Method and system for harmonizer framework for load balancer

Abstract

Embodiments of the disclosure describe a method for managing Control Plane (CP) traffic in a wireless communication network. The method includes monitoring the CP traffic between a load balancer (400) and one or more units associated with one or more Network Functions (NFs). The method includes detecting one or more failures in one or more CP sessions associated with one or more units while monitoring the CP traffic. The method includes determining, in response to detecting the one or more failures one or more harmonized cost functions and one or more profile weights associated with each unit to facilitate load balancing across the one or more units. The method includes identifying one or more CP paths associated with the one or more units, to manage the CP traffic in the wireless communication network based on the one or more determined harmonized cost functions and one or more determined profile weights.

Description

METHOD AND SYSTEM FOR HARMONIZER FRAMEWORK FOR LOAD BALANCER

[0001] The present disclosure generally relates to the field of wireless communication systems, and more specifically relates to a method and a system for a harmonizer framework for a load balancer.

[0002] A load balancer in 5G wireless communication systems / networks is a critical component that optimizes resource utilization, enhances application performance, and ensures high availability by distributing incoming network traffic across multiple servers or services. In the context of 5G architecture, the load balancer facilitates efficient management of data flows, thereby reducing latency and preventing bottlenecks in network performance. The load balancer can operate at various layers of an Open Systems Interconnection (OSI) model, including Layer 4 (Transport) and Layer 7 (Application), allowing for intelligent routing based on real-time traffic conditions and application-specific metrics. The load balancer supports both horizontal and vertical scaling, enabling dynamic adjustments to resource allocation in response to fluctuating demand. However, several problems are encountered in an existing load balancer, which is mentioned below.

[0003] The existing cloud-native load balancer employs conventional scheduling algorithms, such as Round Robin (RR) and Least Connection (LC), for distributing CP signaling traffic to Cloud-native Network Functions. These algorithms are inherently single-dimensional, relying on singular cost function variables active connections for LC, and a cyclical approach for RR. Consequently, the conventional scheduling algorithms are insufficient for addressing the multifaceted requirements of 5G services, including latency, reliability, and energy efficiency. 5G New Radio (NR) ensures latency and reliability to fulfill Service Level Agreements (SLAs) for critical applications such as factory automation, autonomous vehicles, remote control, and virtual / augmented reality, any degradation in communication transmission and computational capabilities of nodes within the 5G network can adversely impact latency and reliability. As a result, the end-user experience may be compromised for these essential 5G services.

[0004] The above information is presented as background information only to assist with an understanding of the disclosure. No determination has been made, and no assertion is made, as to whether any of the above might be applicable as prior art with regard to the disclosure.

[0005] This summary is provided to introduce a selection of concepts, in a simplified format, that are further described in the detailed description of the disclosure. This summary is neither intended to identify key or essential inventive concepts of the disclosure nor is it intended for determining the scope of the disclosure.

[0006] According to one embodiment of the present disclosure, a method for managing Control Plane (CP) traffic in a wireless communication network is disclosed herein. The method includes monitoring, by a load balancer, the CP traffic between the load balancer and one or more units associated with one or more Network Functions (NFs). The method further includes detecting, by the load balancer, one or more failures in one or more CP sessions associated with one or more units while monitoring the CP traffic. The one or more failures are attributed to load imbalance. The method further includes determining, in response to detecting the one or more failures, by the load balancer, one or more harmonized cost functions and one or more profile weights associated with each unit to facilitate load balancing across the one or more units. The method further includes identifying, by the load balancer, one or more CP paths associated with the one or more units, to manage the CP traffic in the wireless communication network based on the one or more determined harmonized cost functions and one or more determined profile weights.

[0007] According to another embodiment of the present disclosure, a load balancer for managing Control Plane (CP) traffic in a wireless communication network. The load balancer includes a system. The system may further include a CP traffic management module of a processor coupled with a memory and a communicator. The CP traffic management module is configured to monitor the CP traffic between the load balancer and one or more units associated with one or more Network Functions (NFs). The CP traffic management module is further configured to detect one or more failures in one or more CP sessions associated with one or more units while monitoring the CP traffic. The one or more failures are attributed to load imbalance. The CP traffic management module is further configured to determine, in response to detecting the one or more failures one or more harmonized cost functions and one or more profile weights associated with each unit to facilitate load balancing across the one or more units. The CP traffic management module is further configured to identify one or more CP paths associated with the one or more units, to manage the CP traffic in the wireless communication network based on the one or more determined harmonized cost functions and one or more determined profile weights.

[0008] To further clarify the advantages and features of the present invention, a more particular description of the disclosure will be rendered by reference to specific embodiments thereof, which are illustrated in the appended drawings. It is appreciated that these drawings depict only typical embodiments of the disclosure and are therefore not to be considered limiting of its scope. The disclosure will be described and explained with additional specificity and detail in the accompanying drawings.

[0009] These and other features, aspects, and advantages of the present disclosure will become better understood when the following detailed description is read with reference to the accompanying drawings in which like characters represent like parts throughout the drawings, wherein:

[0010] FIG. 1 illustrates a load balancer in the 5G network;

[0011] FIG. 2 illustrates a load balancer with a harmonizer framework, according to an embodiment as disclosed herein;

[0012] FIGS. 3A-3B illustrates one or more harmonizing different service cost functions and upstream flow service cost computer associated with a Hypertext Transfer Protocol (HTTP) proxy, according to an embodiment as disclosed herein;

[0013] FIG. 4 illustrates a block diagram of the load balancer for managing Control Plane (CP) traffic in a wireless communication network, according to an embodiment as disclosed herein;

[0014] FIG. 5 illustrates an upstream unit cost mechanism designed to determine an energy cost function for upstream data flow servicing, according to an embodiment as disclosed herein;

[0015] FIG. 6 illustrates a comparative analysis between a conventional load balancer and the disclosed load balancer for managing CP traffic, for the upstream data flow servicing, based on a reliability cost function, according to an embodiment as disclosed herein;

[0016] FIG. 7 illustrates a comparative analysis between the conventional load balancer and the disclosed load balancer for managing CP traffic, for the upstream data flow servicing, based on a rebalancing cost function, according to an embodiment as disclosed herein;

[0017] FIGS. 8A-8B illustrates a comparative analysis between the conventional load balancer and the disclosed load balancer for managing CP traffic, for the upstream data flow servicing, based on a heuristic cost function, according to an embodiment as disclosed herein;

[0018] FIG. 9 illustrates a cost function harmonizer calculation, according to an embodiment as disclosed herein;

[0019] FIG. 10 illustrates a weight assignment mechanism, according to an embodiment as disclosed herein; and

[0020] FIG. 11 is a flow diagram illustrating a method for managing the CP traffic in the wireless communication network, according to an embodiment as disclosed herein.

[0021] Further, skilled artisans will appreciate that elements in the drawings are illustrated for simplicity and may not have necessarily been drawn to scale. For example, the flow charts illustrate the method in terms of the most prominent steps involved to help to improve understanding of aspects of the present disclosure. Furthermore, in terms of the construction of the device, one or more components of the device may have been represented in the drawings by conventional symbols, and the drawings may show only those specific details that are pertinent to understanding the embodiments of the present disclosure so as not to obscure the drawings with details that will be readily apparent to those of ordinary skill in the art having the benefit of the description herein.

[0022] For the purpose of promoting an understanding of the principles of the disclosure, reference will now be made to the embodiment illustrated in the drawings and specific language will be used to describe the same. It will nevertheless be understood that no limitation of the scope of the disclosure is thereby intended, such alterations and further modifications in the illustrated system, and such further applications of the principles of the disclosure as illustrated therein being contemplated as would normally occur to one skilled in the art to which the disclosure relates.

[0023] It will be understood by those skilled in the art that the foregoing general description and the following detailed description are explanatory of the disclosure and are not intended to be restrictive thereof.

[0024] Reference throughout this specification to "an aspect", "another aspect" or similar language 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, appearances of the phrase "in an embodiment", "in one embodiment", "in another embodiment" and similar language throughout this specification may, but do not necessarily, all refer to the same embodiment.

[0025] The terms "comprise", "comprising", or any other variations thereof, are intended to cover a non-exclusive inclusion, such that a process or method that comprises a list of steps does not include only those steps but may include other steps not expressly listed or inherent to such process or method. Similarly, one or more devices or sub-systems or elements or structures or components proceeded by "comprises... a" does not, without more constraints, preclude the existence of other devices or other sub-systems or other elements or other structures or other components or additional devices or additional sub-systems or additional elements or additional structures or additional components.

[0026] The embodiments herein and the various features and advantageous details thereof are explained more fully with reference to the non-limiting embodiments that are illustrated in the accompanying drawings and detailed in the following description. Descriptions of well-known components and processing techniques are omitted so as to not unnecessarily obscure the embodiments herein. Also, the various embodiments described herein are not necessarily mutually exclusive, as some embodiments can be combined with one or more other embodiments to form new embodiments. The term "or" as used herein, refers to a non-exclusive or unless otherwise indicated. The examples used herein are intended merely to facilitate an understanding of ways in which the embodiments herein can be practiced and to further enable those skilled in the art to practice the embodiments herein. Accordingly, the examples should not be construed as limiting the scope of the embodiments herein.

[0027] As is traditional in the field, embodiments may be described and illustrated in terms of blocks that carry out a described function or functions. These blocks, which may be referred to herein as units or modules or the like, are physically implemented by analog or digital circuits such as logic gates, integrated circuits, microprocessors, microcontrollers, memory circuits, passive electronic components, active electronic components, optical components, hardwired circuits, or the like, and may optionally be driven by firmware and software. The circuits may, for example, be embodied in one or more semiconductor chips, or on substrate supports such as printed circuit boards and the like. The circuits constituting a block may be implemented by dedicated hardware, or by a processor (e.g., one or more programmed microprocessors and associated circuitry), or by a combination of dedicated hardware to perform some functions of the block and a processor to perform other functions of the block. Each block of the embodiments may be physically separated into two or more interacting and discrete blocks without departing from the scope of the disclosure. Likewise, the blocks of the embodiments may be physically combined into more complex blocks without departing from the scope of the disclosure.

[0028] The accompanying drawings are used to help easily understand various technical features and it should be understood that the embodiments presented herein are not limited by the accompanying drawings. As such, the present disclosure should be construed to extend to any alterations, equivalents, and substitutes in addition to those which are particularly set out in the accompanying drawings. Although the terms first, second, etc. may be used herein to describe various elements, these elements should not be limited by these terms. These terms are generally only used to distinguish one element from another.

[0029] The following description with reference to the accompanying drawings is provided to assist in a comprehensive understanding of various embodiments of the disclosure as defined by the claims and their equivalents. It includes various specific details to assist in that understanding but these are to be regarded as merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the various embodiments described herein can be made without departing from the scope of the disclosure. In addition, descriptions of well-known functions and constructions may be omitted for clarity and conciseness.

[0030] The terms and words used in the following description and claims are not be limited to the bibliographical meanings, but, are merely used by the inventor to enable a clear and consistent understanding of the disclosure. Accordingly, it should be apparent to those skilled in the art that the following description of various embodiments of the disclosure is provided for illustration purpose only and not for the purpose of limiting the disclosure as defined by the appended claims and their equivalents. .

[0031] It is to be understood that the singular forms "a," "an," and "the" include plural referents unless the context clearly dictates otherwise. Thus, for example, reference to "a component surface" includes reference to one or more of such surfaces.

[0032] In various examples of the disclosure described below, a hardware approach will be described as an example. However, since various embodiments of the disclosure may include a technology that utilizes both the hardware-based and the software-based approaches, they are not intended to exclude the software-based approach.

[0033] As used herein, the terms referring to merging (e.g., merging, grouping, combination, aggregation, joint, integration, unifying), the terms referring to signals (e.g., packet, message, signal, information, signaling), the terms referring to resources (e.g. section, symbol, slot, subframe, radio frame, subcarrier, resource element (RE), resource block (RB), bandwidth part (BWP), opportunity), the terms used to refer to any operation state (e.g., step, operation, procedure), the terms referring to data (e.g. packet, message, user stream, information, bit, symbol, codeword), the terms referring to a channel, the terms referring to a network entity (e.g., distributed unit (DU), radio unit (RU), central unit (CU), control plane (CU-CP), user plane (CU-UP), O-DU -open radio access network (O-RAN) DU), O-RU (O-RAN RU), O-CU (O-RAN CU), O-CU-UP (O-RAN CU-CP), O-CU-CP (O-RAN CU-CP)), the terms referring to the components of an apparatus or device, or the like are only illustrated for convenience of description in the disclosure. Therefore, the disclosure is not limited to those terms described below, and other terms having the same or equivalent technical meaning may be used therefor. Further, as used herein, the terms, such as '~ module', '~ unit', '~ part', '~ body’, or the like may refer to at least one shape of structure or a unit for processing a certain function.

[0034] Further, throughout the disclosure, an expression, such as e.g., 'above' or 'below' may be used to determine whether a specific condition is satisfied or fulfilled, but it is merely of a description for expressing an example and is not intended to exclude the meaning of 'more than or equal to' or 'less than or equal to'. A condition described as 'more than or equal to' may be replaced with an expression, such as 'above', a condition described as 'less than or equal to' may be replaced with an expression, such as 'below', and a condition described as 'more than or equal to and below' may be replaced with 'above and less than or equal to', respectively. Furthermore, hereinafter, 'A' to 'B' means at least one of the elements from A (including A) to B (including B). Hereinafter, 'C' and / or 'D' means including at least one of 'C' or 'D', that is, {'C', 'D', or 'C' and 'D'}.

[0035] The disclosure describes various embodiments using terms used in some communication standards (e.g., 3rd Generation Partnership Project (3GPP), extensible radio access network (xRAN), open-radio access network (O-RAN) or the like), but it is only of an example for explanation, and the various embodiments of the disclosure may be easily modified even in other communication systems and applied thereto.

[0036] Throughout this disclosure, the terms "Network Function", "unit", and "pod" are used interchangeably and mean the same.

[0037] In the context of 5G networks, a load balancer is typically implemented as a Service Communication Proxy (SCP) in accordance with 3GPP standards. Its primary function is to efficiently distribute Control Plane (CP) sessions among various 5G network elements. The 3GPP standards have permitted proprietary implementations of the SCP, leading to variability in deployment strategies. Traditional cloud-native load Balancers employ techniques such as Round Robin (RR) and Least Connections (LC) to allocate CP traffic to upstream 5G Network Functions (NFs). However, these methodologies are inherently one-dimensional. For instance, the RR method relies solely on uniform server capabilities, while the LC method focuses exclusively on session liveliness, neglecting the server capabilities when managing traffic distribution.

[0038] Moreover, existing solutions do not adequately address a pluggable harmonizer framework that caters to the diverse service requirements of 5G, including latency, energy efficiency, and reliability. This gap can be bridged by introducing a harmonized cost function that incorporates multiple profiles tailored to specific service needs, as discussed throughout the disclosure (FIGS. 1 to 11).

[0039] The disclosed load balancer framework / method offers a multi-dimensional approach to harmonizing various service requirements. By implementing dynamic weight assignments for each service, the framework prioritizes 5G services according to specific use case demands. For instance, use cases such as discrete automation may necessitate lower end-to-end reliability compared to Intelligent Transport Systems (ITS). The disclosed load balancer framework / method is unprecedented in its ability to integrate multiple 5G service requirements for the establishment of 5G CP paths.

[0040] In addition, the disclosed load balancer framework / method utilizes Artificial Intelligence (AI) and Machine Learning (ML) to analyze a heuristics of Network Function (NF) transmission capabilities and traffic patterns, thereby enhancing latency and reliability in 5G CP path setups, as described in conjunction with FIGS. 1 to 11. The disclosed load balancer framework / method is poised to play a pivotal role in the 5G core network, particularly in the reliable and efficient management of service requests. The 5G standalone architecture facilitates Ultra-Reliable Low Latency Communication (URLLC), which is essential for a range of future applications, including autonomous driving and real-time remote surgeries. The disclosed load balancer framework / method may be instrumental in delivering the instantaneous response times required for these critical applications, and the same principles can be applied to load distribution between Distributed Units (DUs) and a Centralized Units (CU) within the Radio Access Network (RAN).

[0041] Referring now to the drawings, and more particularly to FIGS. 1 to 11, where similar reference characters denote corresponding features consistently throughout the figures, there are shown preferred embodiments.

[0042] FIG. 1 illustrates the load balancer 100 in the 5G network. In the context of the 5G network, several key components play a crucial role in ensuring efficient operations and seamless connectivity in the 5G network. Examples of the key components may include an Access and Mobility Management Function (AMF), a Session Management Function (SMF), a User Plane Function (UPF), a 3rd Generation Partnership Project (3GPP) radio network, a Non-3GPP network, etc. The AMF is configured to perform one or more operations related to user equipment (UE) access, registration, and mobility management. Complementing this, the SMF is configured to manage sessions, encompassing their establishment, modification, and termination. Additionally, the Network Identifier (NI) and Network Area (NA) help define specific network elements and operational regions, respectively, within the broader 5G architecture.

[0043] In the context of the 5G network, each network entity may communicate with other network entities via a specific interface (e.g., Y1, Y2, N1, N2, N3, N4, N6, N11, etc.). For instance, the N3 and N6 interfaces are pivotal in this setup: the N3 interface connects the UPF to a Radio Access Network (RAN), while the N6 interface connects the UPF to external data networks, including the Internet. The UPF itself is essential for handling user data traffic, and optimizing routing and processing to enhance overall network performance. Furthermore, the presence of Non-3GPP networks, such as Wireless Fidelity (Wi-Fi), and an N3 Interworking Function (N3-IWF) ensures interoperability between different network types, enriching the user experience.

[0044] In addition, the 5G network / architecture also delineates various pathways for data flow, including a control plane path, which manages signaling for connection establishment and session management. The transition from the control plane to a user plane path is crucial for maintaining session continuity, while the user plane path itself illustrates the routing of user data packets, emphasizing the importance of low latency. Additionally, a management plane path encompasses the orchestration of network resources, ensuring efficient operation and maintenance of the network infrastructure. Service requirements within this framework are critical for optimal performance.

[0045] For instance, Ultra-Reliable Low Latency Communication (URLLC) necessitates user plane latency to be less than the IMS single-way latency for both downlink and uplink, alongside a control plane latency of less than 10 ms for session establishment. The end-to-end path latency is calculated as Min (A) + (B) + (C), highlighting the need for low latency across all pathways. This monitoring is not confined to URLLC but extends to Mobile Broadband (MBB) and massive IoT (mIoT) sessions, reflecting the diverse demands of modern connectivity. Moreover, energy efficiency is a significant consideration in the design of load balancers 100 within the 5G network. The selection of upstream network functions should prioritize minimal power consumption to reduce operational expenditures (OpEx). Energy consumption for the end-to-end path, measured in Joules, is also calculated as Min (A) + (B) + (C), underscoring the necessity for energy-saving measures in network operations. Together, these interconnected components and requirements illustrate the complexity and sophistication of load balancing in the evolving landscape of 5G networks.

[0046] Thus, it is desired to address the above-mentioned disadvantages or other shortcomings or at least provide a useful alternative as a harmonizer framework for the load balancer.

[0047] FIG. 1 illustrates the load balancer with the harmonizer framework 200, according to an embodiment as disclosed herein. To identify one or more Control Plane (CP) paths associated with multiple units for the management of CP traffic within a wireless communication network, utilizing harmonized cost functions and profile weights. The disclosed method (load balancer with the harmonizer framework 200) performs several operations detailed below. Example of the wireless communication network may include, but is not limited to, a Fifth Generation (5G) network and a beyond 5G network.

[0048] At operation-1, a Service Management Orchestrator (SMO) 201 enables, via an LB controller 203, a harmonizer function during a load balancer installation procedure. The SMO 201 enables one or more LB services with specified profiles and weight inputs for each 5G deployment. At operation-2, the LB controller 203 may create an LB deployment that is exposed as Network Function (NF) service 204 using a service proxy 205, a config reloader 206, and a profile builder 207, which are exposed as an NF load balancing service.

[0049] At operation-3, the config reloader 206 may feed weights (e.g., W1, W2, etc.) for external factors / services / variables, including, for example, but not limited to, Service Quality Flow Identifiers (QFI), time, geography, and other factors (e.g., Factor-N) to the service proxy 205, as defined by the SMO 201.

[0050] At operations-4, 5, 6, and 7, the profile builder 207 evaluates one or more programmed services (e.g., P1, P2, etc.), as described in conjunction with FIG. 5, FIG. 6, FIG. 7, and FIGS. 8A-8B. For instance, (a) analyzing energy utilized by upstream units for servicing upstream flow costs; (b) analyzing one or more reliability metrics of upstream units for servicing upstream flow costs; (c) analyzing one or more rebalancing requirements of upstream units for servicing upstream flow costs.; and (d) providing an extensible framework for programming additional services.

[0051] In addition, one or more profile weights (e.g., W1, W2, etc.) are systematically assigned to each service requirement / programmed service (e.g., P1, P2, etc.), incorporating factors such as time and geographical considerations, as described in conjunction with FIG. 10. The weight function can be expressed as " weight　Function[i]=[W1, W2,..., Wn]", where "i" signifies a type of service (e.g., Quality of experience factors such as reliability, latency, and energy efficiency). This framework is designed to be extensible, allowing for the integration of additional external factors / services / variables, including user-defined parameters related to time and geography.

[0052] At operations-8 and 9, each output from the profile builder 207 feeds into a pluggable cost function architecture within the service proxy 205, which evaluates a profile value for each NF replica 208, denoted as aijor said matrix "A", where "i" represents a profile and "j" denotes a replica. In other words, the profile builder 207 feeds cost function data (operations 4 to 7) alongside weights (operation-3) into the service proxy 205 to determine the harmonized cost function, as described in conjunction with FIG. 9. The pluggable cost function architecture facilitates the harmonization of load balancing across 5G control plane sessions by leveraging one or more profiles / programmed services (e.g., P1, P2, etc.) to derive comprehensive service cost functions. The harmonized cost function is represented as "A·WT", where "W" denotes a multi-dimensional matrix encapsulating external factors such as service type, temporal considerations, geographical influences, and other pertinent parameters. Subsequently, the service proxy 204 utilizes the harmonized cost functions to effectively load balance traffic across NF replicas 208 (e.g., replica-1, replica-2, etc.).

[0053] FIGS. 3A-3B illustrates one or more harmonizing different service cost functions and upstream flow service cost computers associated with a Hypertext Transfer Protocol (HTTP) proxy, according to an embodiment as disclosed herein.

[0054] FIG. 3A illustrates a Kubernetes cluster architecture 301. The Kubernetes cluster architecture is a sophisticated framework designed to facilitate the orchestration of containerized applications. Within this Kubernetes cluster architecture 301, several key components play pivotal roles in ensuring efficient resource management and service delivery.

[0055] Examples of the several key components may include an Access and Mobility Management Function (AMF) 302, Session Management Function (SMF) 303, User Plane Function (UPF) 304 and Unified Data Management (UDM) 305, a service mesh 306, and multiple HTTP proxies (e.g., 307, 308, 309, and 310).

[0056] The AMF 302 is configured to manage the lifecycle of applications within the Kubernetes cluster architecture 301, ensuring that deployments are executed with high availability and scalability. The AMF 302 is further configured to handle user sessions and mobility management. The SMF 303 is configured to terminate NAS signaling related to session management, PDU session control (i.e. establishing, modifying, and terminating PDU sessions) policy enforcement, Charging and LI support, IP address management, and UPF selection. The UPF 304 and the UDM 305 are essential components for managing user data and session continuity within the Kubernetes cluster architecture 301, allowing for efficient data handling and user experience optimization.

[0057] In addition, multiple HTTP proxies (e.g., 307, 308, 309, and 310) are deployed within the Kubernetes cluster architecture 301 to manage incoming and outgoing traffic, serving as gateways for client requests and enhancing security through isolation and control mechanisms. These proxies facilitate both north-south and east-west traffic, ensuring seamless communication between external clients and internal services. The load balancer (311,312, 313, and 314) embedded within the HTTP proxy (e.g., 307, 308, 309, and 310) is a critical component of the Kubernetes cluster architecture 301. It ensures efficient traffic distribution, monitors service health, maintains session persistence, and integrates seamlessly with the service mesh to provide a robust and reliable application environment. Herein, the service mesh 306 is a critical component that enhances communication between microservices, the service mesh 306 provides robust features such as traffic management, security, and observability. The service mesh 306 enables fine-grained control over service interactions, facilitating both East-West (service-to-service) and North-South (client-to-service) traffic flows.

[0058] In one or more embodiments, the disclosed method has the potential to optimize the setup of 5G Control Plane (CP) signals by efficiently managing both east-west traffic (inter-5G Core unit communication) and north-south traffic (communication between g-NodeB / 4G Core and 5G Core) at the load balancer (311,312, 313, and 314). This optimization is facilitated by a set of cost functions (e.g., harmonized cost functions) designed to balance traffic flow or said efficient load balancing flow functions in the 5G control plane setup, thereby delivering a range of benefits, as outlined below.

[0059] a) Energy aware: Choose energy-efficient upstream NF for servicing flow from the pleural of upstream units energy cost function with a combination of other profiles and external factors using weights.

[0060] b) Reliability aware: Maintain reliability of units by determining the safe operating threshold of upstream units; thereby limiting the servicing of flow to units about to cross the operating threshold reliability cost function with a combination of other profiles and external factors using weights.

[0061] c) Rebalance aware: Maintain logical classification of flows; For instance, flows with the same registration and de-registration time like IoT smart meter flows can be admitted in the same upstream units; therefore, this upstream NF can be evacuated from the cloud without rebalancing the load across upstream units. Rebalancing Cost Function with a combination of other profiles and external factors using weights.

[0062] d) Heuristics aware: Forecasting the number of pending requests for each upstream NF over a defined period to improve the CP signal setup between units / nodes. Heuristic Cost Function with a combination of other profiles and external factors using weights.

[0063] FIG. 3B illustrates upstream flow service cost computers associated with the HTTP proxy 302. In one or more embodiments, the disclosed method provides an integrating upstream flow service computer for enhanced load balancing across multiple cost functions (e.g., harmonized cost functions) such as energy, reliability, rebalance, and heuristics.

[0064] a) In the listener manager, each HTTP stream (or flow) is linked to a corresponding downstream HTTP servicing flow cost function. Initially, the request is processed through the servicing cost function. Upon invocation of the decode headers method within the router filter, the appropriate route is selected, and a cluster is identified. The request headers associated with the stream are then forwarded to an upstream endpoint within the designated cluster, in accordance with the selected servicing cost characteristics. Additionally, the router filter retrieves an HTTP connection pool from the cluster manager corresponding to the identified cluster.

[0065] b) Load balancing specific to the cluster is executed by the cluster manager to identify an endpoint (Upstream node) that optimally satisfies the cost criteria for servicing the HTTP stream. The circuit breakers of the cluster are assessed to ascertain whether a new stream can be processed. If the endpoint's connection pool is either empty or lacks sufficient capacity, a new connection to the endpoint is established.

[0066] c) For each stream, an upstream node is designated that effectively aligns with specified criteria (e.g., energy, reliability). The HTTP / 2 codec of the upstream endpoint multiplexes and frames the request's stream alongside any other streams directed to that upstream node over a single TCP connection.

[0067] FIG. 4 illustrates a block diagram of a load balancer 400 for managing CP traffic in a wireless communication network, according to an embodiment as disclosed herein.

[0068] In one or more embodiments, the load balancer 400 may relate to the load balancer with the harmonizer framework 200. The wireless communication network may include one or more network entities (not shown in FIG. 4). Examples of the one or more network entities may include, but are not limited to, the AMF, the SMF, the UPF, etc.

[0069] In one or more embodiments, the load balancer 400 may operate as a Service Communication Proxy (SCP) to manage a load distribution in the one or more CP sessions between at least one Radio Access Network (RAN) node and one or more core modules, or among core modules.

[0070] In one or more embodiments, the load balancer 400 comprises a system 401. The system 401 may include a memory 410, a processor 420, and a communicator 430. In one or more embodiments, the system 401 may be implemented on one or multiple electronic devices (not shown in FIG. 4).

[0071] In one or more embodiments, the memory 410 stores instructions to be executed by the processor 420 for managing the CP traffic in the wireless communication network, as discussed throughout the disclosure. The memory 410 may include non-volatile storage elements. Examples of such non-volatile storage elements may include magnetic hard discs, optical discs, floppy discs, flash memories, or forms of electrically programmable memories (EPROM) or electrically erasable and programmable (EEPROM) memories. In addition, the memory 410 may, in some examples, be considered a non-transitory storage medium. The term "non-transitory" may indicate that the storage medium is not embodied in a carrier wave or a propagated signal. However, the term "non-transitory" should not be interpreted that the memory 410 is non-movable. In some examples, the memory 410 can be configured to store larger amounts of information than the memory. In certain examples, a non-transitory storage medium may store data that can, over time, change (e.g., in Random Access Memory (RAM) or cache). The memory 410 can be an internal storage unit, or it can be an external storage unit of the load balancer 400, a cloud storage, or any other type of external storage.

[0072] In one or more embodiments, the processor 420 communicates with the memory 410, and the communicator 430. The processor 420 is configured to execute instructions stored in the memory 410 and to perform various processes for managing the CP traffic in the wireless communication network, as discussed throughout the disclosure. The processor 420 may include one or a plurality of processors, maybe a general-purpose processor, such as a Central Processing Unit (CPU), an Application Processor (AP), or the like, a graphics-only processing unit such as a Graphics Processing Unit (GPU), a Visual Processing Unit (VPU), and / or an Artificial intelligence (AI) dedicated processor such as a Neural Processing Unit (NPU).

[0073] In one or more embodiments, the processor 420 may include a CP traffic management module 421. The CP traffic management module 421 is implemented by processing circuitry such as logic gates, integrated circuits, microprocessors, microcontrollers, memory circuits, passive electronic components, active electronic components, optical components, hardwired circuits, or the like, and may optionally be driven by firmware. The circuits may, for example, be embodied in one or more semiconductor chips, or on substrate supports such as printed circuit boards and the like.

[0074] In one or more embodiments, the CP traffic management module 421 may perform various operations, to manage the CP traffic in the wireless communication network, outlined as follows.

[0075] In one or more embodiments, the CP traffic management module 421 is configured to monitor the CP traffic between the load balancer and one or more units associated with one or more Network Functions (NFs) (e.g., AMF, SMF, etc.). The CP traffic management module 421 is further configured to detect one or more failures in one or more CP sessions associated with one or more units while monitoring the CP traffic, where the one or more failures are attributed to load imbalance.

[0076] In one or more embodiments, in response to detecting the one or more failures, the CP traffic management module 421 is further configured to determine one or more harmonized cost functions and one or more profile weights associated with each unit to facilitate load balancing across the one or more units, which may relate to FIG. 2. The one or more harmonized cost functions for upstream data flow servicing comprise an energy cost function, a reliability cost function, a rebalancing cost function, and a heuristic cost function.

[0077] In one or more embodiments, to determine the one or more harmonized cost functions, the CP traffic management module 421 is configured to integrate one or more profiles and one or more external factors, utilizing predefined weighted metrics, to determine the one or more harmonized service cost functions. Examples of the one or more profiles may include, but are not limited to, an energy profile, a reliability profile, a rebalancing profile, and a heuristics profile, and each profile comprises one or more cost attributes. Examples of the one or more external factors may include, but are not limited to, service information, time information, and location information.

[0078] In one or more embodiments, the CP traffic management module 421 is further configured to identify one or more CP paths associated with the one or more units, to manage the CP traffic in the wireless communication network based on the one or more determined harmonized cost functions and one or more determined profile weights, as described in conjunction with FIG. 5, FIG. 6, FIG. 7, FIGS. 8A-8B, FIG. 9, and FIG. 10.

[0079] In one or more embodiments, to identify the one or more CP paths for upstream data flow servicing, the CP traffic management module 421 is configured to determine one or more energy parameters associated with each PoD. The one or more energy parameters may include, but are not limited to, a value of energy level, a value of consumed energy, a number of User Plane (UP) sessions, and a Control Plane (CP) session. The CP traffic management module 421 is further configured to determine an energy cost function associated with each unit based on the one or more energy parameters to identify an optimal energy-efficient unit among a plurality of units. The CP traffic management module 421 is further configured to identify the one or more CP paths for upstream data flow servicing based on the identified optimal energy-efficient unit, as described in conjunction with FIG. 5.

[0080] For instance, consider a scenario where the CP traffic management module 421 may identify the one or more CP paths for upstream data flow servicing by utilizing the value of energy level, the value of consumed energy, the number of UP sessions, and the CP session, for example, as shown below in Table-1.

[0081]

[0082] Further, the SMO 201 can be tuned to orchestrate the NF based on weighted upstream unit energy consumption. In one example, the servicing ability of UPF NF may depend on the number of user plane sessions supported (on an Avg.). In another example, the servicing ability of SMF NF may depend on the number of control plane sessions supported (on an Avg.)

[0083] In one or more embodiments, to identify the one or more CP paths for upstream data flow servicing, the CP traffic management module 421 is configured to determine one or more reliability parameters associated with each Unit. The one or more reliability parameters may include, but are not limited to, a reliability weight, a session threshold, a current session count, and a value of Heart Beat (HB). The CP traffic management module 421 is further configured to determine a reliability cost function associated with each unit based on the one or more reliability parameters to identify an optimal safe-operating unit among a plurality of units. The CP traffic management module 421 is further configured to identify the one or more CP paths for upstream data flow servicing based on the identified optimal safe-operating unit, as described in conjunction with FIG. 6.

[0084] In one or more embodiments, to identify the one or more CP paths for upstream data flow servicing, the CP traffic management module 421 is configured to determine one or more rebalancing parameters associated with each unit. The one or more rebalancing parameters may include, but are not limited to, Long Term (LT) traffic information and Short Term (ST) traffic information. The CP traffic management module 421 is further configured to determine a rebalancing cost function associated with each unit based on the one or more rebalancing parameters. The CP traffic management module 421 is further configured to distribute one or more sessions between a dedicated unit and one or more normal Units among a plurality of units based on the determined rebalancing cost function. The CP traffic management module 421 is further configured to identify the one or more CP paths for upstream data flow servicing based on the one or more distributed sessions, as described in conjunction with FIG. 7.

[0085] In one or more embodiments, to identify the one or more CP paths for upstream data flow servicing, the CP traffic management module 421 is configured to determine one or more heuristic parameters associated with each unit. The one or more heuristic parameters may include, but are not limited to, a value of Round Trip Time (RTT), a value of pending request, a value of forecasted RTT, and a value of forecasted pending request. The CP traffic management module 421 is further configured to determine a heuristic cost function associated with each unit based on the one or more heuristic parameters to identify an optimal low-latency unit among a plurality of units. The CP traffic management module 421 is further configured to identify the one or more CP paths for upstream data flow servicing based on the identified optimal low-latency unit, as described in conjunction with FIG. 8B.

[0086] In one or more embodiments, the CP traffic management module 421may configure one or more weights assigned to each profile in real-time, using a Deep Reinforcement Learning, based on one or more external factors that influence each slice flow, as described in conjunction with FIG. 9 and FIG. 10.

[0087] The communicator 430 is configured for communicating internally between internal hardware components and with external devices (e.g., server) via one or more networks (e.g., radio technology). The communicator 430 includes an electronic circuit specific to a standard that enables wired or wireless communication.

[0088] A function associated with the various components of the load balancer 400 may be performed through the non-volatile memory, the volatile memory, and the processor 420. One or a plurality of processors controls the processing of the input data in accordance with a predefined operating rule or AI model stored in the non-volatile memory and the volatile memory. The predefined operating rule or AI model is provided through training or learning. Here, being provided through learning means that, by applying a learning algorithm to a plurality of learning data, a predefined operating rule or AI model of the desired characteristic is made. The learning may be performed in a device itself in which AI according to an embodiment is performed, and / or may be implemented through a separate server / system. The learning algorithm is a method for training a predetermined target device (for example, a robot) using a plurality of learning data to cause, allow, or control the target device to decide or predict. Examples of learning algorithms include, but are not limited to, supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning.

[0089] The AI model may consist of a plurality of neural network layers. Each layer has a plurality of weight values and performs a layer operation through a calculation of a previous layer and an operation of a plurality of weights. Examples of neural networks include, but are not limited to, convolutional neural network (CNN), deep neural network (DNN), recurrent neural network (RNN), restricted Boltzmann Machine (RBM), deep belief network (DBN), bidirectional recurrent deep neural network (BRDNN), generative adversarial networks (GAN), and deep Q-networks.

[0090] Although FIG. 4 shows various hardware components of the load balancer 400, but it is to be understood that other embodiments are not limited thereon. In other embodiments, the load balancer 400 may include less or more number of components. Further, the labels or names of the components are used only for illustrative purposes and do not limit the scope of the disclosure. One or more components can be combined to perform the same or substantially similar functions to manage the CP traffic in the wireless communication network.

[0091] FIG. 5 illustrates an upstream unit cost mechanism 500 designed to determine an energy cost function for upstream data flow servicing, according to an embodiment as disclosed herein.

[0092] To determine the energy cost function associated with upstream flow servicing, an energy estimator may execute a series of operations utilizing one or more integrated modules. These one or more integrated modules typically include a profile distributor, a model server, an Operating System / Virtual Machine (OS / VM) unit, and a monitoring unit.

[0093] The profile distributor is configured to encompass various upstream units, along with a worklet that interfaces with a cloud orchestrator. It integrates a hardware profiler in conjunction with a hardware interface, which may include sensors, Hardware Control Interface (HCI), Running Average Power Limit (RAPL) or Application Power Management (APM) via Model Specific Registers (MSR), and Graphics Processing Unit (GPU) metrics. Additionally, it features an I / O metric exporter that employs extended Berkeley Packet Filter (eBPF) virtual machines, Memory Allocation Protocol (MAP), and system calls that are interconnected with the OS / VM unit.

[0094] The output generated by the profile distributor is subsequently routed to the energy estimator, the model server, and the monitoring unit. The energy estimator is configured to provide an output related to power utilization metrics, including CPU, RAM, and I / O statistics, which are associated with various vendor specifications, which allows for a detailed analysis of energy consumption patterns, facilitating informed decision-making regarding resource allocation and optimization in upstream flow servicing.

[0095] FIG. 6 illustrates a comparative analysis between a conventional load balancer 100 and the load balancer 400 for managing CP traffic, for the upstream data flow servicing, based on the reliability cost function, according to an embodiment as disclosed herein. Consider scenarios (601 and 602) where a load balancer is positioned between the AMF and multiple SMFs, to manage the CP traffic.

[0096] In a first scenario 601, the conventional load balancer 100 typically relies on standard scheduling algorithms to manage the CP traffic. This approach can lead to suboptimal performance, as evidenced by the scenario where SMF-3 experiences heartbeat failures due to an excessive number of concurrent sessions, resulting in overload conditions.

[0097] In a second scenario 602, in contrast, the load balancer 400 introduces a sophisticated mechanism for load distribution that incorporates a proactive learning phase prior to session allocation. Specifically, the load balancer 400 monitors and analyzes a correlation between each unit's heartbeat failures and a number of active sessions over a defined temporal window. This analytical process enables the load balancer 400 to establish a session threshold for each unit (e.g., SMF-3), thereby enhancing system reliability.

[0098] This reliability cost function is determined from one or more reliability parameters that characterize the performance and stability of each unit. In essence, the load balancer 400 dynamically assesses the reliability of sessions at any given moment by integrating a variety of profiles and external factors, weighted appropriately to reflect their influence on performance. The mathematical representation of the reliability cost function is stated below.

[0099] Reliability cost function = Reliability_Weight * (Session threshold - Current session_count) (1)

[0100] To determine the reliability cost function, the load balancer 400 performs a series of operations aimed at calculating the reliability cost function for each unit. The series of operations involved in the computation of the reliability cost function are detailed below.

[0101] a) Measuring traffic, by a traffic volume collection module associated with the load balancer 400 (not shown in FIG. 6), between the load balancer 400 and each upstream host (e.g., SMF-3) over the defined temporal window / period.

[0102] b) Capturing, by a heartbeat failure collection module associated with the load balancer 400 (not shown in FIG. 6), failures of upstream hosts' heartbeats over the defined temporal window / period.

[0103] c) Combining, by a correlation module associated with the load balancer 400 (not shown in FIG. 6), data from the traffic volume and heartbeat failure modules.

[0104] d) Determining, by a session threshold calculation module associated with the load balancer 400 (not shown in FIG. 6), a maximum number of sessions to prevent heartbeat failures.

[0105] e) Preserving, by a threshold maintenance module associated with the load balancer 400 (not shown in FIG. 6), threshold information for each upstream host.

[0106] f) Detecting, by an analytic engine associated with the load balancer 400 (not shown in FIG. 6), one or more anomalies, including sudden bursts of traffic attributed to abnormal handovers when a neighbour cell is down.

[0107] FIG. 7 illustrates a comparative analysis between the conventional load balancer 100 and the load balancer 400 for managing CP traffic, for the upstream data flow servicing, based on a rebalancing cost function, according to an embodiment as disclosed herein. Consider scenarios (701 and 702) where a load balancer is positioned between the AMF and multiple SMFs, to manage the CP traffic.

[0108] In a first scenario 701, conventional load balancer 100 employs standard scheduling algorithms to efficiently distribute CP traffic. However, this traditional approach often results in suboptimal performance due to its inability to adapt dynamically to varying traffic patterns and session characteristics. The conventional load-balancing mechanism relies heavily on predefined algorithms that may not account for the real-time state of sessions. This can lead to inefficiencies, particularly during peak load conditions, where traffic distribution may not align with the actual resource availability or session activity, ultimately degrading the quality of service.

[0109] In a second scenario 702, in contrast, the load balancer 400 introduces a sophisticated methodology for session distribution based on session liveness metrics. Specifically, it intelligently allocates sessions to specific SMFs. This dynamic allocation is predicated on the evaluation of the one or more rebalancing parameters that contribute to the determination of the rebalancing cost function.

[0110] Examples of the one or more rebalancing parameters may include, but are not limited to, a unique identifier for each session (Session ID), an originating IP address of the traffic (source IP), a port number on a source device (source port), a target IP address for the traffic (target IP), a port number on a destination device (destination port), a communication protocol in use(e.g., TCP, UDP), a time at which the session was initiated (timestamp), a total time span of the session (flow duration), a cumulative number of packets sent from the source device to the destination device "Total Forward Packets (TF)", a cumulative number of packets sent from the destination device back to the source device "Total Backward Packets (TB)", a size of the packets being transmitted (packet length), a time taken for a packet to travel to the destination and back "Packet Round-Trip Time (RTT)", a ratio of backward packets to forward packets "Down-Up Ratio (TB / TF)", a mean size of packets transmitted during the session (average packet size). The mathematical representation of the rebalancing cost function is stated below.

[0111] Rebalancing cost function = (LT_flag * LT%) + (ST_flag * ST%) (2)

[0112] To assess session liveness, the load balancer 400 performs a series of operations aimed at calculating the rebalancing cost function for each unit. The series of operations involved in the computation of the rebalancing cost function are detailed below.

[0113] a) Optimized resource allocation through session-based clustering:

[0114] ⅰ. The implementation of a clustering mechanism on LB for network traffic based on flow duration enables efficient resource allocation and reduces rebalancing long-term sessions.

[0115] ⅱ. Long-term (LT) traffic patterns are segregated from short-term (ST) ones, allowing dedicated backend allocation for sustained flows and dynamic scaling for transient traffic, optimizing resource utilization

[0116] ⅲ. Rebalancing cost function = (LT_flag * LT%) + (ST_flag * ST%); here, LT_flag / ST_flag, enabled if session is LT / ST, and LT% / ST% indicates a percentage of LT / ST sessions

[0117] b) Anomaly handling in traffic behavior: The clustering process, recalibrated from real-time datasets at regular intervals, adeptly identifies anomalies in traffic behavior, such as shifts from long-term to short-term patterns due to UE movements. This adaptive approach ensures continuous optimization of resource utilization despite unexpected changes in traffic nature. The above points help to calculate the probability of the number of sessions migrated at that moment with a combination of other profiles and external factors using weights.

[0118] The load balancer 400 also incorporates a mechanism for scaling unit(s) resources in response to session termination events. When a significant number of sessions are concluded, the load balancer 400 can dynamically scale in resources, optimizing operational efficiency. Furthermore, the load balancer 400 differentiates between long-term and short-term traffic patterns. Long-term traffic is directed to dedicated backend resources, while short-term traffic is routed to scaled-up backend resources. This strategic distribution minimizes the need for frequent rebalancing, achieving a reduction in rebalancing operations by approximately 15%.

[0119] FIGS. 8A-8B illustrates a comparative analysis between the conventional load balancer 100 and the load balancer 400 for managing CP traffic, for the upstream data flow servicing, based on a heuristic cost function, according to an embodiment as disclosed herein. Consider scenarios (801 and 802) where a load balancer is positioned between the AMF and multiple SMFs, to manage the CP traffic.

[0120] In a first scenario 801, the conventional load balancer 100 utilizes established scheduling algorithms to optimize the distribution of CP traffic, primarily relying on two key metrics, Round Trip Time (RTT) and one or more pending requests. The RTT serves as an indicator of historical performance, reflecting latency experienced during past transactions, while the one or more pending requests provide insight into the current operational state by measuring the number of requests awaiting processing. The mathematical representation of the cost function for the conventional load balancer 100 is stated below.

[0121] Cost function = RTT_ewma Х Pending Request[t] (3)

[0122] However, this approach has notable disadvantages, including its reliance solely on past performance metrics, which can lead to suboptimal resource allocation during fluctuating traffic conditions and an inability to adapt to emerging patterns.

[0123] In a second scenario 802, in contrast, the load balancer 400 employs a sophisticated time series forecasting algorithm that leverages multiple heuristic parameters to derive a more comprehensive heuristic cost function. This approach incorporates not only RTT (value of RTT) and one or more pending requests (value of pending request) but also forecasted RTT (value of forecasted RTT) and forecasted pending requests (value of forecasted pending request). The forecasted RTT indicates a predictive metric that estimates future latency based on historical trends and expected changes in traffic patterns. The forecasted pending requests anticipate future demand by analyzing factors such as transmission capacity, traffic characteristics, and computational resources.

[0124] The load balancer 400 may determine the heuristic cost function associated with each unit based on the one or more heuristic parameters to identify the optimal low-latency unit among the plurality of units (e.g., SMF-1, SMF-2, SMF-3). The mathematical representation of the heuristic cost function is stated below, where "t" is time.

[0125] Heuristic cost function (forecast based cost function) = 0.75 * (RTT_ewma * pending_request[t]) + 0.25 * (RTT _forecasted * pending_req_forecasted) (4)

[0126] To identify the one or more CP paths, the load balancer 400 performs a series of operations for each unit. The series of operations involved in the computation of the heuristic cost function are detailed below.

[0127] a) Forecasting: Employing at least one Artificial Intelligence and Machine Learning (AI-ML) model to predict the number of pending requests for each upstream host over a specified time frame. For instance, Seasonal Autoregressive Integrated Moving Average (SARIMA) forecasting model.

[0128] b) Load balancing policy application: Utilizing a designated load balancing policy, the heuristic cost function incorporates Round Trip Time (RTT), pending requests, forecasted RTT, and forecasted pending requests over a defined decay periodic interval (n) to effectively distribute traffic.

[0129] c) Traffic prediction: Analyzing traffic volume, application types, user behavior, network topology, and congestion control mechanisms, which indirectly influence pending requests and RTT. By continuously monitoring and analyzing these predictor variables, the accuracy and precision of forecasting RTT and pending requests are enhanced.

[0130] d) Upstream host selection: By factoring in future pending requests and RTT, the selection of the upstream host can reduce CP signaling time compared to conventional load balancer models and making more reliable NFs to achieve SLAs of Next Generational Networks (NGN) applications.

[0131] e) Anomaly detection: Identifying one or more anomalies such as sudden traffic surges and unexpected network congestion.

[0132] The aforementioned points contribute to optimizing the latency associated with CP session establishment time required by services at any given moment, integrating various profiles and external factors through weighted considerations. Consequently, the load balancer 400 anticipates future latency and demand based on parameters including transmission capacity, traffic characteristics, and computational resources.

[0133] The advantages of this advanced mechanism encompass improved resource management, enhanced adaptability to fluctuating traffic patterns, and the capability to proactively optimize performance to identify the one or more CP paths, ultimately resulting in increased efficiency and reliability in load distribution. Notably, the load balancer 400 utilizing the heuristic framework demonstrates a reduction in latency compared to traditional round-robin methods.

[0134] FIG. 9 illustrates a cost function harmonizer calculation 900, according to an embodiment as disclosed herein.

[0135]

[0136] Subsequently, the load balancer 400 assigns weights "Wk" to each parameter through a DRL methodology, as described in conjunction with FIG. 10. These weights are defined for external factors including service type, time, and geographical location. The combinations enabled by the SMO 201 process allow for the retrieval of weights from the configuration reloader 206, which are then assigned to each profile value for the Network Function (NF) pod as an initial state. These weights are dynamically adjusted in response to service flow requirements, external influences, and the behavior of the NF pod, leveraging the DRL methodology.

[0137]

[0138]

[0139] FIG. 10 illustrates a weight assignment mechanism 1000, according to an embodiment as disclosed herein. In the context of the weight assignment mechanism 1000 via the DRL methodology, for optimal weight adjustment, for example, a Proximal Policy Optimization (PPO) algorithm is employed to dynamically modify the weight matrix "W" for effective load balancing, taking into account external factors and flow types. The load balancer 400 may perform several operations for the configuration and training of a DRL model, which is stated below.

[0140]

[0141]

[0142] For instance, consider a scenario associated with a cloud-based video streaming service, user demand fluctuates significantly throughout the day, particularly during peak hours like evenings when many users stream movies and shows, compared to off-peak hours such as early mornings when demand decreases. To manage this variability and ensure a seamless streaming experience, the load balancer 400 employs the cost function to evaluate the performance of each pod hosting video content across various geographical locations. This cost function considers parameters like current load, response time, and user location. For instance, if "Pod A" (e.g., SMF-1) is heavily loaded while "Pod B" (e.g., SMF-2) remains underutilized, the cost function reflects higher costs for Pod A.

[0143] To facilitate fair comparisons, the performance metrics of each pod such as response time and bandwidth usage are normalized. The load balancer 400 also assigns weights to various parameters, including time of day, geographical location, and service type. During peak hours, for example, the weight for response time may be increased to prioritize pods capable of delivering faster streaming. The system further enhances its efficiency by employing the DRL methodology, such as PPO, which continuously learns from traffic patterns. As user behavior evolves, such as increased streaming during weekends, the methodology dynamically adjusts the weights to optimize load distribution.

[0144] At any moment, the load balancer 400 calculates the cost function for each pod, directing new user requests to the pod with the lowest cost function value, which indicates its ability to handle incoming traffic efficiently. In the event of a sudden traffic spike, such as the release of a popular show, the load balancer rapidly reassesses the situation, recalculates the weights based on the new traffic flow, and may redirect users to additional pods to maintain performance. By leveraging the cost function and dynamically adjusting weights through DRL, the video streaming service can effectively manage varying traffic loads, thereby minimizing buffering and downtime while enhancing overall user satisfaction.

[0145] FIG. 11 is a flow diagram illustrating a method 1100 for managing the CP traffic in the wireless communication network, according to an embodiment as disclosed herein. The method 1100 may execute multiple operations to manage the CP traffic, which are given below.

[0146] At operation 1101, the method 1100 includes monitoring the CP traffic between the load balancer and one or more units associated with one or more NFs. At operation 1102, the method 1100 includes detecting the one or more failures in the one or more CP sessions associated with the one or more units while monitoring the CP traffic. At operation 1103, the method 1100 includes determining, in response to detecting the one or more failures, the one or more harmonized cost functions and the one or more profile weights associated with each unit to facilitate load balancing across the one or more units. At operation 1104, the method 1100 includes identifying the one or more CP paths associated with the one or more units, to manage the CP traffic in the wireless communication network, based on the one or more determined harmonized cost functions and one or more determined profile weights. Further, a detailed description related to the various operations of FIG. 11 is covered in the description related to FIG. 2 to FIG. 10, and is omitted herein for the sake of brevity.

[0147] In one or more embodiments, the disclosed method / harmonizer framework 200 for the load balancer 400 has several advantages, which are mentioned below.

[0148] The harmonizer framework 200 offers a sophisticated approach to load balancing by analyzing various characteristics of NF units, such as response time, pending request latency, session thresholds, session liveliness, and energy consumption. This analysis is critical for enhancing the reliability, efficiency, and overall performance of NF deployments. The harmonizer framework 200 evaluates critical metrics, including, for example,:

[0149] a) Response time: Assessing the latency of NF units to optimize user experience.

[0150] b) Pending Requests: Monitoring future requests to manage load effectively.

[0151] c) Session thresholds: Establishing limits to prevent heartbeat failures in NF units.

[0152] d) Session clustering: Grouping sessions based on liveliness to enhance reliability.

[0153] e) Energy consumption: Analyzing energy usage to promote efficiency.

[0154] Dynamic cost function matrix: Inputs from the analysis are compiled into a multi-dimensional cost function matrix with dynamic weights that consider external factors such as service requirements, time constraints, and geographic locations. This matrix serves as the foundation for selecting optimal NF units, not only for immediate performance but also for future scalability.

[0155] Deployment architecture: The harmonizer framework 200 operates as a sidecar container alongside service proxies (e.g., Envoy, Samsung Sloth) within the deployment of the load balancer 400. This architecture facilitates seamless integration and enhanced functionality.

[0156] Data collection and processing: The harmonizer framework 200 leverages Kubernetes API, proxy metrics API, and a datastore for AI / ML models to gather inputs and train models for each characteristic. This enables a robust data-driven approach to load balancing. The harmonizer framework 200 employs advanced AI / ML methodologies, including:

[0157] a) Time series forecasting: Utilizing algorithms like SARIMA and Holt-Winters to predict future active connections.

[0158] b) Clustering algorithms: Categorizing sessions based on their liveliness (long / short).

[0159] c) Energy metrics analysis: Implementing techniques such as eBPF for accurate energy consumption measurement.

[0160] d) Statistical Analysis: Establishing thresholds for healthy deployments through statistical methods.

[0161] e) Deep reinforcement learning: Dynamically adjusting profile weights based on real-time data.

[0162] Pub-Sub design approach: the profile builder 207 of the harmonizer framework 200 employs a publish-subscribe model, where harmonized inputs are published to the load balancer 400, allowing proxies to subscribe based on user-defined filters. This flexibility ensures that decision-making aligns with specific operational requirements.

[0163] The integration of the harmonizer framework 200 into load balancer 400 has yielded significant performance enhancements, for example:

[0164] a) Reduced setup time: A 26% decrease in CP setup establishment time.

[0165] b) Session rebalancing: A 15% reduction in the number of sessions that require rebalancing during auto-scaling or traffic surges, leading to minimal service disruptions.

[0166] c) Increased reliability: Achieving zero heartbeat failures in NF units due to effective session threshold management.

[0167] d) Energy efficiency: A 20% reduction in energy consumption, aligning with service demands.

[0168] Transformational impact on load balancing: Traditional load balancers primarily focus on ingress traffic management, service availability, and scalability. However, the harmonizer framework 200 transcends these limitations by introducing a multi-dimensional cost function matrix that incorporates heuristics and server capabilities for upstream selection. This approach positions the load balancer 400 to meet the stringent requirements of 5G Ultra-Reliable Low Latency Communications (URLLC), effectively reducing service time, minimizing energy consumption, and enhancing service reliability.

[0169] Strategic application in virtual Radio Access Network (vRAN): The harmonizer framework's implementation in vRAN is particularly advantageous for managing SCTP associations between Central Units (CUs) and Distributed Units (DUs). By integrating this harmonizer framework 200, end-to-end latency is significantly reduced, ensuring minimal service disruption. This capability provides a competitive edge over existing cloud-native load balancers (e.g., F5, Amazon Web Services (AWS), and Network Load Balancer (NLB)), by delivering superior performance and reliability tailored for 5G applications.

[0170] According to an embodiment, a method for managing Control Plane (CP) traffic in a wireless communication network, may comprise monitoring , by a load balancer , the CP traffic between the load balancer and one or more units associated with one or more Network Functions (NFs), detecting, by the load balancer , one or more failures in one or more CP sessions associated with one or more units while monitoring the CP traffic, wherein the one or more failures are attributed to load imbalance, determining, in response to detecting the one or more failures, by the load balancer , one or more harmonized cost functions and one or more profile weights associated with each unit to facilitate load balancing across the one or more units, and identifying, by the load balancer , one or more CP paths associated with the one or more units, to manage the CP traffic in the wireless communication network based on the one or more determined harmonized cost functions and one or more determined profile weights.

[0171] For example, the one or more harmonized cost functions for upstream data flow servicing may comprise an energy cost function, a reliability cost function, a rebalancing cost function, and a heuristic cost function.

[0172] For example, determining the one or more harmonized cost functions may comprise integrating one or more profiles and one or more external factors, utilizing predefined weighted metrics, to determine the one or more harmonized service cost functions. The one or more profiles may comprise an energy profile, a reliability profile, a rebalancing profile, and a heuristics profile, and each profile may comprise one or more cost attributes. The one or more external factors may comprise service information, time information, and location information.

[0173] For example, identifying the one or more CP paths for upstream data flow servicing based on the one or more determined harmonized cost functions may comprise determining one or more energy parameters associated with each Unit, wherein the one or more energy parameters comprise a value of energy level, a value of consumed energy, a number of User Plane (UP) sessions, and a Control Plane (CP) session, determining an energy cost function associated with each unit based on the one or more energy parameters to identify an optimal energy-efficient unit among a plurality of units, and identifying the one or more CP paths for upstream data flow servicing based on the identified optimal energy-efficient Unit.

[0174] For example, identifying the one or more CP paths for upstream data flow servicing based on the one or more determined harmonized cost functions may comprise determining one or more reliability parameters associated with each Unit, wherein the one or more reliability parameters may comprise at least one of a reliability weight, a session threshold, a current session count, and a value of Heart Beat (HB), determining a reliability cost function associated with each unit based on the one or more reliability parameters to identify an optimal safe-operating unit among a plurality of units, and identifying the one or more CP paths for upstream data flow servicing based on the identified optimal safe-operating Unit.

[0175] For example, identifying the one or more CP paths for upstream data flow servicing based on the one or more determined harmonized cost functions may comprise determining one or more rebalancing parameters associated with each Unit, wherein the one or more rebalancing parameters comprise at least one of Long Term (LT) traffic information and Short Term (ST) traffic information, determining a rebalancing cost function associated with each unit based on the one or more rebalancing parameters, distributing one or more sessions between a dedicated unit and one or more normal Units among a plurality of units based on the determined rebalancing cost function, and identifying the one or more CP paths for upstream data flow servicing based on the one or more distributed sessions.

[0176] For example, identifying the one or more CP paths for upstream data flow servicing based on the one or more determined harmonized cost functions may comprise determining one or more heuristic parameters associated with each Unit, wherein the one or more heuristic parameters comprise at least one of a value of Round Trip Time (RTT), a value of pending request, a value of forecasted RTT, a value of forecasted pending request, determining a heuristic cost function associated with each unit based on the one or more heuristic parameters to identify an optimal low-latency unit among a plurality of Units, and identifying the one or more CP paths for upstream data flow servicing based on the identified optimal low-latency Unit.

[0177] For example, determining the one or more profile weights may comprise: configuring, by the one or more determined harmonized cost functions, one or more weights assigned to each profile in real-time, using a Deep Reinforcement Learning, based on one or more external factors that influence each slice flow.

[0178] For example, the load balancer operates as a Service Communication Proxy (SCP) to manage a load distribution in the one or more CP sessions between at least one Radio Access Network (RAN) node and one or more core modules, or among core modules.

[0179] According to an embodiment, a load balancer for managing Control Plane (CP) traffic in a wireless communication network, may comprise a processor , operably connected to a memory and a communicator. The processor may be configured to monitor the CP traffic between the load balancer and one or more units associated with one or more Network Functions (NFs), detect one or more failures in one or more CP sessions associated with one or more units while monitoring the CP traffic, wherein the one or more failures are attributed to load imbalance, determine, in response to detecting the one or more failures, one or more harmonized cost functions and one or more profile weights associated with each unit to facilitate load balancing across the one or more units, and identify one or more CP paths associated with the one or more units, to manage the CP traffic in the wireless communication network based on the one or more determined harmonized cost functions and one or more determined profile weights.

[0180] For example, the one or more harmonized cost functions for upstream data flow servicing may comprise an energy cost function, a reliability cost function, a rebalancing cost function, and a heuristic cost function.

[0181] For example, to determine the one or more harmonized cost functions, the load balancer may be configured to integrate one or more profiles and one or more external factors, utilizing predefined weighted metrics, to determine the one or more harmonized service cost functions. The one or more profiles may comprise an energy profile, a reliability profile, a rebalancing profile, and a heuristics profile, and each profile may comprise one or more cost attributes. The one or more external factors may comprise service information, time information, and location information.

[0182] For example, to identify the one or more CP paths for upstream data flow servicing based on the one or more determined harmonized cost functions, the load balancer may be configured to determine one or more energy parameters associated with each Unit, wherein the one or more energy parameters comprise a value of energy level, a value of consumed energy, a number of User Plane (UP) sessions, and a Control Plane (CP) session, determine an energy cost function associated with each unit based on the one or more energy parameters to identify an optimal energy-efficient unit among a plurality of units, and identify the one or more CP paths for upstream data flow servicing based on the identified optimal energy-efficient Unit.

[0183] For example, to identify the one or more CP paths for upstream data flow servicing based on the one or more determined harmonized cost functions, the load balancer may be configured to determine one or more reliability parameters associated with each Unit, wherein the one or more reliability parameters comprise at least one of a reliability weight, a session threshold, a current session count, and a value of Heart Beat (HB), determine a reliability cost function associated with each unit based on the one or more reliability parameters to identify an optimal safe-operating unit among a plurality of units, and identify the one or more CP paths for upstream data flow servicing based on the identified optimal safe-operating Unit.

[0184] For example, to identify the one or more CP paths for upstream data flow servicing based on the one or more determined harmonized cost functions, the load balancer may be configured to determine one or more rebalancing parameters associated with each Unit, wherein the one or more rebalancing parameters comprise at least one of Long Term (LT) traffic information and Short Term (ST) traffic information, determine a rebalancing cost function associated with each unit based on the one or more rebalancing parameters, distribute one or more sessions between a dedicated unit and one or more normal Units among a plurality of units based on the determined rebalancing cost function, and identify the one or more CP paths for upstream data flow servicing based on the one or more distributed sessions.

[0185] For example, to identify the one or more CP paths for upstream data flow servicing based on the one or more determined harmonized cost functions, the load balancer may be configured to determine one or more heuristic parameters associated with each Unit, wherein the one or more heuristic parameters comprise at least one of a value of Round Trip Time (RTT), a value of pending request, a value of forecasted RTT, a value of forecasted pending request, determine a heuristic cost function associated with each unit based on the one or more heuristic parameters to identify an optimal low-latency unit among a plurality of Units, and identify the one or more CP paths for upstream data flow servicing based on the identified optimal low-latency Unit.

[0186] For example, to determine the one or more profile weights, may comprise configuring, by the one or more determined harmonized cost functions, one or more weights assigned to each profile in real-time, using a Deep Reinforcement Learning, based on one or more external factors that influence each slice flow.

[0187] For example, the load balancer operates as a Service Communication Proxy (SCP) to manage a load distribution in the one or more CP sessions between at least one Radio Access Network (RAN) node and one or more core modules, or among core modules.

[0188] According to an embodiment, a method for managing control plane (CP) traffic, performed by an electronic device for a load balancer , in a wireless communication network, may comprise monitoring the CP traffic between the load balancer and one or more network elements associated with one or more network functions (NFs), detecting one or more failures in one or more CP sessions associated with one or more network elements while monitoring the CP traffic, wherein the one or more failures are attributed to load imbalance, determining , in response to detecting the one or more failures, one or more cost functions and one or more profile weights associated with each network element to facilitate load balancing across the one or more network elements, and identifying one or more CP paths associated with the one or more network elements, to manage the CP traffic in the wireless communication network based on the one or more determined cost functions and one or more determined profile weights.

[0189] For example, the one or more cost functions for upstream data flow servicing may comprise an energy cost function, a reliability cost function, a rebalancing cost function, and a heuristic cost function.

[0190] For example, determining the one or more cost functions may comprise integrating one or more profiles and one or more external factors, utilizing predefined weighted metrics, to determine the one or more service cost functions. The one or more profiles may comprise an energy profile, a reliability profile, a rebalancing profile, and a heuristics profile, and each profile may comprise one or more cost attributes. The one or more external factors may comprise service information, time information, and location information.

[0191] For example, identifying the one or more CP paths for upstream data flow servicing based on the one or more determined cost functions may comprise determining one or more energy parameters associated with each network element, wherein the one or more energy parameters comprise a value of energy level, a value of consumed energy, a number of user Plane (UP) sessions, and a control Plane (CP) session, determining an energy cost function associated with each network element based on the one or more energy parameters to identify an optimal energy-efficient network element among a plurality of network elements, and identifying the one or more CP paths for upstream data flow servicing based on the identified optimal energy-efficient network element.

[0192] For example, identifying the one or more CP paths for upstream data flow servicing based on the one or more determined cost functions may comprise determining one or more reliability parameters associated with each network element, wherein the one or more reliability parameters may comprise at least one of a reliability weight, a session threshold, a current session count, and a value of heart beat (HB), determining a reliability cost function associated with each network element based on the one or more reliability parameters to identify an optimal safe-operating network element among a plurality of network elements, and identifying the one or more CP paths for upstream data flow servicing based on the identified optimal safe-operating network element.

[0193] For example, identifying the one or more CP paths for upstream data flow servicing based on the one or more determined cost functions may comprise determining one or more rebalancing parameters associated with each network element, wherein the one or more rebalancing parameters comprise at least one of long term (LT) traffic information and short term (ST) traffic information, determining a rebalancing cost function associated with each network element based on the one or more rebalancing parameters, distributing one or more sessions between a dedicated network element and one or more normal elements among a plurality of network elements based on the determined rebalancing cost function, and identifying the one or more CP paths for upstream data flow servicing based on the one or more distributed sessions.

[0194] For example, identifying the one or more CP paths for upstream data flow servicing based on the one or more determined cost functions may comprise determining one or more heuristic parameters associated with each network element, wherein the one or more heuristic parameters comprise at least one of a value of round trip time (RTT), a value of pending request, a value of forecasted RTT, a value of forecasted pending request, determining a heuristic cost function associated with each network element based on the one or more heuristic parameters to identify an optimal low-latency network element among a plurality of network elements, and identifying the one or more CP paths for upstream data flow servicing based on the identified optimal low-latency network element.

[0195] For example, determining the one or more profile weights may comprise configuring, by the one or more determined cost functions, one or more weights assigned to each profile in real-time, using a Deep Reinforcement Learning, based on one or more external factors that influence each slice flow.

[0196] For example, the load balancer may operate as a service communication proxy (SCP) to manage a load distribution in the one or more CP sessions between at least one radio access network (RAN) node and one or more core modules, or among core modules.

[0197] According to an embodiment, an electronic device for a load balancer for managing control plane (CP) traffic in a wireless communication network, may comprise communication circuitry, memory comprising one or more storage media, storing instructions, and at least one processor comprising processing circuitry. The instructions, when executed by the at least one processor, may cause the electronic device to monitor the CP traffic between the load balancer and one or more elements associated with one or more network functions (NFs), detect one or more failures in one or more CP sessions associated with one or more elements while monitoring the CP traffic, wherein the one or more failures are attributed to load imbalance, determine, in response to detecting the one or more failures, one or more cost functions and one or more profile weights associated with each element to facilitate load balancing across the one or more elements, and identify one or more CP paths associated with the one or more elements, to manage the CP traffic in the wireless communication network based on the one or more determined cost functions and one or more determined profile weights.

[0198] For example, the one or more cost functions for upstream data flow servicing may comprise an energy cost function, a reliability cost function, a rebalancing cost function, and a heuristic cost function.

[0199] For example, the instructions, when executed by the at least one processor, may cause the electronic device to integrate one or more profiles and one or more external factors, utilizing predefined weighted metrics, to determine the one or more service cost functions. The one or more profiles comprise an energy profile, a reliability profile, a rebalancing profile, and a heuristics profile, and each profile may comprise one or more cost attributes. The one or more external factors comprise service information, time information, and location information.

[0200] For example, the instructions, when executed by the at least one processor, may cause the electronic device to determine one or more energy parameters associated with each element, wherein the one or more energy parameters comprise a value of energy level, a value of consumed energy, a number of User Plane (UP) sessions, and a Control Plane (CP) session, determine an energy cost function associated with each element based on the one or more energy parameters to identify an optimal energy-efficient element among a plurality of elements, and identify the one or more CP paths for upstream data flow servicing based on the identified optimal energy-efficient element.

[0201] For example, the instructions, when executed by the at least one processor, may cause the electronic device to determine one or more reliability parameters associated with each element, wherein the one or more reliability parameters comprise at least one of a reliability weight, a session threshold, a current session count, and a value of Heart Beat (HB), determine a reliability cost function associated with each element based on the one or more reliability parameters to identify an optimal safe-operating element among a plurality of elements, and identify the one or more CP paths for upstream data flow servicing based on the identified optimal safe-operating element.

[0202] According to an embodiment, A non-transitory computer storage media may store one or more programs. The one or more programs may include instructions which, when executed by at least one processor of an electronic device for a load balancer, cause the electronic device to monitor the CP traffic between the load balancer and one or more elements associated with one or more network functions (NFs), detect one or more failures in one or more CP sessions associated with one or more elements while monitoring the CP traffic, wherein the one or more failures are attributed to load imbalance, determine, in response to detecting the one or more failures, one or more cost functions and one or more profile weights associated with each element to facilitate load balancing across the one or more elements, and identify one or more CP paths associated with the one or more elements, to manage the CP traffic in the wireless communication network based on the one or more determined cost functions and one or more determined profile weights.

[0203] The various actions, acts, blocks, steps, operations, or the like in the flow diagrams may be performed in the order presented, in a different order, or simultaneously. Further, in some embodiments, some of the actions, acts, blocks, steps, or the like may be omitted, added, modified, skipped, or the like without departing from the scope of the disclosure.

[0204] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one ordinary skilled in the art to which this disclosure belongs. The system, methods, and examples provided herein are illustrative only and not intended to be limiting.

[0205] While specific language has been used to describe the present subject matter, any limitations arising on account thereto, are not intended. As would be apparent to a person in the art, various working modifications may be made to the method to implement the inventive concept as taught herein. The drawings and the forgoing description give examples of embodiments. Those skilled in the art will appreciate that one or more of the described elements may well be combined into a single functional element. Alternatively, certain elements may be split into multiple functional elements. Elements from one embodiment may be added to another embodiment.

[0206] The embodiments disclosed herein can be implemented using at least one hardware device and performing network management functions to control the elements.

[0207] The foregoing description of the specific embodiments will so fully reveal the general nature of the embodiments herein that others can, by applying current knowledge, readily modify and / or adapt for various applications such specific embodiments without departing from the generic concept, and, therefore, such adaptations and modifications should and are intended to be comprehended within the meaning and range of equivalents of the disclosed embodiments. It is to be understood that the phraseology or terminology employed herein is for the purpose of description and not of limitation. Therefore, while the embodiments herein have been described in terms of preferred embodiments, those skilled in the art will recognize that the embodiments herein can be practiced with modification within the scope of the embodiments as described herein.

[0208] For one or more embodiments, at least one of the components set forth in one or more of the preceding figures may be configured to perform one or more operations, techniques, processes, and / or methods as set forth herein. For example, a processor (e.g., baseband processor) as described herein in connection with one or more of the preceding figures may be configured to operate in accordance with one or more of the examples set forth herein. For another example, circuitry associated with a UE, base station, network element, etc. as described above in connection with one or more of the preceding figures may be configured to operate in accordance with one or more of the examples set forth herein.

[0209] Any of the above described embodiments may be combined with any other embodiment (or combination of embodiments), unless explicitly stated otherwise. The foregoing description of one or more implementations provides illustration and description, but is not intended to be exhaustive or to limit the scope of embodiments to the precise form disclosed. Modifications and variations are possible in light of the above teachings or may be acquired from practice of various embodiments.

[0210] The methods according to various embodiments described in the claims and / or the specification of the disclosure may be implemented in hardware, software, or a combination of hardware and software.

[0211] When implemented by software, a computer-readable storage medium storing one or more programs (software modules) may be provided. One or more programs stored in such a computer-readable storage medium (e.g., non-transitory storage medium) are configured for execution by one or more processors in an electronic device. The one or more programs include instructions that cause the electronic device to execute the methods according to embodiments described in the claims or specification of the disclosure.

[0212] Such a program (e.g., software module, software) may be stored in a random-access memory, a non-volatile memory including a flash memory, a read only memory (ROM), an electrically erasable programmable read only memory (EEPROM), a magnetic disc storage device, a compact disc-ROM (CD-ROM), digital versatile discs (DVDs), other types of optical storage devices, or magnetic cassettes. Alternatively, it may be stored in a memory configured with a combination of some or all of the above. In addition, respective constituent memories may be provided in a multiple number.

[0213] Further, the program may be stored in an attachable storage device that can be accessed via a communication network, such as e.g., Internet, Intranet, local area network (LAN), wide area network (WAN), or storage area network (SAN), or a communication network configured with a combination thereof. Such a storage device may access an apparatus performing an embodiment of the disclosure through an external port. Further, a separate storage device on the communication network may be accessed to an apparatus performing an embodiment of the disclosure.

[0214] In the above-described specific embodiments of the disclosure, a component included therein may be expressed in a singular or plural form according to a proposed specific embodiment. However, such a singular or plural expression may be selected appropriately for the presented context for the convenience of description, and the disclosure is not limited to the singular form or the plural elements. Therefore, either an element expressed in the plural form may be formed of a singular element, or an element expressed in the singular form may be formed of plural elements.

[0215] Meanwhile, specific embodiments have been described in the detailed description of the disclosure, but it goes without saying that various modifications are possible without departing from the scope of the disclosure.

Claims

1.A method (1100) for managing control plane (CP) traffic, performed by an electronic device for a load balancer (400), in a wireless communication network, the method (1100) comprising:monitoring (1101) the CP traffic between the load balancer (400) and one or more network elements associated with one or more network functions (NFs);detecting (1102) one or more failures in one or more CP sessions associated with one or more network elements while monitoring the CP traffic, wherein the one or more failures are attributed to load imbalance;determining (1103), in response to detecting the one or more failures, one or more cost functions and one or more profile weights associated with each network element to facilitate load balancing across the one or more network elements; andidentifying (1104) one or more CP paths associated with the one or more network elements, to manage the CP traffic in the wireless communication network based on the one or more determined cost functions and one or more determined profile weights.2.The method (1100) as claimed in claim 1, wherein the one or more cost functions for upstream data flow servicing comprises an energy cost function, a reliability cost function, a rebalancing cost function, and a heuristic cost function.3.The method (1100) as claimed in claim 2, wherein determining the one or more cost functions comprises:integrating one or more profiles and one or more external factors, utilizing predefined weighted metrics, to determine the one or more service cost functions,wherein the one or more profiles comprise an energy profile, a reliability profile, a rebalancing profile, and a heuristics profile, and each profile comprises one or more cost attributes, andwherein the one or more external factors comprise service information, time information, and location information.4.The method (1100) as claimed in claim 1, wherein identifying the one or more CP paths for upstream data flow servicing based on the one or more determined cost functions comprises:determining one or more energy parameters associated with each network element, wherein the one or more energy parameters comprise a value of energy level, a value of consumed energy, a number of user Plane (UP) sessions, and a control Plane (CP) session;determining an energy cost function associated with each network element based on the one or more energy parameters to identify an optimal energy-efficient network element among a plurality of network elements; andidentifying the one or more CP paths for upstream data flow servicing based on the identified optimal energy-efficient network element.5.The method (1100) as claimed in claim 1, wherein identifying the one or more CP paths for upstream data flow servicing based on the one or more determined cost functions comprises:determining one or more reliability parameters associated with each network element, wherein the one or more reliability parameters comprises at least one of a reliability weight, a session threshold, a current session count, and a value of heart beat (HB);determining a reliability cost function associated with each network element based on the one or more reliability parameters to identify an optimal safe-operating network element among a plurality of network elements; andidentifying the one or more CP paths for upstream data flow servicing based on the identified optimal safe-operating network element.6.The method (1100) as claimed in claim 1, wherein identifying the one or more CP paths for upstream data flow servicing based on the one or more determined cost functions comprises:determining one or more rebalancing parameters associated with each network element, wherein the one or more rebalancing parameters comprise at least one of long term (LT) traffic information and short term (ST) traffic information;determining a rebalancing cost function associated with each network element based on the one or more rebalancing parameters;distributing one or more sessions between a dedicated network element and one or more normal elements among a plurality of network elements based on the determined rebalancing cost function; andidentifying the one or more CP paths for upstream data flow servicing based on the one or more distributed sessions.7.The method (1100) as claimed in claim 1, wherein identifying the one or more CP paths for upstream data flow servicing based on the one or more determined cost functions comprises:determining one or more heuristic parameters associated with each network element, wherein the one or more heuristic parameters comprise at least one of a value of round trip time (RTT), a value of pending request, a value of forecasted RTT, a value of forecasted pending request;determining a heuristic cost function associated with each network element based on the one or more heuristic parameters to identify an optimal low-latency network element among a plurality of network elements; andidentifying the one or more CP paths for upstream data flow servicing based on the identified optimal low-latency network element.8.The method (1100) as claimed in claim 1, wherein determining the one or more profile weights comprises:configuring, by the one or more determined cost functions, one or more weights assigned to each profile in real-time, using a Deep Reinforcement Learning, based on one or more external factors that influence each slice flow.9.The method (1100) as claimed in claim 1, wherein the load balancer (400) operates as a service communication proxy (SCP) to manage a load distribution in the one or more CP sessions between at least one radio access network (RAN) node and one or more core modules, or among core modules.10.An electronic device for a load balancer (400) for managing control plane (CP) traffic in a wireless communication network, the electronic device comprising:communication circuitry;memory comprising one or more storage media, storing instructions; andat least one processor comprising processing circuitry,wherein the instructions, when executed by the at least one processor, cause the electronic device to:monitor the CP traffic between the load balancer and one or more elements associated with one or more network functions (NFs);detect one or more failures in one or more CP sessions associated with one or more elements while monitoring the CP traffic, wherein the one or more failures are attributed to load imbalance;determine, in response to detecting the one or more failures, one or more cost functions and one or more profile weights associated with each element to facilitate load balancing across the one or more elements; andidentify one or more CP paths associated with the one or more elements, to manage the CP traffic in the wireless communication network based on the one or more determined cost functions and one or more determined profile weights.11.The electronic device of claim 10, wherein the one or more cost functions for upstream data flow servicing comprises an energy cost function, a reliability cost function, a rebalancing cost function, and a heuristic cost function.12.The electronic device of claim 11, wherein the instructions, when executed by the at least one processor, cause the electronic device to:integrate one or more profiles and one or more external factors, utilizing predefined weighted metrics, to determine the one or more service cost functions,wherein the one or more profiles comprise an energy profile, a reliability profile, a rebalancing profile, and a heuristics profile, and each profile comprises one or more cost attributes, andwherein the one or more external factors comprise service information, time information, and location information.13.The electronic device as claimed in claim 10, wherein the instructions, when executed by the at least one processor, cause the electronic device to:determine one or more energy parameters associated with each element, wherein the one or more energy parameters comprise a value of energy level, a value of consumed energy, a number of User Plane (UP) sessions, and a Control Plane (CP) session;determine an energy cost function associated with each element based on the one or more energy parameters to identify an optimal energy-efficient element among a plurality of elements; andidentify the one or more CP paths for upstream data flow servicing based on the identified optimal energy-efficient element.14.The electronic device as claimed in claim 10, wherein the instructions, when executed by the at least one processor, cause the electronic device to:determine one or more reliability parameters associated with each element, wherein the one or more reliability parameters comprise at least one of a reliability weight, a session threshold, a current session count, and a value of Heart Beat (HB);determine a reliability cost function associated with each element based on the one or more reliability parameters to identify an optimal safe-operating element among a plurality of elements; andidentify the one or more CP paths for upstream data flow servicing based on the identified optimal safe-operating element.15.A non-transitory computer storage media storing one or more programs, wherein the one or more programs include instructions which, when executed by at least one processor of an electronic device for a load balancer (400), cause the electronic device to:monitor the CP traffic between the load balancer and one or more elements associated with one or more network functions (NFs);detect one or more failures in one or more CP sessions associated with one or more elements while monitoring the CP traffic, wherein the one or more failures are attributed to load imbalance;determine, in response to detecting the one or more failures, one or more cost functions and one or more profile weights associated with each element to facilitate load balancing across the one or more elements; andidentify one or more CP paths associated with the one or more elements, to manage the CP traffic in the wireless communication network based on the one or more determined cost functions and one or more determined profile weights.

Images