone Network (PSTN), a cable network, a cellular network, a satellite network, a fiber optic network, a VOIP or some combination thereof.
[0040] The environment 100 further includes the system 120 communicably coupled to the server 115 and the network operator equipment 110 via the communication network 105. The system 120 is configured for managing the resources in the communication network 105. As per one or more embodiments, the system 120 is adapted to be embedded within the server 115 or embedded as an individual entity.
[0041] Operational and construction features of the system 120 will be explained in detail with respect to the following figures.
[0042] FIG. 2 is an exemplary block diagram of the system 120 for managing resources in the communication network 105, according to one or more embodiments of the present invention.
[0043] As per the illustrated embodiment, the system 120 includes one or more processors 205, a memory 210, a user interface 215, and a database 220. For the purpose of description and explanation, the description will be explained with respect to one processor 205 and should nowhere be construed as limiting the scope of the present disclosure. In alternate embodiments, the system 120 may include more than one processor 205 as per the requirement of the communication network 105. The one or more processors 205, hereinafter referred to as the processor 205 may be implemented as one or more microprocessors, microcomputers, microcontrollers, digital signal processors, central processing units, state machines, logic circuitries, single board computers, and/or any devices that manipulate signals based on operational instructions.
[0044] As per the illustrated embodiment, the processor 205 is configured to fetch and execute computer-readable instructions stored in the memory 210. The memory 210 may be configured to store one or more computer-readable instructions or routines in a non-transitory computer-readable storage medium, which may be fetched and executed to create or share data packets over a network service. The memory 210 may include any non-transitory storage device including, for example, volatile memory such as RAM, or non-volatile memory such as disk memory, EPROMs, FLASH memory, unalterable memory, and the like.
[0045] In an embodiment, the user interface 215 includes a variety of interfaces, for example, interfaces for a graphical user interface, a web user interface, a Command Line Interface (CLI), and the like. The user interface 215 facilitates communication of the system 120. In one embodiment, the user interface 215 provides a communication pathway for one or more components of the system 120. Examples of such components include, but are not limited to, the network operator equipment 110 and the database 220.
[0046] The database 220 is one of, but not limited to, a centralized database, a cloud-based database, a commercial database, an open-source database, a distributed database, an end-user database, a graphical database, a No-Structured Query Language (NoSQL) database, an object-oriented database, a personal database, an in-memory database, a document-based database, a time series database, a wide column database, a key value database, a search database, a cache databases, and so forth. The foregoing examples of database 220 types are non-limiting and may not be mutually exclusive e.g., a database can be both commercial and cloud-based, or both relational and open-source, etc.
[0047] In order for the system 120 for managing the resources in the communication network 105, the processor 205 includes one or more modules. In one embodiment, the one or more modules includes, but not limited to, a data integration unit 225, a model training unit 230, a prediction unit 235, a display device 240, a detection unit 245, a reporting unit 250 and a recommendation unit 255 communicably coupled to each other for managing the resources in the communication network 105.
[0048] In one embodiment, the one or more modules includes, but not limited to, the data integration unit 225, the model training unit 230, the prediction unit 235, the display device 240, the detection unit 245, the reporting unit 250 and the recommendation unit 255 can be used in combination or interchangeably for 120 for managing the resources in the communication network 105.
[0049] The data integration unit 225, the model training unit 230, the prediction unit 235, the display device 240, the detection unit 245, the reporting unit 250 and the recommendation unit 255 in an embodiment, may be implemented as a combination of hardware and programming (for example, programmable instructions) to implement one or more functionalities of the processor 205. In the examples described herein, such combinations of hardware and programming may be implemented in several different ways. For example, the programming for the processor 205 may be processor-executable instructions stored on a non-transitory machine-readable storage medium and the hardware for the processor 205 may comprise a processing resource (for example, one or more processors), to execute such instructions. In the present examples, the memory 210 may store instructions that, when executed by the processing resource, implement the processor 205. In such examples, the system 120 may comprise the memory 210 storing the instructions and the processing resource to execute the instructions, or the memory 210 may be separate but accessible to the system 120 and the processing resource. In other examples, the processor 205 may be implemented by electronic circuitry.
[0050] In one embodiment, the data integration unit 225 is configured to collect one or more types of data pertaining to the load in the communication network 105. The collected data includes at least one of historical data, one or more consumer defined policies and current load in the communication network 105. The historical data is the data pertaining to the load in the communications network 105 in previous times. The one or more consumer defined policies refer to preferences of quality of service which include but not limited to resource allocation limits, traffic management, security, priority access and dynamic adaptation. The resource includes at least one of a network slices. The load is the amount of data traffic or resource usage in the communication network 105 at a given time. The current load pertains to at least one of amount of data transmitted and resource in the communication network 105 in real time. The present embodiment collects data pertaining to the current load of each of the network slices within the communication network 105. The data is collected from a plurality of sources. The plurality of sources includes at least one of the database 220, network functions, network application program interfaces. The network functions are specific tasks performed by network components. The network functions include but are not limited to routing, switching, firewalls and load balancers. The network application programming interfaces refer to a set of tools that allow one or more software applications to communicate with each other over a network resource and perform one or more tasks. The firewall refers to security devices or software that monitor and control network traffic within a network. The load balancers are devices or software applications that distribute network traffic across one or more servers or network components so that there is minimized response times and overload on any single network. There is real time understanding of current load in the network by at least one of the database 220, network functions, network application program interfaces which is received by the data integration unit 225 for further processes.
[0051] In an embodiment, the collected data is preprocessed using the data integration unit 225. The preprocessing includes but is not limited to data definition, data cleaning, data normalization and removing null values. The collected data is raw data which is heterogenous or non-uniform. The collected data further possesses redundant information on the communication network 105. For example, the collected data include but not limited to, the time taken for a packet to transmit over the communication network 105, total number of bytes sent and received within a specific time frame and the duration of time users have been connected to each of the network slices. The data transmission time is measured in milliseconds, number of data transmitted is measured in bytes and duration of user connection is measured in hours. The differently formatted data is not suitable for training a model. For proper learning of the model, the raw data is transformed into standardized data. The data which is redundant and not relevant to the current load in the communication network 105 is removed from the raw data by the data integration unit 225. The preprocessing transforms the raw data into standardized data with uniform format and free of at least one of redundant, irrelevant and null values. The data integration unit 225 further splits the standardized collected data into training and test data.
[0052] Upon preprocessing the collected data, the training data is fed into the model training unit 230. The model training unit 230 is configured to train the model with the training data. The model is at least one of a machine learning based algorithm which is trained on a set of training data to learn insights from the training data and configured to apply the insights on an unseen data. The model is trained utilizing the training data to identify patterns and trends in the load of the communication network 105. The trends and patterns in the preprocessed data pertain to the threshold value or range of values pertaining to network load in each of the plurality of network slices for a stable network performance with negligible data packet loss and latency. For example, on training a model using the data pertaining to the workspace communication network during morning, the model learns the data volume transmitted during weekdays in is 200 GB to 500GB per hour. During the weekend, the volume of data transmitted is 50 GB to 150 GB per hour. The model further understands the number of network slices utilized to transmit the learnt volumes of data on weekdays and weekends. The number of network slices for 200 GB to 500 GB per hour is, for instance, 8 and for 50 to 150 GB is only 3. The training model learns the pattern of number of network slices and data volume transmitted across the given workspace communication network as high during weekdays and low at weekends.
[0053] In an embodiment, the trained model utilizes the test data from the data integration unit 225 to evaluate the performance of the trained model. The test data includes the data which is unseen by or new to the trained model. In the present embodiment, the test data pertains to the load in the communication network 105. The test data is the data given to at least one of the machine learning models to evaluate the performance of the trained model. For instance, the performance of the test data is evaluated based on the one or more performance metrics. The performance metrics include at least one of but not limited to precision, accuracy, mean absolute error and mean squared error. If it is determined based on the performance metrics, that the model is not accurately trained, then the model is to be trained again. If it is determined based on the performance metrics that the model is accurately trained, then the trained model is used for further processes.
[0054] Upon learning from the model training unit 230, the model is further configured to receive the current data. The current data is the data pertaining to the current load in the communication network 105. The collected current data is utilized by the trained model for further processes including at least one of monitoring the network load and managing the resources correspondingly. The current load is the load in each of the network slices within the communication network 105 in real time. Upon receiving the current data, the prediction unit 235 is configured to dynamically predict the number of resources required to manage the current load in the communication network 105 utilizing the trained model. The prediction by the prediction unit 235 is performed by comparing the current load and the one or more pre-defined policies with the historical data. The historical data is the data learnt by the model during the training of the model. The prediction unit 235 is configured to depict a predicted data and an actual value on the display device 240. The depiction is in at least one of graphical representations. The predicted data is depicted in multiple network operator defined formats. Whenever there is a deviation of at least one of, the current load and the one or more pre-defined policies in comparison to the historical data, the predicting unit predicts the number of resources required to manage the current load in the communication network 105. In the previous example of the workspace network communication, the prediction unit 235 predicts the number of the network slices required in a normal weekday with the high data volume in transmission, for instance, 5 network slices. If the actual number of network slices in use is, for example 2, then there is a deviation. The prediction unit 235 is configured to dynamically predict a number of resources required to manage the current load in the communication network 105. The dynamic character of the prediction by the prediction unit 235 refers to prediction of appropriate number of network slices to be utilized for each volume of data transmitted. In the previous example of the workspace communication network 105, if the volume of data transmitted during mornings on weekdays reduces, from 200 -500GB per hour to 150- 350 GB, then the prediction of the number of network slices required for transmission is reduced, for instance, from 8 to 5. Further, if the volume of data transmitted during weekend mornings increases, from 50-150 GB per hour to 100-200 GB, then prediction for the number of network slices required for transmission is increased, for instance from 3 to 4. For example, if the predicted number of network slices for a given volume of data, 150- 350 GB on weekdays is 5, which is the historical data for the given data volume. The policies predefined by the network operators dictate that the resources including one or more network slices are to be allocated based on the network load so that there is at least one of negligible latency and error rate. But if the actual number of network slices in use is only 2 against the predicted count of 5, there is high latency and error rate in the data transmission. If the actual number of resources is less than or more than the predicted number against the predefined set of network policies, the deviations is a breach. The breach in the present embodiment be referred as deviations in at least one of the current loads and the one or more pre-defined policies in comparison to the historical data. The historical data is the trends and patterns learnt by the trained model during the training. Therefore, upon predicting the number of resources required to manage the current load, the detection unit 245 detects a breach in at least one of the current loads and the one or more pre-defined policies in comparison to the historical data.
[0055] Upon detection the reporting unit 250 is configured to report the detected breach to the network operator. The reporting unit 250 is configured to report the detected breach in real time to the network operator. The reporting of the one or more detected breaches is transmitted to the network operators by at least one of SMS, email, dashboard visuals or application program interfaces. Upon reporting by the reporting unit 250 the network operator is able to rectify the one or more breaches and allocate the required number of network slices to reduce the load in each of the plurality of network slices.
[0056] Upon reporting by the reporting unit 250, the recommendation unit 255 is configured to suggest remedial actions to the network operators. The remedial actions include at least one of scale in and scale out of the one or more resources to or from the communication network 105. For the previous example of the workspace communication network, if the network slice possesses load value or range of values greater than the learnt value or range of value, then the remedial action is to scale in or increase the number of network slice to be used to reduce the load in the existing network slice. The user or network operators either manually increase the network slices to be used or the system 120 automatically executes the recommendation. In an alternate embodiment of automated resolving of breaches includes but not limited to transmitting request to microservices to scale in or scale out the network slices from the plurality of network slices and receiving replies on status of resolution. The status of resolution involves at least one of resolved and not resolved. The auto scale-in reduces the load and latency improving the quality of network service. If the load in each of the plurality of network slices in use is less than the threshold value or range of values, then the recommendation is to scale out a number of network slices so that the load in each of the network slices is at a value or range of values. The threshold value or range of values is either configured by the user or set by the training model based on the training. The threshold is a value or range of values which is suitable for data transmission with at least one of negligible data packet loss, no error and insignificant latency.
[0057] In an embodiment, the system 120 continuously monitors the data to detect breach pertaining to the network load of the communications network 105Based on the data stored in the database 220 comprising at least one of the learning of the trained model, one or more breaches and corresponding actions initiated to resolve the one or more breaches, the closed loop reporting and closed loop actions are performed. The trained model continuously utilizes the learnt patterns to forecast the number of resources to be utilized for the current load based on the feedback including at least one of the user behaviors, changing consumer needs and trends in the telecommunication industry. Upon continuous monitoring of data and detection of one or more breaches similar to one or more previous breaches in one or more consumer defined policies, one or more similar actions are triggered based on the data utilized by at least one of the data stored in database 220, closed loop reporting and closed loop actions. The model utilizes reinforcement learning to interact with the environment to adapt and evolve with the changing network conditions and user demands. The model through continuous learning and optimization improves decision making capacity and refines the performance of the system 120.
[0058] In an alternative embodiment, current data of at least one of the network slices are automatically transmitted to microservice or applications via Hypertext Transfer Protocol (HTTP) based request. In particular, the microservice or applications are transmitting the request to the system 120 and receiving the end-response from the system 120. Thus, no manual interactions are involved. The automated embodiment enables reliability with high quality performance of the communication network in situations of breaches and negligible downtime.
[0059] FIG. 3 describes a preferred embodiment of the system 120 of FIG. 2, according to various embodiments of the present invention. It is to be noted that the embodiment with respect to FIG. 3 will be explained with respect to the first network operator equipment 110a and the system 120 for the purpose of description and illustration and should nowhere be construed as limited to the scope of the present disclosure.
[0060] As mentioned earlier in FIG. 1, each of the first network operator equipment 110a, the second network operator equipment 110b, and the third network operator equipment 110c may include an external storage device, a bus, a main memory, a read-only memory, a mass storage device, communication port(s), and a processor. The exemplary embodiment as illustrated in FIG. 3 will be explained with respect to the first network operator equipment 110a without deviating from the scope of the present disclosure and the limiting the scope of the present disclosure. The first network operator equipment 110a includes one or more primary processors 305 communicably coupled to the one or more processors 205 of the system 120.
[0061] The one or more primary processors 305 are coupled with a memory 210 storing instructions which are executed by the one or more primary processors 305. Execution of the stored instructions by the one or more primary processors 305 enables the first network operator equipment 110a to transmit, network operator defined formats to depict predicted data.
[0062] As mentioned earlier in FIG. 2, the one or more processors 205 of the system 120 is configured for managing resources in a communication network 105. As per the illustrated embodiment, the system 120 includes the one or more processors 205, the memory 210, the user interface 215 and the database 220. The operations and functions of the one or more processors 202, the memory 210, the user interface 215, and the database 220 are already explained in FIG. 2. For the sake of brevity, a similar description related to the working and operation of the system 120 as illustrated in FIG. 2 has been omitted to avoid repetition.
[0063] Further, the processor 205 includes the data integration unit 225, the model training unit 230, the prediction unit 235, the detection unit 245, the reporting unit 250 and the recommendation unit 255. The operations and functions of the data integration unit 225, the model training unit 230, the prediction unit 235, the detection unit 245, the reporting unit 250 and the recommendation unit 255 are already explained in FIG. 2. Hence, for the sake of brevity, a similar description related to the working and operation of the system 120 as illustrated in FIG. 2 has been omitted to avoid repetition. The limited description provided for the system 120 in FIG. 3, should be read with the description provided for the system 120 in the FIG. 2 above, and should not be construed as limiting the scope of the present disclosure.
[0064] FIG. 4 is an exemplary block diagram of an architecture 400 implemented in the system 120 of the FIG. 2, according to one or more embodiments of the present invention.
[0065] The architecture 400 includes data consumers 405, Network Data Analytics Function (NWDAF) 410, an Artificial Intelligence/ Machine Learning (AI/ML) unit 415, the data lake 420 and the user interface 215. The AI/ML unit 415 comprises of the data integration unit 225, a data preprocessing unit 425, the model training unit 230 and the prediction unit 235.
[0066] In an embodiment, the AI/ML unit 415 is a dedicated module that utilizes AI or ML algorithms and systems to create intelligent solutions, enabling automation, predictive analytics, and enhanced decision-making processes. In the present embodiment the data integration unit 225 within the AI/ML unit 415 and is configured to collect from a plurality of sources, one or more types of data pertaining to load in the communication network 105. The plurality of sources of data includes at least one of databases 220 and the NWDAF 410. The NWDAF 410 is a key component in the communication network 105 designed to provide data analytics capabilities. The NWDAF 410 gathers data from various network elements from at least one of the network operator equipment 110, the data consumers 405, radio access network and core network functions. The data consumers 405 are network operators who utilize the data and insights generated by the network analytics to monitor and manage the network 105. The data lake 420 is at least one of the databases 220 is configured to store the data on the network slice performance. The collected data includes but is not limited to at least one of historical data, one or more consumer defined policies and current load in the communication network 105. The collected data is raw data.
[0067] Upon data integration by the data integration unit 225, the integrated data is preprocessed by the data preprocessing unit 425. The integrated data is raw data with values which are at least one of non-uniform formats, redundant, irrelevant and null values. The data preprocessing unit 425 is configured to transform the raw data into standardized format through at least one of data definition, data cleaning, data normalization and null value removal. The standardized data refers to the data free of the non-uniform formats, redundant, irrelevant and null values. If a raw data is utilized for training a model, the output of the model training becomes unreliable. Therefore, raw data is not suitable for model training. The standardized data is suitable for the training of the model. The preprocessing unit 425 is further configured to split the standardized data into training data and test data.
[0068] Upon preprocessing the data collected by the data preprocessing unit 425, the standardized data is fed into the model training unit 230. The model training unit 230 is configured to train the model with the training data to identify trends and patterns in the load of the communication network 105. The model learns threshold value or range of values from the training data for a stable functioning of the data transmission with negligible data packet loss and latency. The data pertaining to the trends and patterns of the training data is stored in the data lake 420. Thereafter the test data is applied on the model by the model training unit 230. The test data identifies the load is higher whenever the network parameters are higher as learnt from the training data.
[0069] Upon identifying the trends and patterns in the training data using the model, the model is configured to utilize the data pertaining to the current data. The current data pertains to the real time load in each of the plurality of network slices. Upon utilization of the current data pertaining to the current load in each of the plurality of network slices by the trained model, the prediction unit 235 is configured to dynamically predict the number of resources required to manage the current load in the communication network 105. For prediction, the current load, the one or more predefined policies and historical data are compared against each other. Thereafter the prediction unit 235 is further configured to dynamically predict the number of network slices in the communication network 105 essential for stable network load, compliance of the predefined polices, negligible latency and insignificant data packet loss. The prediction unit 235 is further configured to display the predicted data and the actual data on a display device 240. The predicted data is depicted in one or more formats defined by the network operator. Upon any deviation of the actual data from the predicted data, the prediction unit 235 is further configured to detect the deviations as one or more breaches.
[0070] Upon prediction and detection of breaches by the prediction unit 235 is further configured to report the breaches to at least one of the data consumers 405 and user interface 215. The reporting includes at least one of notifications or suggestions of remedial actions. When the current load is greater than the predicted value then the remedy is to increase the number of network slices in use for distributing the network load aggregated in the given network slice. The increase in the number of network slices is called scale in. When the current load is less than the predicted value then the remedy is to reduce the number of network slices in use. The reduction in the number of network slices is called scale out. Upon receiving the reporting on the breaches, the scale in and scale out is done at least by the user or the system 120 by automation.
[0071] In an embodiment the system 120 is in continuous evolution and refinement by the continuous monitoring of the data and real time detection of breach pertaining to the collected data. The model adapts with the changing user demands and network conditions pertaining to the network performance within the communication network 105, one or more detected breaches in the network and the one or more actions initiated for one or more breaches. The closed loop reporting, closed loop action and continuous process of evolution enables the model to improve the decision-making capacity for the future breaches.
[0072] FIG. 5 is a signal flow diagram for managing the resources in the communication network 105, according to one or more embodiments of the present invention.
[0073] At step 505, the data integration unit 225 collects the one or more type of data from the plurality of data sources. The data collected is slice load data from the plurality of data sources. The data collected pertains to at least one of historical data on the network load from the database 220, one or more consumer defined threshold policies from the data consumers 405 and current load in the communication network 105. The data consumers 405 define the threshold value or range of values for load in the network slices so that there is stable data transmission with negligible data packet loss and latency for diverse volume of data.
[0074] At step 510, the data collected which is raw data is preprocessed into standardized data. The raw data which is not suitable for training a model undergoes at least one of data cleaning, data normalization. The standardized data is further split into training and testing data for the process of model training.
[0075] At step 515, the model is trained using the historical data. The model learns to predict the network performance based on the slice load analytics. The model identifies trends and patterns in each of the network slices within the communication network 105. The trained model learns to predict the number of network slices required within a communications network 105, to share the load value in each of the network slice so that there is stable network performance.
[0076] At step 520, the predicted data and the actual data are depicted visually. Utilizing the trained models, the network performance for the current network or real time network are predicted which is depicted against the actual value of the current network performance on a display device 240 in user defined formats.
[0077] At step 525, the AI/ML unit 415 is configured to continuously monitor the network performance. On comparing the predicted value and actual value or network performance of each network slices, the one or more deviation of actual value from the predicted value is detected as one or more breaches in the consumer policies. Upon detecting the one or more breaches, the one or more detected breaches are communicated to the data consumers 405 to change policies or take actions to scale in or scale out network slices. The continuous monitoring of the network slice load data and detecting the breaches in consumer policy is continuously performed. The continuous response to changing network conditions and user demands is stored in the data lake 420. The training model is configured to refine the predicting ability based on learning and unlearning from the previous predictions and actions of which data is stored in the data lake 420. The closed loop reporting and action enables continuous learning and optimization of predicting capability of the training model.
[0078] FIG. 6 is a flow diagram of the method 600 for managing the resources in the communication network 105, according to one or more embodiments of the present invention. For the purpose of description, the method 600 is described with the embodiments as illustrated in FIG. 2 and should nowhere be construed as limiting the scope of the present disclosure.
[0079] At step 605, the method 600 includes the step of collecting one or more types of data pertaining to the load in the communication network 105. The data collected includes at least one of the historical data, one or more consumer defined policies and current load in the communication network 105. The plurality of the data sources includes at least one of the databases 220 pertaining to the communication network 105 which may include the network functions, the network application program interfaces and the network management systems. At step 605, the collected data which is raw data is further transformed into standardized data for training the model. The data is further split into the training and the test data.
[0080] At step 610, the method 600 includes the step of training the model with the collected data. The model is trained on the training data to identify the trends and patterns on the training data. The trends and patterns learnt by the training model refer to the threshold values or range of values pertaining to the stable data transmission. The performance of the trained model is ensured by utilizing the test data.
[0081] At step 615, the method 600 includes the step of dynamically predicting the number of resources required to manage the current load in the communication network 105. The prediction is performed utilizing the trained model. The current load and one or more pre-defined policies are compared with the historical data.
[0082] At step 620, the method 600 includes the step of detecting a breach pertaining to the collected data. When the deviation of current load of at least one of the network slices and the one or more pre-defined policies occurs in comparison to the historical data, the detection unit 245 is configured to detect the deviation as the breach in the communication network 105.
[0083] At step 625, the method 600 includes the step of suggesting the remedial actions when the one or more breaches are detected. The recommendation unit 255 is configured to recommend remedial actions include at least one of scaling in or scaling out the one or more network slices. The remedies are performed by at least one of the users or the system 120 by automation.
[0084] The present invention further discloses a non-transitory computer-readable medium having stored thereon computer-readable instructions. The computer-readable instructions are executed by the processor 205. The processor 205 is configured to collect from a plurality of sources one or more types of data pertaining to the load in the communication network 105. The processor 205 is further configured to train the model with the collected slice load data. The processor 205 is further configured to dynamically predict the number of resources required to manage the current load in the communication network 105 using the trained model. The processor 205 is further configured to detect the breach pertaining to the collected data if at least one of the current loads or the one or more pre-defined policies crosses a pre-defined threshold. The processor 205 is further configured to suggest remedial actions, when the breach is detected pertaining to the collected data.
[0085] A person of ordinary skill in the art will readily ascertain that the illustrated embodiments and steps in description and drawings (FIG.1-6) are set out to explain the exemplary embodiments shown, and it should be anticipated that ongoing technological development will change the manner in which particular functions are performed. These examples are presented herein for purposes of illustration, and not limitation. Further, the boundaries of the functional building blocks have been arbitrarily defined herein for the convenience of the description. Alternative boundaries can be defined so long as the specified functions and relationships thereof are appropriately performed. Alternatives (including equivalents, extensions, variations, deviations, etc., of those described herein) will be apparent to persons skilled in the relevant art(s) based on the teachings contained herein. Such alternatives fall within the scope and spirit of the disclosed embodiments.
[0086] The present disclosure incorporates technical advancement in solving the problem managing network slices within a communications network. Further, the present invention improves the efficiency and reliability of data transmission. The flexible scale in and scale out facilitates optimized utilization of resources without under-utilization or over-utilization. The present invention with alternate embodiment of automated solving aggregation of traffic in few network slices and distributing the data in transmission evenly, increases the efficiency of data transmission. The automation upgrades the service quality of the communications network. The present invention integrates analytical data to predict resource usage and trigger remedial actions for seamless scaling without even the need for manual intervention. The present invention increases the customer satisfaction and efficiency of network operators, bringing in technical and economic significance in the field of telecommunications.
[0087] The present invention offers multiple advantages over the prior art and the above listed are a few examples to emphasize on some of the advantageous features. The listed advantages are to be read in a non-limiting manner.

REFERENCE NUMERALS

[0088] Environment- 100
[0089] Communication Network- 105
[0090] Network Operator Equipment -110
[0091] Server-115
[0092] System- 120
[0093] Processor-205
[0094] Memory- 210
[0095] User interface- 215
[0096] Database- 220
[0097] Data Integration unit- 225
[0098] Model Training Unit- 230
[0099] Prediction Unit- 235
[00100] Display Device- 240
[00101] Detection Unit- 245
[00102] Reporting Unit- 250
[00103] Recommendation Unit- 255
[00104] Primary Processor- 305
[00105] Primary Memory-310
[00106] Data Consumers- 405
[00107] Network Data Analytics Function (NWDAF)- 410
[00108] AI/ML Unit- 415
[00109] Data lake- 420
[00110] Data Preprocessing Unit- 425 ,CLAIMS:CLAIMS
We Claim:
1. A method (600) of managing resources in a communication network (105), the method (600) comprising the steps of:
collecting (605), by one or more processors (205), from a plurality of sources, one or more types of data pertaining to load in the communication network (105);
training (610), by the one or more processors (205), a model with the collected data;
dynamically predicting (615), by the one or more processors (205), a number of resources required to manage current load in the communication network (105) using the trained model;
detecting (620), by the one or more processors (205), a breach pertaining to the collected data if at least one of, the current load or the one or more pre-defined policies crosses a pre-defined threshold; and
suggesting (625) remedial actions, by the one or more processors (205), when the breach is detected pertaining to the collected data.

2. The method (600) as claimed in claim 1, wherein the resources include at least one of a network slices.

3. The method (600) as claimed in claim 1, wherein the plurality of sources includes at least one of a database (220), pertaining to the communication network (105) which may include network functions, network application program interfaces and network management systems.

4. The method (600) as claimed in claim 1, wherein the collected data includes at least one of, historical data, one or more consumer defined policies and current load in the communication network (105).

5. The method (600) as claimed in claim 1, wherein the step of, collecting, by one or more processors (205), data from a plurality of sources, further includes the step of:
preprocessing, by the one or more processors (205), the collected data by at least one of data normalizing, data cleaning and removing null values from the collected data.

6. The method (600) as claimed in claim 1, wherein the step of, dynamically predicting, a number of resources required to manage a current load in the communication network (105) using the trained model, further includes the step of:
depicting, by the one or more processors (205), the predicted data and actual value on a display device (240), wherein the predicted data is depicted in multiple network operator defined formats.

7. The method (600) as claimed in claim 1, wherein the step of, detecting, a breach pertaining to the collected data if at least one of, the current load or the one or more pre-defined policies crosses a pre-defined threshold, further includes the step of:
reporting in real time, by the one or more processors (205), to a network operator the detected breach pertaining to the collected data.

8. The method (600) as claimed in claim 1, wherein the remedial actions include at least one of, scale-in and/or scale-out the one or more resources to/from the communication network (105).

9. The method (600) as claimed in claim 1, wherein the step of, dynamically predicting, a number of resources required to manage the current load in the communication network (105) using the trained model, includes the steps of:
comparing, by the one or more processors (205), at least one of, the current load and the one or more pre-defined policies with the historical data;
in response to detecting, by the one or more processors (205), a deviation in at least one of, the current load and the one or more pre-defined policies in comparison to the historical data, predicting the number of resources required to manage the current load in the communication network (105).

10. The method (600) as claimed in claim 9, wherein the historical data is the data learnt by the model during training.

11. The method (600) as claimed in claim 1, wherein the one or more processors (205) continuously monitors the data to detect breach pertaining to the collected data.

12. The method (600) as claimed in claim 1, wherein the model continuously receives feedback from the one or more processors (205), wherein the model adapts and evolve based on the received feedback.

13. A system (120) for managing resources in a communication network (105), the system (120) comprising:
a data integration unit (225), configured to, collect from a plurality of sources, one or more types of data pertaining to load in the communication network (105);
a model training unit (230), configured to, train, a model with the collected data;
a prediction unit (235), configured to, dynamically predict, a number of resources required to manage the current load in the communication network (105) using the trained model;
a detection unit (245), configured to, detect, a breach pertaining to the collected data if at least one of, the current load or the one or more pre-defined policies crosses a pre-defined threshold; and
a recommendation unit (255), configured to, suggest remedial actions, when the breach is detected pertaining to the collected data.

14. The system (120) as claimed in claim 13, wherein the resources include at least one of a network slices.

15. The system (120) as claimed in claim 13, wherein the plurality of sources includes at least one of a database (220), pertaining to the communication network (105) which may include network functions, network application program interfaces and network management systems.

16. The system (120) as claimed in claim 13, wherein the collected data includes at least one of, historical data, one or more consumer defined policies and current load in the communication network (105).

17. The system (120) as claimed in claim 13, wherein the data integration unit (225), is further configured to, preprocess, the collected data by at least one of the data normalizing, the data cleaning and removing null values from the collected data.

18. The system (120) as claimed in claim 13, wherein the prediction unit (235) is further configured to, depict, the predicted data and the actual value on a display device (240); wherein the predicted data is depicted in multiple network operator defined formats.

19. The system (120) as claimed in claim 13, wherein a reporting unit (250) is configured to, report in real time, to a network operator the detected breach pertaining to the collected data.

20. The system (120) as claimed in claim 13, wherein the remedial actions include at least one of, scale-in and/or scale-out the one or more resources to/from the communication network (105).

21. The system (120) as claimed in claim 13, wherein the prediction unit (235), dynamically predicts, a number of resources required to manage a current load in the communication network (105) using the trained model, by:
comparing, at least one of, the current load and the one or more pre-defined policies with the historical data; and
in response to detecting, a deviation in at least one of, the current load and the one or more pre-defined policies in comparison to the historical data, predicting the number of resources required to manage the current load in the communication network (105).

22. The system (120) as claimed in claim 21, wherein the historical data is the data learnt by the model during training.

23. The system (120) as claimed in claim 13, wherein the one or more processors (205) continuously monitors the data to detect breach pertaining to the collected data.

24. The system (120) as claimed in claim 13, wherein the model continuously receives feedback from the one or more processors (205), wherein the model adapts and evolve based on the received feedback.

25. A network operator equipment (110), comprising:
one or more primary processors (305) communicatively coupled to one or more processors (205), the one or more primary processors (305) coupled with a memory (210), wherein said memory (210) stores instructions which when executed by the one or more primary processors (305) causes the network service operator (110) to:
transmit, network operator defined formats to depict predicted data;
wherein the one or more processors (205) is configured to perform the steps as claimed in claim 1.