Method and system for managing multi-hop relay chain in a network
The AI-driven multi-hop relay management system addresses scalability and adaptability issues in 5G sidelink networks by using RL agents and FL for dynamic relay selection, optimizing throughput and latency, and ensuring secure, transparent operations.
Patent Information
- Application Number
- PCT/IN2026/050791
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2025-05-08
- Filing Date
- 2026-05-08
- Publication Date
- 2026-11-12
AI Technical Summary
Conventional sidelink relay systems in 5G NR networks face limitations in scalability, adaptability, and efficiency due to static configurations and lack of real-time environmental awareness, leading to issues like overlapping transmissions, increased interference, and poor flow control, especially in dynamic and heterogeneous environments.
An AI-driven multi-hop relay management system using Reinforcement Learning (RL) agents for dynamic relay selection and Federated Learning (FL) for collaborative model training, integrated with Explainable AI (XAI) for transparency, optimizing throughput, latency, and route stability across multiple hops.
The system enhances network adaptability, reduces latency, improves throughput, and ensures scalable and secure relay operations by dynamically selecting optimal multi-hop paths based on real-time network parameters, while maintaining privacy and transparency.
Smart Images

Figure IN2026050791_12112026_PF_FP_ABST
Abstract
Description
METHOD AND SYSTEM FOR MANAGING MULTI-HOP RELAY CHAIN IN A NETWORK RESERVATION OF RIGHTS
[0001] A portion of the disclosure of this patent document contains material, which is subject to intellectual property rights such as, but are not limited to, copyright, design, trademark, Integrated Circuit (IC) layout design, and / or trade dress protection, belonging to Jio Platforms Limited (JPL) or its affiliates (hereinafter referred as owner). The owner has no objection to the facsimile reproduction by anyone of the patent document or the patent disclosure, as it appears in the Patent and Trademark Office patent files or records, but otherwise reserves all rights whatsoever. All rights to such intellectual property are fully reserved by the owner.TECHNICAL FIELD
[0002] The present disclosure relates to a field of telecommunications network. In particular, the present disclosure relates to a method and a system for managing multi-hop relay chain in a network.DEFINITION
[0003] As used in the present disclosure, the following terms are generally intended to have the meaning as set forth below, except to the extent that the context in which they are used to indicate otherwise.
[0004] The term “Remote User Equipment (UE)” as used herein in the specification refers to a device such as a smartphone, Internet of Things (loT) sensor, or vehicle that cannot establish a direct connection to a gNodeB (gNB) due to physical or environmental constraints, such as being out of the network’s coverage area, and at the cell edge.
[0005] The term “Intermediate relay UE” as used herein in the specification refers to a UE that serves as a middle node in a multi-hop sidelink relay chain. TheIntermediate relay UE receives data from a downstream node such as a remote UE or another intermediate relay UE and forwards it to an upstream node such as another intermediate relay UE or an anchor relay UE that is in direct coverage of the gNB.
[0006] The term “Reinforcement Learning (RL)” as used herein in the specification refers to a machine learning model where an agent learns optimal behaviour through trial-and-error interactions with an environment. The RL agent takes actions, observes the outcomes in terms of states and rewards, and adjusts its policy to maximize a long-term reward.
[0007] The term “Federated Learning (FL)” as used herein in the specification refers to a distributed machine learning approach where multiple UEs collaboratively train a shared global model without exchanging the raw data. Instead, each UE trains a local model using its own data, and only the model updates such as weights or gradients are shared with a central coordinator (e.g., an edge server or a gNB-based FL Coordinator).
[0008] The term “PC5 protocol stack” as used herein in the specification refers to a set of communication protocols used for sidelink communication between the UEs in 5G New Radio (NR). The PC5 protocol stack denotes the direct Device-to-Device (D2D) interface used for sidelink communication, which allows the UEs to communicate with each other without necessarily involving the network infrastructure (e.g., gNodeB or eNodeB).
[0009] The term “Uu protocol stack” as used herein in the specification refers to a set of protocols used for communication between the UE and the gNB in a 5G network, or between the UE and the eNodeB in an LTE network. The Uu protocol stack protocol stack is critical for enabling data transfer, control signalling, and mobility management over the wireless link, ensuring reliable and secure communication in the 5G and the 5G networks.
[0010] The term “gNB-Central Unit (CU)” as used herein in the specification refers to a centralized component of the gNB, which is the 5G base station responsible for providing wireless connectivity to the UEs. The gNB-CU hosts the higher-layer protocols of the 5G protocol stack, specifically a Radio Resource Control (RRC), a Service Data Adaptation Protocol (SDAP), and a Packet Data Convergence Protocol (PDCP) layers.
[0011] The term “gNB-Distributed Unit (DU)” as used herein in the specification refers to a distributed part of the gNB responsible for handling lower-layer protocol functions in the 5G NR protocol stack. The gNB-DU manages the Radio Link Control (RLC), Medium Access Control (MAC), and Physical (PHY) layers. The gNB-DU is typically deployed closer to the radio edge, handling real-time radio access functions such as scheduling, beamforming, and physical layer processing for UEs (including relay UEs and remote UEs in sidelink scenarios).
[0012] The term “Explainable Artificial Intelligence (XAI)” as used herein in the specification refers to a set of methods, techniques, and processes in Al that aim to make the decisions, actions, or predictions of Al systems understandable and interpretable to humans. The XAI encompasses techniques that enable humans to comprehend why an Al system made a specific decision or prediction.
[0013] The term ‘SidelinkUEInformationNR message’ as used herein in the specification refers to a sidelink-related Radio Resource Control (RRC) message transmitted by a relay UE toward a network-side node to report information associated with sidelink operation, relay operation, or a remote UE connection request. In the present disclosure, the SidelinkUEInformationNR message may be used by a relay UE to indicate that a remote UE or an intermediate relay UE seeks access to the network through a relay path.
[0014] The term ‘RRCSetupRequesf as used herein in the specification refers to a Radio Resource Control connection establishment request message transmitted by a UE to initiate establishment of an RRC connection toward the network, either directly or through one or more relay UEs.
[0015] The term ‘RRCSetup’ as used herein in the specification refers to a Radio Resource Control message transmitted in response to a RRCSetupRequest for establishing an RRC connection for a UE.
[0016] The term ‘RRCSetupComplete’ as used herein in the specification refers to a Radio Resource Control message transmitted by a UE after successful application of an RRCSetup message and may include a Non-Access Stratum (NAS) message associated with a core-network procedure.
[0017] The term ‘ SecurityModeCommand’ as used herein in the specification refers to an access-stratum security-related Radio Resource Control message transmitted by a network-side node to activate security procedures for a UE.
[0018] The term ‘SecurityModeComplete’ as used herein in the specification refers to an access-stratum security-related Radio Resource Control message transmitted by a UE after successful application of a SecurityModeCommand.
[0019] The term ‘RRCReconfiguration’ as used herein in the specification refers to a Radio Resource Control message used to configure, modify, or update one or more radio bearers, relay parameters, logical channels, or other communication parameters associated with a UE or relay chain.
[0020] The term ‘RRCReconfigurationComplete’ as used herein in the specification refers to a Radio Resource Control message transmitted after successful application of a RRCReconfiguration message.
[0021] These definitions are in addition to those expressed in the art.BACKGROUND
[0022] The following description of related art is intended to provide background information pertaining to the field of the disclosure. This section may include certain aspects of the art that may be related to various features of the present disclosure. However, it should be appreciated that this section be used only toenhance the understanding of the reader with respect to the present disclosure, and not as admissions of prior art.
[0023] The evolution of mobile communication technologies has seen a rapid transition from voice-centric services to high-throughput, low-latency applications that support a vast array of use cases, including autonomous driving, mission-critical communications, and enhanced mobile broadband. With the advent of Fifth Generation (5G) New Radio (NR), sidelink communication has emerged as a critical enabler for direct Device-to-Device (D2D) connectivity, particularly in scenarios lacking conventional network infrastructure, such as vehicular ad hoc networks and public safety operations.
[0024] Conventional sidelink communication frameworks in 5G NR rely heavily on pre-configured relay selection and static network topology, which are often suboptimal in dynamic and heterogeneous environments. The introduction of multihop relay mechanisms aims to extend communication range and enhance network robustness. However, existing relay management schemes suffer from limitations in scalability, adaptability, and efficiency. The shortcomings stem from the lack of real-time environmental awareness and the inability to dynamically optimize relay selection based on varying user requirements, channel conditions, and mobility patterns.
[0025] The need for multi-hop relaying where data is forwarded through multiple relay UEs to reach the gNB has been recognized, but conventional implementations are limited in scope, focusing on nominal multi-hop support with static configurations. The conventional solutions do not adequately address the dynamic nature of 5G environments, where UEs may move rapidly (such as vehicles on a highway), experience varying link qualities, or face sudden changes in network conditions. Additionally, existing relay selection mechanisms lack the ability to optimize end-to-end resource coordination across multiple hops, leading to issues like overlapping transmissions, increased interference, and poor flow control. Further, there is also a gap in ensuring scalability and privacy in relay systems, aslarge-scale deployments involving numerous UEs require efficient learning and adaptation without compromising user data security.
[0026] There is, therefore, a need in the art to provide a method and a system that can mitigate the disadvantages of the prior art.SUMMARY OF THE DISCLOSURE
[0027] In an embodiment, a method for managing multi-hop relay chain in a network is described. The method includes receiving an indication that a remote User Equipment (UE) requests access to the network through one or more relay UEs. Further, the method further include determining a multi-hop relay chain including at least one relay UE between the remote UE and the network node based on the received indication. The method includes generating a multi-hop configuration container associated with the multi-hop relay chain. The multi-hop configuration container includes at least one of multi-hop relay chain identifier, remote UE information, hop-wise relay configuration information, and bearer configuration for signaling and data communication associated with the remote UE. Further, the method further include transmitting a Radio Resource Control (RRC) reconfiguration message including the multi-hop configuration container to the remote UE and the one or more relay UEs to establish Signaling Radio Bearer (SRB) across the multi-hop relay chain. Further, the method include receiving an RRC setup complete message including a Non-Access Stratum (NAS) message from the remote UE through the multi-hop relay chain. The method includes transmitting a security control message for the remote UE through the multi-hop relay chain. Further, the method include establishing one or more data radio bearers for the remote UE over the multi-hop relay chain.
[0028] In an embodiment, wherein receiving the indication, the method includes receiving at least one of a RRC setup request, an initial access request message, and a relay request information associated with the remote UE through the one or more relay UEs.
[0029] In another embodiment, wherein determining the multi-hop relay chain, the method includes applying a machine learning model to at least one of signal quality, relay load, throughput, latency, mobility condition, coverage condition, and quality -of-service requirement associated with the one or more relay UEs to optimize the determination of the multi-hop relay chain.
[0030] In another embodiment, wherein determining the multi-hop relay chain, the method includes determining topology context information identifying an ordered sequence of the remote UE and the at least one relay UE. The method includes assigning a multi-hop relay chain identifier to the multi-hop relay chain.
[0031] In another embodiment, wherein transmitting the RRC reconfiguration message the method includes applying each of the hop-wise relay configuration information from the multi-hop configuration container to the corresponding relay UEs based on the topology context information of the multi-hop relay chain.
[0032] In another embodiment, the method includes transmitting the machine learning model to the one or more relay UEs for local update. Further, the method includes receiving model update information from the one or more relay UEs. The method includes aggregating the model update information to generate an updated machine learning model. Further, the method includes using the updated machine learning model for subsequent determination of the multi-hop relay chain.
[0033] In another embodiment, the method includes generating relay chain selection information associated with determination of the multi-hop relay chain. The relay chain selection information includes at least one of an identity of at least one selected relay UE, an ordered position of the at least one selected relay UE in the multi-hop relay chain, a chain identifier, or one or more relay metrics used for determination of the multi-hop relay chain.
[0034] In another embodiment, the one or more data radio bearers provide controlplane signaling and user-plane communication between the remote UE and the network node.
[0035] In another exemplary embodiment, a system for managing multi-hop relay chain in a network is described. The system includes a network node configured to receive an indication that a remote User Equipment (UE) requests access to the network through one or more relay UEs. The network node is configured to determine a multi-hop relay chain including at least one relay UE between the remote UE and the network node based on the received indication. Further, the network node is configured to generate a multi-hop configuration container associated with the multi-hop relay chain. The multi-hop configuration container includes at least one of multi-hop relay chain identifier, remote UE information, hop-wise relay configuration information, and bearer configuration for signaling and data communication associated with the remote UE. The network node is configured to transmit a Radio Resource Control (RRC) reconfiguration message including the multi-hop configuration container to the remote UE and the one or more relay UEs to establish Signaling Radio Bearer (SRB) across the multi-hop relay chain. Further, the network node is configured to receive an RRC setup complete message comprising a Non-Access Stratum (NAS) message from the remote UE through the multi-hop relay chain. The network node is configured to transmit a security control message for the remote UE through the multi-hop relay chain. Further, the network node is configured to establish one or more data radio bearers for the remote UE over the multi-hop relay chain.
[0036] In yet another embodiment, a computer program product including a non-transitory computer-readable medium including instructions that, when executed by one or more processors, cause the one or more processors to execute a method for managing multi-hop relay chain in a network is disclosed. The method includes receiving an indication that a remote User Equipment (UE) requests access to the network through one or more relay UEs. Further, the method further include determining a multi-hop relay chain including at least one relay UE between the remote UE and the network node based on the received indication. The method includes generating a multi-hop configuration container associated with the multihop relay chain. The multi-hop configuration container includes at least one ofmulti-hop relay chain identifier, remote UE information, hop-wise relay configuration information, and bearer configuration for signaling and data communication associated with the remote UE. Further, the method further include transmitting a Radio Resource Control (RRC) reconfiguration message including the multi-hop configuration container to the remote UE and the one or more relay UEs to establish Signaling Radio Bearer (SRB) across the multi-hop relay chain. Further, the method include receiving an RRC setup complete message including a Non-Access Stratum (NAS) message from the remote UE through the multi-hop relay chain. The method includes transmitting a security control message for the remote UE through the multi-hop relay chain. Further, the method include establishing one or more data radio bearers for the remote UE over the multi-hop relay chain.OBJECTIVES OF THE PRESENT DISCLOSURE
[0037] Some of the objectives of the present disclosure, which at least one embodiment herein satisfies, are as follows:
[0038] An objective of the present disclosure is to provide a method and a system for intelligent multi-hop relay management in Fifth Generation (5G) New Radio (NR) sidelink communication networks using Artificial Intelligence (Al)-driven decision-making.
[0039] Another objective of the present disclosure is to provide a method and a system that optimize relay selection dynamically based on real-time network parameters such as channel quality, node mobility, signal strength, and user-specific QoS requirements.
[0040] Another objective of the present disclosure is to provide a method and a system that reduce latency and improve throughput in sidelink networks by intelligently selecting the most efficient and stable multi-hop communication paths.
[0041] Another objective of the present disclosure is to provide a method and a system that provide a framework for continuous learning and performance improvement by integrating feedback loops into the relay management algorithm.
[0042] Yet another objective of the present disclosure is to provide a method and a system that enable proactive and autonomous decision-making in relay selection using predictive analytics, reducing the need for centralized control or manual intervention.
[0043] Other objectives and advantages of the present disclosure will be more apparent from the following description, which is not intended to limit the scope of the present disclosure.BRIEF DESCRIPTION OF THE DRAWINGS
[0044] The accompanying drawings, which are incorporated herein, and constitute a part of this disclosure, illustrate exemplary embodiments of the disclosed methods and systems in which like reference numerals refer to the same parts throughout the different drawings. Components in the drawings are not necessarily to scale, emphasis instead being placed upon clearly illustrating the principles of the present disclosure. Some drawings may indicate the components using block diagrams and may not represent the internal circuitry of each component. It will be appreciated by those skilled in the art that disclosure of such drawings includes the disclosure of electrical components, electronic components or circuitry commonly used to implement such components.
[0045] FIG. 1 illustrates an exemplary network architecture for managing sidelink relay in a network, in accordance with an embodiment of the present disclosure.
[0046] FIG. 2 illustrates an exemplary block diagram of a system for managing multi-hop relay chain in a network, in accordance with an embodiment of the present disclosure.
[0047] FIG. 3 illustrates an exemplary system architecture for managing multi-hop relay chain in a network, in accordance with an embodiment of the present disclosure.
[0048] FIG. 4 illustrates an exemplary process flow managing multi-hop relay chain in a network, in accordance with an embodiment of the present disclosure.
[0049] FIG. 5 illustrates an exemplary process flow for managing multi-hop relay chain in a network, in accordance with an embodiment of the present disclosure.
[0050] FIG. 6 illustrates an exemplary process flow for managing multi-hop relay chain in a network, in accordance with an embodiment of the present disclosure.
[0051] FIG. 7 illustrates an exemplary process flow for managing multi-hop relay chain in a network, in accordance with an embodiment of the present disclosure.
[0052] FIG. 8 illustrates an exemplary computer system in which or with which the embodiments of the present disclosure may be implemented.
[0053] The foregoing shall be more apparent from the following detailed description of the disclosure.LIST OF REFERENCE NUMERALS100 - Network architecture102 -User(s)104 -User Equipments (UEs)106 - Network108 - System200 - Block diagram202 - Processor(s)- Memory-Interface(s)- Network node- Database- System architecture-UE side- Radio Access Network (RAN)- Remote UE- Intermediate relay UE- Anchor relay UE- Federated Learning (FL) coordinator- gNodeB (gNB)-Central Unit (CU)- gNB -Distributed Unit (DU)A, 318B, and 318C - Reinforcement Learning (RL) agent + FL client A, 320B, and 320C - PC5 Protocol stack, 324, and 326 - Uu Protocol stack- Flow Diagram- Flow Diagram- Flow Diagram- Method800 - A computer system810 - External Storage Device820 - Bus830 - Main Memory840 - Read Only Memory850 - Mass Storage Device860 - Communication Port870 - ProcessorDETAILED DESCRIPTION
[0054] In the following description, for the purposes of explanation, various specific details are set forth in order to provide a thorough understanding of embodiments of the present disclosure. It will be apparent, however, that embodiments of the present disclosure may be practiced without these specific details. Several features described hereafter can each be used independently of one another or with any combination of other features. An individual feature may not address any of the problems discussed above or might address only some of the problems discussed above. Some of the problems discussed above might not be fully addressed by any of the features described herein. Example embodiments of the present disclosure are described below, as illustrated in various drawings in which like reference numerals refer to the same parts throughout the different drawings.
[0055] The ensuing description provides exemplary embodiments only, and is not intended to limit the scope, applicability, or configuration of the disclosure. Rather, the ensuing description of the exemplary embodiments will provide those skilled in the art with an enabling description for implementing an exemplary embodiment.It should be understood that various changes may be made in the function and arrangement of elements without departing from the spirit and scope of the disclosure as set forth.
[0056] Specific details are given in the following description to provide a thorough understanding of the embodiments. However, it will be understood by one of ordinary skill in the art that the embodiments may be practiced without these specific details. For example, circuits, systems, networks, processes, and other components may be shown as components in block diagram form in order not to obscure the embodiments in unnecessary detail. In other instances, well-known circuits, processes, algorithms, structures, and techniques may be shown without unnecessary detail in order to avoid obscuring the embodiments.
[0057] Also, it is noted that individual embodiment may be described as a process that is depicted as a flowchart, a flow diagram, a data flow diagram, a structure diagram, or a block diagram. Although a flowchart may describe the operations as a sequential process, many of the operations can be performed in parallel or concurrently. In addition, the order of the operations may be re-arranged. A process is terminated when its operations are completed but could have additional steps not included in a figure. A process may correspond to a method, a function, a procedure, a subroutine, a subprogram, etc. When a process corresponds to a function, its termination can correspond to a return of the function to the calling function or the main function.
[0058] The word “exemplary” and / or “demonstrative” is used herein to mean serving as an example, instance, or illustration. For the avoidance of doubt, the subject matter disclosed herein is not limited by such examples. In addition, any aspect or design described herein as “exemplary” and / or “demonstrative” is not necessarily to be construed as preferred or advantageous over other aspects or designs, nor is it meant to preclude equivalent exemplary structures and techniques known to those of ordinary skill in the art. Furthermore, to the extent that the terms “includes,” “has,” “contains,” and other similar words are used in either the detaileddescription or the claims, such terms are intended to be inclusive like the term “comprising” as an open transition word without precluding any additional or other elements.
[0059] Reference throughout this specification to “one embodiment” or “an embodiment” or “an instance” or “one instance” means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the present disclosure. Thus, the appearances of the phrases “in one embodiment” or “in an embodiment” in various places throughout this specification are not necessarily all referring to the same embodiment. Furthermore, the particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.
[0060] The terminology used herein is to describe particular embodiments only and is not intended to be limiting the disclosure. As used herein, the singular forms “a”, “an”, and “the” are intended to include the plural forms as well, unless the context indicates otherwise. It will be further understood that the terms “comprises” and / or “comprising,” when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof. As used herein, the term “and / or” includes any combinations of one or more of the associated listed items. It should be noted that the terms “mobile device”, “user equipment”, “user device”, “communication device”, “device” and similar terms are used interchangeably for the purpose of describing the invention. These terms are not intended to limit the scope of the invention or imply any specific functionality or limitations on the described embodiments. The use of these terms is solely for convenience and clarity of description. The invention is not limited to any particular type of device or equipment, and it should be understood that other equivalent terms or variations thereof may be used interchangeably without departing from the scope of the invention as defined herein.
[0061] As used herein, an “electronic device”, or “portable electronic device”, or “user device” or “communication device” or “user equipment” or “device” refers to any electrical, electronic, electromechanical, and computing device. The user device is capable of receiving and / or transmitting one or parameters, performing function / s, communicating with other user devices, and transmitting data to the other user devices. The user equipment may have a processor, a display, a memory, a battery, and an input-means such as a hard keypad and / or a soft keypad. The user equipment may be capable of operating on any radio access technology including but not limited to internet protocol (IP) enabled communication, Zig Bee, Bluetooth, Bluetooth Low Energy, Near Field Communication, Z-Wave, Wi-Fi, Wi-Fi direct, etc. For instance, the user equipment may include, but not limited to, a mobile phone, smartphone, virtual reality (VR) devices, augmented reality (AR) devices, laptop, a general -purpose computer, desktop, personal digital assistant, tablet computer, mainframe computer, or any other device as may be obvious to a person skilled in the art for implementation of the features of the present disclosure.
[0062] Further, the user device may also comprise a “processor” or “processing unit” includes processing unit, wherein processor refers to any logic circuitry for processing instructions. The processor may be a general -purpose processor, a special purpose processor, a conventional processor, a digital signal processor, a plurality of microprocessors, one or more microprocessors in association with a Digital Signalling Processing (DSP) core, a controller, a microcontroller, Application Specific Integrated Circuits, Field Programmable Gate Array circuits, any other type of integrated circuits, etc. The processor may perform signal coding data processing, input / output processing, and / or any other functionality that enables the working of the system according to the present disclosure. More specifically, the processor is a hardware processor.
[0063] While considerable emphasis has been placed herein on the components and component parts of the preferred embodiments, it will be appreciated that many embodiments can be made and that many changes can be made in the preferred embodiments without departing from the principles of the disclosure. These andother changes in the preferred embodiment, as well as other embodiments of the disclosure, will be apparent to those skilled in the art from the disclosure herein, whereby it is to be distinctly understood that the foregoing descriptive matter is to be interpreted merely as illustrative of the disclosure and not as a limitation.
[0064] Wireless communication technology has rapidly evolved over the past few decades. The first generation of wireless communication technology was analog, offering only voice services. Further, text messaging and data services became possible when the second-generation (2G) technology was introduced. The third generation (3G) technology marked the introduction of high-speed internet access, mobile video calling, and location-based services. The fourth generation (4G) technology revolutionized wireless communication with faster data speeds, improved network coverage, and security. Currently, fifth generation (5G) technology is being deployed, offering significantly faster data speeds, lower latency, and the ability to connect many devices simultaneously. These advancements represent a significant leap forward from previous generations, enabling enhanced mobile broadband, improved Internet of Things (loT) connectivity, and more efficient use of network resources. The sixth generation (6G) technology promises to build upon these advancements, pushing the boundaries of wireless communication even further. While the 5G technology is still being rolled out globally, research and development into the 6G are rapidly progressing, with the aim of revolutionizing the way to connect and interact with technology.
[0065] A fifth-generation (5G) network support sidelink communication via a PC5 interface, enabling direct device-to-device (D2D) connectivity for applications like vehicle-to-everything (V2X) and public safety. Sidelink relays allow a remote User Equipment (UE) to connect to a gNodeB (gNB) via a relay UE, extending coverage in out-of-coverage areas. Further, an Uu protocol stack facilitates communication between the relay UE and the gNB, while the PC5 interface supports sidelink communication. However, existing sidelink relays are primarily static or singlehop, relying on simple metrics like Reference Signal Received Power (RSRP) forrelay selection, which limits their effectiveness in dynamic 5G network environments.
[0066] Conventional 5G sidelink relay systems struggle to adapt to fast-changing conditions such as vehicle mobility, network congestion, and Non-Line of Sight (NLOS) links, common in scenarios like highway pileups or urban canyons. Static or single-hop relay approaches fail to provide seamless coverage extension, efficient resource management, or dynamic path switching, leading to reduced Quality of Service (QoS), higher latency, and connection failures for the remote UEs. Additionally, the conventional systems lack scalability, privacy-preserving learning mechanisms, and transparency, making it difficult to optimize relay operations across large-scale deployments or ensure accountability in safety-critical applications like V2X.
[0067] There is, therefore, a need for a method and a system for managing sidelink relay in a network. The present disclosure introduces an Artificial Intelligence (AI)-driven multi-hop relay management system where each UE employs a Reinforcement Learning (RL) Agent to dynamically select relays and form multihop paths, optimizing for throughput, latency, and route stability. Further, a Federated Learning (FL) enables UEs to collaboratively train a global RL model via a FL Coordinator, enhancing scalability and privacy by sharing only model parameters. The present disclosure further introduces an Explainable Al (XAI) module that logs decision rationales for transparency and safety audits. The present disclosure integrates the existing standard procedures such as RRC signalling over Uu and PC5 interfaces, introducing minimal enhancements like multi-hop route indicators, to ensure adaptive, reliable, and scalable sidelink relay operations in 5G networks. Hereinafter, exemplary embodiments of the present disclosure will be described with reference to the accompanying drawings. The various embodiments throughout the disclosure will be explained in more detail with reference to FIG. 1-FIG. 8.
[0068] FIG. 1 illustrates an exemplary network architecture 100 for managing multi-hop relay chain in a network 106, in accordance with an embodiment of the present disclosure. As illustrated in FIG. 1, the network architecture 100 may include one or more User Equipments (UEs) 104-1, 104-2... 104-N associated with one or more users 102-1, 102-2... 102-N in an environment. A person of ordinary skill in the art will understand that one or more users 102-1, 102-2... 102-N may be collectively referred to as the users 102. Similarly, a person of ordinary skill in the art will understand that one or more UEs 104-1, 104-2... 104-N may be collectively referred to as the UE 104 or the UEs 104. Although only three UE 104 are depicted in FIG. 1, however, any number of the UE 104 may be included without departing from the scope of the ongoing description.
[0069] In an embodiment, the UE 104 may include smart devices operating in a smart environment, for example, an Internet of Things (loT) system. In such an embodiment, the UE 104 may include, but are not limited to, smartphones, smart watches, smart sensors (e.g., a mechanical, a thermal, an electrical, a magnetic, etc.), networked appliances, networked peripheral devices, networked lighting system, communication devices, networked vehicle accessories, networked vehicular devices, smart accessories, tablets, a smart television (TV), computers, a smart security system, a smart home system, other devices for monitoring or interacting with or for the users 102 and / or entities, or any combination thereof. A person of ordinary skill in the art will appreciate that the UE 104 may include, but not limited to, intelligent, multi-sensing, network-connected devices, that may integrate seamlessly with each other and / or with a central server or a cloudcomputing system or any other device that is network-connected.
[0070] Additionally, in some embodiments, the UE 104 may include, but not limited to, a handheld wireless communication device (e.g., a mobile phone, a smartphone, a phablet device, and so on), a wearable computer device (e.g., a headmounted display computer device, a head-mounted camera device, a wristwatch computer device, and so on), a Global Positioning System (GPS) device, a laptop computer, a tablet computer, or another type of portable computer, a media playingdevice, a portable gaming system, and / or any other type of computer device with wireless communication capabilities, and the like. In an embodiment, the UE 104 may include, but are not limited to, any electrical, electronic, electromechanical, or equipment, or a combination of one or more of the above devices, such as virtual reality (VR) devices, augmented reality (AR) devices, a laptop, a general-purpose computer, a desktop, a personal digital assistant, a tablet computer, a mainframe computer, or any other computing device. Further, the UE 104 may include one or more in-built or externally coupled accessories including, but not limited to, a visual aid device such as a camera, an audio aid, a microphone, a keyboard, and input devices for receiving input from the user 102 or an entity such as a touchpad, a touch-enabled screen, an electronic pen, and the like. A person of ordinary skill in the art will appreciate that the UE 104 may not be restricted to the mentioned devices and various other devices may be used.
[0071] In FIG. 1, the UE 104 may communicate with the system 108 through the network 106 for sending or receiving various types of data. In an embodiment, the network 106 may include at least one of the 5G network, the 6G network, or the like. The network 106 may enable the UE 104 to communicate with other devices in the network architecture 100 and / or with the system 108. The network 106 may include a wireless card or some other transceiver connection to facilitate this communication. In another embodiment, the network 106 may be implemented as, or include any of a variety of different communication technologies such as a wide area network (WAN), a local area network (LAN), Virtual Local Area Network (VLAN), a wireless network, a mobile network, a Virtual Private Network (VPN), the Internet, the Public Switched Telephone Network (PSTN), or the like.
[0072] In an embodiment, the network 106 may include, by way of example but not limitation, at least a portion of one or more networks having one or more nodes that transmit, receive, forward, generate, buffer, store, route, switch, process, or a combination thereof, etc. one or more messages, packets, signals, waves, voltage or current levels, some combination thereof, or so forth. The network 106 may also include, by way of example but not limitation, one or more of, a wireless network,a wired network, an internet, an intranet, a public network, a private network, a packet-switched network, a circuit-switched network, an ad hoc network, an infrastructure network, the PSTN, a cable network, a cellular network, a satellite network, a fiber optic network, or some combination thereof.
[0073] In an embodiment, the UE 104 is communicatively coupled with the network 106. The network 106 may receive a connection request from the UE 104. The network 106 may send an acknowledgment of the connection request to the UE 104. The UE 104 may transmit a plurality of signals in response to the connection request.
[0074] In some embodiments, the system 108 may be implemented within the network 106. The system 108 may receive an indication that a remote User Equipment (UE) requests access to the network through one or more relay UEs. The system 108 may determine a multi -hop relay chain including at least one relay UE between the remote UE and the network node based on the received indication. Further, the system 108 may generate a multi-hop configuration container associated with the multi-hop relay chain. The multi-hop configuration container includes at least one of multi-hop relay chain identifier, remote UE information, hop-wise relay configuration information, and bearer configuration for signaling and data communication associated with the remote UE. The system 108 may transmit a Radio Resource Control (RRC) reconfiguration message including the multi-hop configuration container to the remote UE and the one or more relay UEs to establish Signaling Radio Bearer (SRB) across the multi-hop relay chain. Further, the system 108 may receive an RRC setup complete message comprising a Non-Access Stratum (NAS) message from the remote UE through the multi-hop relay chain. The system 108 may transmit a security control message for the remote UE through the multi -hop relay chain. Further, the system 108 may establish one or more data radio bearers for the remote UE over the multi-hop relay chain.
[0075] Although FIG. 1 shows exemplary components of the network architecture 100, in other embodiments, the network architecture 100 may include fewercomponents, different components, differently arranged components, or additional functional components than depicted in FIG. 1. Additionally, or alternatively, one or more components of the network architecture 100 may perform functions described as being performed by one or more other components of the network architecture 100.
[0076] FIG. 2 illustrates an exemplary block diagram 200 of the system 108 for managing multi-hop relay chain in a network 106, in accordance with an embodiment of the disclosure.
[0077] In an embodiment, the system 108 may include one or more processor(s) 202. The one or more processor(s) 202 may be implemented as one or more microprocessors, microcomputers, microcontrollers, digital signal processors, central processing units, logic circuitries, and / or any devices that process data based on operational instructions. Among other capabilities, the one or more processor(s) 202 may be configured to fetch and execute computer-readable instructions stored in a memory 204 of the system 108. The memory 204 may be configured to store one or more computer-readable instructions or routines in a non-transitory computer readable storage medium, which may be fetched and executed to create or share data packets over a network service. The memory 204 may include any non-transitory storage device including, for example, volatile memory such as a Random-Access Memory (RAM), or a non-volatile memory such as an Erasable Programmable Read Only Memory (EPROM), a flash memory, and the like.
[0078] In an embodiment, the system 108 may include an interface(s) 206. The interface(s) 206 may include a variety of interfaces, for example, interfaces for data input and output devices (VO), storage devices, and the like. The interface(s) 206 may facilitate communication through the system 108. The interface(s) 206 may also provide a communication pathway for one or more components of the system 108. Examples of such components include, but are not limited to, a processing engine 208 and a database 210.
[0079] In an embodiment, the system 108 may include a network node 208 that may be implemented as a combination of hardware and programming (for example, programmable instructions) to implement one or more functionalities of the network node 208. In examples described herein, such combinations of hardware and programming may be implemented in several different ways. For example, the programming for the network node 208 may be processor-executable instructions stored on a non-transitory machine-readable storage medium. The hardware for the network node 208 may include a processing resource (for example, one or more processors) to execute such instructions. In the present examples, the machine-readable storage medium may store instructions that, when executed by the processing resource, implement the network node 208. In such examples, the system 108 may include the machine-readable storage medium storing the instructions and the processing resource to execute the instructions, or the machine-readable storage medium may be separate but accessible to the system 108 and the processing resource. In other examples, the network node 208 may be implemented by electronic circuitry. In an embodiment, the network node 208 may be implemented within a gNB-central unit (gNB-CU), an edge server, or an operator-controlled network controller.
[0080] In an embodiment, the plurality of UEs 104 are in the network’s 106 coverage. Each of the plurality of UEs 104 may send a UECapability Information to the network 106. The UECapability Information is used to transfer the UE radio access capabilities requested by the network 106. In some embodiments, the plurality of UEs 104 may include a remote UE which at some point of time may be out-of-coverage of the network 106, an intermediate relay UE which may or may not be out-of-coverage at any point of time, and an anchor relay UE which is always in coverage of the network 106. Further, the relay-capable UEs such as an intermediate relay UE and an anchor relay UE may indicate “Relay capability” or “multi-hop L2 Relay support” indicating the relaying capabilities. The base station (gNB-CU) of the network 106 stores the UE capabilities in a database 210. In an embodiment, the network node 208 may be configured for managing multi -hoprelay chain establishment and optimization in the network 106. In some embodiments, the network node 208 may be implemented within a gNB-CU, an edge server, or an operator-controlled network controller. The network node 208 may maintain one or more machine learning (ML) models, such as a Reinforcement Learning (RL) model, for assisting in determination, update, and optimization of the multi-hop relay chain. The network node 208 may further store relay capability information, UE context information, and model-related information in the database 210 for subsequent relay chain management.
[0081] In an embodiment, the network node 208 may be configured to provide one or more initialization parameters associated with ML-assisted relay determination. The one or more initialization parameters may include one or more of configuration settings, initial weights, threshold values, route-selection parameters, relay advertisement parameters, discovery intervals, reward-function coefficients, or operational constraints associated with relay selection. In some embodiments, the one or more initialization parameters may be derived based on network configuration, operator policy, UE operational context, or a ML model maintained at the network node 208. In an embodiment, each of the plurality of UEs 104 may obtain an initial RL model from a federated learning coordinator associated with the network node 208 or may use a fallback local RL model when a shared global model is unavailable. In an embodiment, the shared global model may correspond to an aggregated reinforcement learning model generated by a federated learning coordinator based on local model updates received from multiple UEs. The shared global model may be redistributed to participating UEs for subsequent relay selection, route optimization, or scheduling-related decision making, while a fallback local RL model may be used when the shared global model is unavailable. In some embodiments, the RL model may be stored locally at the UE in a memory as model parameters, for example, ModelParams O. The RL model may correspond to a neural-network-based learning model, including a Q-learning model, deep Q-network model, policy-gradient model, or another learning model suitable for relay selection and route optimization. In an embodiment, the one or more relay-capableUEs may use the RL model to adapt relay advertisement behavior. For example, a relay UE experiencing high load, limited resources, or unfavourable mobility conditions may reduce a relay advertisement frequency, modify one or more transmitted relay parameters, or indicate a load-related condition in a discovery message, so as to discourage selection of the relay UE for additional traffic.
[0082] In an embodiment, the network node 208 may be configured to receive an indication that a remote UE requests access to the network through one or more relay UEs. To receive the indication, the network node 208 may receive at least one of a RRC setup request, an initial access request message, and a relay request information associated with the remote UE through the one or more relay UEs. In an embodiment, the network node 208 may be configured to receive information associated with one or more discovery signals corresponding to one or more relay UEs. The one or more discovery signals may be broadcast or advertised by relay-capable UEs, including an intermediate relay UE and an anchor relay UE, over a PC5 interface during a sidelink discovery phase. In some embodiments, the one or more discovery signals may be transmitted periodically using one or more resource pools and discovery intervals configured by the network 106 through Radio Resource Control (RRC) signaling. In an embodiment, the one or more discovery signals may indicate presence and relay capability of the corresponding relay UE and may include one or more of relay UE identity, network coverage status, relay availability, current load, velocity vector, relay health metric, sidelink support capability, or multi-hop relay support information. Such discovery -related information may enable determination of whether the remote UE is to be served through a single relay UE or through a multi-hop relay chain including multiple relay UEs. In an embodiment, the indication received by the network node 208 may be based on the one or more discovery signals and one or more access-related messages forwarded through one or more relay UEs. The network node 208 may become aware of the remote UE request and one or more available relay candidates for formation of the multi-hop relay chain.
[0083] Further, the network node 208 may be configured to determine a multi-hop relay chain including at least one relay UE between the remote UE and the network node based on the received indication. To determine the multi-hop relay chain, the network node 208 may apply a machine learning model to at least one of signal quality, relay load, throughput, latency, mobility condition, coverage condition, and quality-of-service requirement associated with the one or more relay UEs to optimize the determination of the multi-hop relay chain. In an embodiment, to determine the multi-hop relay chain, the network node 208 may process the one or more discovery signals and extract one or more relay metrics associated with each relay UE, including, for example, signal -to-noise ratio, speed, load, coverage condition, queue state, latency, throughput capability, or mobility stability. The network node 208 may generate a candidate relay list including corresponding relay metrics for relay UEs. In an embodiment, the machine learning model may define a state associated with relay selection. The state includes at least one of the candidate relay list, link qualities, current queue size, UE velocity, potential multihop paths, traffic demand, or service requirements associated with the remote UE. Based on the state, the machine learning model may select an action from an action space including at least one of selecting a relay UE, maintaining a current relay UE, selecting a multi-hop relay path, or switching from a first relay path to a second relay path. In an example, the state S associated with relay selection may be represented as:S = {list of candidate relays, link qualities, current queue size, UE velocity, potential multi-hop paths, traffic demand} . (1)
[0084] In an embodiment, the machine learning model may evaluate a plurality of possible relay paths by estimating one or more composite link characteristics of corresponding multi-hop routes. For example, the machine learning model may determine that a two-hop relay path having moderate per-hop signal quality provides improved end-to-end throughput, reduced packet loss, or improved quality-of-service relative to a single-hop path having poor radio quality. The network node 208 may determine the multi-hop relay chain based on an expectedperformance outcome rather than only on instantaneous signal strength. In an embodiment, once a relay path or updated multi-hop relay chain is determined, the remote UE may initiate a RRC request over a PC5 interface toward a selected relay UE. The selected relay UE, or an in-coverage relay UE associated with the determined chain, may then transmit a SidelinkUEInformationNR message or other relay indication toward the network 106 over a Uu interface, enabling the network node 208 to continue establishment of the multi-hop relay chain.
[0085] The network node 108 may transmit the machine learning model to the one or more relay UEs for local update. Further, the network node 108 may receive model update information from the one or more relay UEs. The network node 108 may aggregate the model update information to generate an updated machine learning model. Further, the network node 108 may use the updated machine learning model for subsequent determination of the multi-hop relay chain. In an embodiment, the machine learning model may be updated using one or more local learning results generated at one or more relay UEs and / or at the remote UE. Each participating UE may collect local experience information, including state, action, and reward tuples, in a local buffer and may perform a local update of model parameters using a RL algorithm, such as Q-learning, deep Q-network learning, or policy-gradient learning. In an embodiment, the one or more relay UEs may transmit updated local model parameters to a federated learning coordinator associated with the network node 208. The network node 208 may aggregate model update information received from multiple UEs to generate the updated machine learning model. In some embodiments, raw user data may remain local to the corresponding UE, while only learned model parameters, gradients, or weights are transmitted to the network node 208. In an example, aggregation of updated local model parameters may be represented as:0_global <— X(k=l to K) (n_k / N) 0_localAk . (2)
[0086] where n_k represents local data size associated with UE k, N represents total data size, and K represents number of participating UEs. In an embodiment, theupdated machine learning model may be redistributed by the network node 208 to one or more UEs for subsequent relay determination, thereby enabling learned relay-selection behavior from one operating environment to improve relay selection in another operating environment.
[0087] In some embodiments, to determine the multi-hop relay chain, the network node 208 may determine topology context information identifying an ordered sequence of the remote UE and the at least one relay UE. Further, the network node 208 may assign a multi-hop relay chain identifier to the multi-hop relay chain. In an embodiment, the topology context information may further identify one or more upstream relay relationships and one or more downstream relay relationships between adjacent relay UEs of the multi-hop relay chain. The topology context information may therefore enable the network node 208 to determine an ordered forwarding structure from the remote UE to an anchor relay UE and further toward the network 106. In an embodiment, the topology context information may be updated responsive to mobility of a relay UE, route degradation, change in load condition, loss of connectivity, or discovery of an alternative relay UE. In such embodiments, the network node 208 may retain the multi-hop relay chain identifier and update one or more relay positions within the multi-hop relay chain.
[0088] In an embodiment, the topology context information and the multi -hop relay chain identifier may be used for mobility handling associated with the multi-hop relay chain. If an in-coverage relay UE moves to another cell served by another gNB while maintaining network connectivity, the gNB-CU may trigger a handover procedure and may transfer context associated with the relay UE together with information associated with the multi-hop relay chain to a target gNB. The target gNB may establish corresponding resources for the relay UE and may re-establish or reconfigure the multi-hop relay chain based on the transferred context information. In an embodiment, if an intermediate relay UE changes position, loses connectivity, becomes overloaded, or if another relay route becomes preferable, the network node 208 may update the topology context information and may reconfigure the multi-hop relay chain to pivot the remote UE from a first relay routeto a second relay route. In some embodiments, the network node 208 may maintain the multi-hop relay chain identifier while updating one or more relay positions of the multi-hop relay chain. In other embodiments, a new multi-hop relay chain identifier may be assigned to an updated relay path. In an embodiment, if the remote UE moves into direct coverage of the network 106 or a shorter connection path becomes available, the network node 208 may release the multi-hop relay chain and may hand over the remote UE to a direct Radio Resource Control connection with the network 106.
[0089] In an embodiment, the network node 208 may be configured to generate a multi-hop configuration container associated with the multi-hop relay chain. The multi-hop configuration container includes at least one of multi-hop relay chain identifier, remote UE information, hop-wise relay configuration information, and bearer configuration for signaling and data communication associated with the remote UE. In an embodiment, the multi-hop configuration container may further include one or more of per-hop PC5 configuration parameters, logical channel details, radio link control parameters, relay-side forwarding parameters, quality-of-service parameters, route index information, remote UE context information, or Uu-side bearer adjustment associated with an anchor relay UE. In an embodiment, the multi-hop configuration container may be generated as a unified chain-level configuration structure such that configuration of multiple relay hops may be coordinated by the network node 208 with reduced repeated hop-by-hop signaling exchanges.
[0090] Further, the network node 208 may be configured to transmit a Radio Resource Control (RRC) reconfiguration message including the multi-hop configuration container to the remote UE and the one or more relay UEs to establish Signaling Radio Bearer (SRB) across the multi-hop relay chain. To transmit the RRC reconfiguration message, the network node 208 may apply each of the hopwise relay configuration information from the multi-hop configuration container to the corresponding relay UEs based on the topology context information of the multi-hop relay chain. In an embodiment, the RRC reconfiguration messageincluding the multi-hop configuration container may be transmitted toward an incoverage relay UE associated with the multi-hop relay chain, and corresponding portions of the multi-hop configuration container may be forwarded to one or more downstream relay UEs and the remote UE in accordance with the topology context information. In an embodiment, establishment of the Signaling Radio Bearer across the multi-hop relay chain may correspond to end-to-end establishment of SRB1 over multiple PC5 segments and a Uu segment. In some embodiments, the one or more relay UEs may apply respective hop-wise relay configuration information for configuring corresponding upstream and downstream hops. In an embodiment, the Signaling Radio Bearer 1 (SRB1) may correspond to a signaling bearer used for Radio Resource Control (RRC) message exchange after initial setup, and in the present disclosure may be established end-to-end across the multi-hop relay chain over one or more PC5 segments and a Uu segment. In some embodiments, Signaling Radio Bearer 2 (SRB2) may correspond to an additional signaling bearer established after security activation, while one or more Data Radio Bearers (DRBs) may correspond to bearers configured for user-plane data transmission associated with the remote UE.
[0091] In an embodiment, the multi-hop relay chain may be configured while reusing existing interface procedures between the gNB-CU and the gNB-DU. In some embodiments, the gNB-CU may use one or more existing Fl procedures including at least one of UL RRC MESSAGE TRANSFER, DL RRC MESSAGE TRANSFER, UE CONTEXT SETUP REQUEST, UE CONTEXT MODIFICATION REQUEST, UE CONTEXT SETUP RESPONSE, or UE CONTEXT MODIFICATION RESPONSE for establishing, updating, or maintaining the multi-hop relay chain. Thus, the network 106 may support multihop relay operation with minimal impact on the Fl interface and without requiring mandatory introduction of a new Fl procedure. In an embodiment, the gNB-DU may treat an in-coverage relay UE associated with the multi-hop relay chain as a scheduled UE on the Uu side while the gNB-CU maintains relay-related context for the remote UE and the multi-hop relay chain. In some embodiments, multi-hop-specific processing may be maintained primarily at the gNB-CU and the relay UEs, while the gNB-DU may continue to handle lower-layer bearer setup, forwarding support, and radio resource scheduling using existing protocol behavior. This may preserve backward compatibility with existing single-hop relay implementations and may further allow deployment of multi-hop relay support with limited modification of DU-side procedures.
[0092] In an embodiment, the network node 208 may be configured to receive an RRC setup complete message including a Non-Access Stratum (NAS) message from the remote UE through the multi -hop relay chain. In an embodiment, the RRC setup complete message including the Non-Access Stratum message may be associated with a core-network procedure of the remote UE, including at least one of registration, service request, authentication, or context setup. The network node 208 may forward or process the Non-Access Stratum message while maintaining the multi-hop relay chain as an access path between the remote UE and the network 106.
[0093] Further, the network node 208 may be configured to transmit a security control message for the remote UE through the multi-hop relay chain. In an embodiment, the security control message may include a Security Mode Command or another access-stratum security-related message associated with activation of security procedures for the remote UE. The one or more relay UEs may forward the security control message through the multi-hop relay chain and may similarly forward a corresponding security completion message received from the remote UE.
[0094] In an embodiment, the network node 208 may be configured to establish one or more data radio bearers for the remote UE over the multi-hop relay chain. The one or more data radio bearers provide control-plane signaling and user-plane communication between the remote UE and the network node. In an embodiment, the network node 208 may be configured to determine one or more traffic scheduling parameters for sidelink communication over the multi-hop relay chain.The one or more traffic scheduling parameters may include one or more of subchannel selection, time-slot allocation, relay transmission order, queue handling policy, traffic priority, or resource request information associated with one or more relay UEs. In some embodiments, the one or more traffic scheduling parameters may be determined to reduce transmission overlap, reduce interference, improve resource utilization, and preserve quality-of-service across multiple hops. In an embodiment, where sidelink communication operates in an autonomous resourceselection mode, the network node 208 may determine or assist in determining resource-selection recommendations for corresponding relay hops. Where sidelink communication operates in a scheduled mode, the network node 208 may incorporate one or more relay-related resource requests into network-side scheduling. In this manner, the network node 208 may remain responsible for network-side traffic scheduling while relay UEs perform forwarding based on configured resources. In an embodiment, one or more relay UEs may buffer packets associated with the remote UE and may report one or more queue-related parameters, throughput-related parameters, or congestion-related parameters to the network node 208. The network node 208 may use such reported parameters to update the multi-hop relay chain, adjust one or more traffic scheduling parameters, or determine an alternative relay path when a current relay UE becomes overloaded.
[0095] Further, the network node 208 may be configured to generate relay chain selection information associated with determination of the multi-hop relay chain. The relay chain selection information includes at least one of an identity of at least one selected relay UE, an ordered position of the at least one selected relay UE in the multi-hop relay chain, a chain identifier, or one or more relay metrics used for determination of the multi-hop relay chain. In an embodiment, the network node 208 may be configured to calculate one or more feedback parameters based on one or more network parameters corresponding to communication over the multi-hop relay chain. The one or more feedback parameters may be based on at least one of achieved throughput, latency, block error rate, queue growth, handover frequency, route stability, or communication success rate associated with the multi-hop relaychain. In an example, a reward function associated with the one or more feedback parameters may be represented as:R = a x (achieved throughput) - P * (latency) - y x (block error rate) . (3)
[0096] where a, P, and y are weight factors. In an embodiment, the reward R may represent a scalar feedback value used by the reinforcement learning process to evaluate an outcome of a selected relay action, relay path, or scheduling decision. In some embodiments, the reward R may increase when throughput or route stability improves and may decrease when latency, block error rate, congestion, or route failure increases. In an embodiment, the network node 208 may calculate one or more updated initialization parameters based on the one or more feedback parameters and may use the one or more updated initialization parameters to refine future determination of the multi-hop relay chain. In some embodiments, updating of the machine learning model may be represented as:Q(S,a) Q(S,a) + p [r + y max_a' Q(S',a') - Q(S,a)] . (4)
[0097] where S represents a current state, a represents a selected relay action, r represents reward, p represents learning rate, and y represents discount factor. In an embodiment, the network node 208 may update selection of the one or more relay UEs for the multi-hop relay chain based on the one or more updated initialization parameters. Such update may include selection of a new relay UE, modification of an existing relay path, switching from a first relay chain to a second relay chain, or maintaining a current relay chain when continued use of the current relay chain is determined to be preferable. In an embodiment, if an anchor relay UE moves to a new cell or if coverage conditions change, the network node 208 may trigger updating of the multi-hop relay chain or initiate relay reselection. In some embodiments, if a current relay path degrades or fails, the machine learning model may assist the network node 208 in selecting an alternative relay path and reestablishing communication through the alternative relay path.
[0098] In an embodiment, the relay chain selection information may be used for logging, operator-side analytics, route adaptation, or explanation of relay-selection decisions. In some embodiments, an explainable artificial intelligence module may identify one or more influential input features associated with a selected relay decision, including at least one of relay load, signal quality, mobility, or historical success rate. Such information may be used to generate human-readable explanation data or to guide adjustment of reward-function parameters or state definitions used for subsequent relay determination.
[0099] In an embodiment, AI / ML-based relay selection, route optimization, model update, federated learning, explainable Al processing, or post-setup optimization may be optional. In some embodiments, the network node 208 may determine, establish, configure, and update the multi-hop relay chain using non-AI signaling and configuration procedures based on relay capability information, topology context information, radio measurements, bearer requirements, or operator policy. In other embodiments, one or more AI / ML techniques may be additionally applied to improve relay selection, route maintenance, scheduling, or performance optimization without changing the underlying compatibility of the multi-hop relay procedure with standard RRC, NAS, and bearer-establishment signaling. In an embodiment, the network node 208 may selectively enable or disable AI / ML-based processing based on operator preference, UE capability, network condition, or availability of model information.
[0100] FIG. 3 illustrates an exemplary system architecture 300 for managing multihop relay chain in the network 106, in accordance with an embodiment of the present disclosure. The system architecture 300 may support Al-driven multi-hop relay management of the UEs 104, enabling adaptive relay selection, route formation, and resource coordination for the UEs in dynamic environments such as out-of-coverage areas, cell-edge scenarios, or non-line-of-sight (NLOS) conditions. The system 300 may leverage Reinforcement Learning (RL), Federated Learning (FL), and Explainable Al (XAI) to enhance coverage, optimize performance, and ensure transparency during the multi-hop sidelink communication.
[0101] In FIG. 3, a communication flow between the various UEs and the gNB 304 of the 5G network architecture is depicted. In an embodiment, the system 300 may include a UE side 302 components and the gNB 304 of the network 106. The UE side 302 components may include a remote UE 306, an intermediate relay UE 308, and an anchor relay UE 310. The remote UE 306 may lack direct connectivity to the gNB 304 due to being out of coverage, at the cell edge, or in an NLOS scenario. For example, the remote UE 306 may be a vehicle in a rural area or an urban canyon unable to establish a direct Uu connection to the gNB 304. Further, the intermediate relay UE 308 may act as a relay in a multi-hop sidelink relay chain, forwarding data between the remote UE 306 and anchor relay UE 310 in the 5G network 106. Unlike the anchor relay UE 310, which directly connects to the gNB 306 via the Uu protocol stack 326, the intermediate relay UE 308 is positioned between the remote UE 306 and the anchor relay UE 310 in the relay chain, facilitating multi-hop sidelink communication. In an embodiment, the intermediate relay UE 308 and the anchor relay UE 310 are the devices authorized to forward data on behalf of other UEs. The intermediate relay UE 308 and the anchor relay UE 310 have both normal 5G NR Uu capabilities and a sidelink (PC5) interface for relay.
[0102] In some embodiments, each of the remote UE 306, the intermediate relay UE 308, and the anchor relay UE 310 may include a Reinforced Learning (RL) agent and a Federated Learning (FL) client 318A, 318B, and 318C respectively (commutatively referred as 318), a PC5 protocol stack 320A, 320B, and 320C respectively (commutatively referred as 320), and a Uu protocol stack (inactive if the remote UE 306 is Out-Of-Coverage (OOC)) 322, a Uu protocol stack (inactive if the intermediate relay UE 308 is truly OOC) 324, and a Uu protocol stack 326 respectively. Further, the RL agent 318 may be responsible for making real-time, autonomous decisions to optimize sidelink relay operations, including relay selection, multi-hop route formation, resource allocation, and traffic management. The RL agent 318 operates using reinforcement learning, where the RL agent 318 learns to make decisions by interacting with its environment, receiving feedback in the form of rewards, and improving its actions over time. The FL client 310 mayallow the UEs to participate in federated learning by sending local RL model parameters to a Federated Learning (FL) Coordinator 312 and receiving an updated global model. The FL client 310 ensures privacy by sharing only model parameters, not raw data. In an embodiment, the RL agent and the FL client 318 may be implemented in an Al relay management module. The Al relay management module may be configured to gather measurements such as RSRP, link throughput, mobility data to feed the RL agent 318. Further, the Al relay management module sends updates to a FL coordinator 312 and performs peer-to-peer averaging of trained RL model parameters. Further, the PC5 protocol stack 320 may enables direct communication between the UEs 104. The PC5 protocol stack 320 may act as a communication pathway between the remote UE 306 and the intermediate relay UE 308 and the anchor relay UE 310 in a multi-hop chain. The PC5 protocol stack 320 supports the exchange of discovery messages, Radio Resource Control (RRC) signalling such as RRCSetupRequest, RRCSetup), and data forwarding. Further, the Uu protocol stack 322, 324, 326 (commutatively referred as 322) may be a set of protocols used for communication between the UEs 104 which are in OOC and the gNB 304 in the 5G network 106. In an embodiment, the “IntRelay” and “AncRelay” may denote the intermediate relay UE 308 and the anchor relay UE 310 respectively. Similarly, “OOC” may denote an out-of-coverage condition in which a corresponding UE is unable to maintain direct Uu connectivity with the gNB.
[0103] In an embodiment, the gNB 304 may include a FL coordinator 312, a gNB-Central unit (CU) 314, and a gNB -Distributed Unit (DU) 316. The FL coordinator 312 may be deployed as a separate edge server or cloud node. The FL coordinator 312 aggregates local RL model parameters from multiple UEs, performs federated averaging, and redistributes an updated global RL model to the UEs, enhancing the RL agent performance across the network 106 without requiring UEs to share raw data. Further, the FL Coordinator 312 is connected to UEs via the Uu protocol stack 324 when the UEs are in coverage, enabling periodic updates of the global model. Further, the gNB-CU 316 may host high-layer protocols such as the RRC, ServiceData Adaptation Protocol (SDAP), and Packet Data Convergence Protocol (PDCP). The gNB-CU 314 may manage RRC connections for both directly connected anchor relay UE 310 and remote UE 306 served via relays. The gNB-CU 314 creates a context for the remote UE 306, referencing the anchor relay UE 310 that connects directly to the gNB 306 via the Uu protocol stack 322. Further, the gNB-DU 316 may handle lower-layer functions, including Radio Link Control (RLC), Medium Access Control (MAC), and Physical (PHY) layers. The gNB-DU 316 may configure sidelink radio bearers on relay UEs 308, 310 for multi-hop transmissions. The gNB-DU 316 may receive sidelink-related messages such as SidelinkUEInformationNR from the anchor relay UE 310 and forwards them to the gNB-CU 314 via the Fl interface. The Fl interface may facilitate the exchange of control messages such as UL RRC Message Transfer, remote UE context, relay UE contexts, sidelink configurations, and UE Context Modification between the gNB-DU 314 and the gNB-CU 316.
[0104] In some embodiments, if the remote UE 304 is out-of-coverage of the gNB 304, the intermediate relay UE 308 and the anchor relay UE 310 broadcast discovery messages over the PC5 protocol stack 320, including metrics such as the identity, network coverage status, and relay health (e.g., load, velocity vector). The remote UE 306 may receive the broadcast messages and compiles a candidate list. The RL Agent 318A evaluates the candidate list and selects an optimal relay path such as either a single relay UE or a multi -hop chain. Once the relay path is selected, the remote UE 306 sends an RRCSetupRequest over the PC5 protocol stack 320 to the chosen intermediate relay UE 308 in a multi-hop scenario. Further, the intermediate relay UE 308 forwards the request to the anchor relay UE 310, which communicates with the gNB-DU 316 via the Uu protocol stack 326 using a SidelinkUEInformationNR message. The gNB-DU 316 and the gNB-CU 314 coordinate via the Fl Interface to establish the remote UE’s 306 context and configure the relay chain.
[0105] After setup, data from the remote UE 306 is forwarded through the relay chain (e.g., remote UE 306 — intermediate relay UE 308 — anchor relay UE 310gNB 304) using the PC5 protocol stack 320 and the Uu protocol stack 322. The gNB 306 ensures end-to-end encryption, while each relay UE 306, 308, and 310 coordinates resource allocation to minimize interference and congestion. Further, the UEs 306, 308, and 310 periodically send the local RL model parameters to the FL Coordinator 312, which aggregates them to update the global RL model. The updated RL model is then distributed back to the UEs 306, 308, and the 310, enhancing the relay selection capabilities. In some embodiments, each UE 306, 308, and the 310 may include the XAI Module that generates logs explaining relay selection decisions (e.g., “intermediate relay UE 308 chosen due to high link stability and low load”). The logs may then be accessed by the operator for auditing purposes, ensuring transparency and safety. In some embodiments, some operators may prefer an offline phase such as lab testing and simulations to get a pretrained global RL model then in the field, the FL learning step continues incrementally ensuring that from day one, the system 300 has a decent policy. In fully out-of-coverage scenarios such as no central server, the UEs 104 may perform peer-to-peer federated averaging if at least some cluster of UEs 104 are able to share initialization parameters within each other.
[0106] FIG. 4 illustrates an exemplary process flow of a method 400 for managing multi-hop relay chain in the network 106, in accordance with an embodiment of the present disclosure. The method 400 may be implemented by the remote UE 306, the intermediate relay UE 308, the anchor relay UE 310, the gNB-CU 314, the gNB-DU 316, and the FL coordinator 312 of the system 300.
[0107] In an embodiment, the remote UE 306, the intermediate relay UE 308, and the anchor relay UE 310 registers with the gNB of the network 106. The remote UE 306, the intermediate relay UE 308, and the anchor relay UE 310 may send an UECapability Information message towards the network 106. The UECapabilitylnformation message is used to transfer the UE radio access capabilities requested by the network 106. Further, the relay-capable UEs such as intermediate relay UE 308 and the anchor relay UE 310 may indicate “Relay capability” or “multi-hop L2 Relay support” indicating the relaying capabilities.The gNB-CU 316 may store the information related to the relaying capabilities. If authorized by the operator for relay, the intermediate relay UE 308 and the anchor relay UE 310 may advertise itself as a relay node over sidelink.
[0108] When the remote UE 306, the intermediate relay UE 308, and the anchor relay UE 310 are still in coverage of the network 106, at step 402 A, the remote UE 306 may download an initial global RL model from the FL coordinator 312. The FL coordinator 312 may be implemented at an edge or cloud within the gNB-DU 316 and the gNB-CU 314. Further, at step 402B, the intermediate relay UE 308 may download the initial global RL model from the FL coordinator 312. At step 402C, the anchor relay UE 310 may download the initial global RL model from the FL coordinator 312. The RL model may be represented as 0global\theta_{\ text{global}}0 global. The remote UE 306, the intermediate relay UE 308, and the anchor relay UE 310 may store the RL model locally in a memory. In some embodiments, the remote UE 306, the intermediate relay UE 308, and the anchor relay UE 310 may retrieve a baseline RL policy from the RL model for multi -hop relay decisions or a fallback local RL model if none is available.
[0109] At step 404, the intermediate relay UE 308 may broadcast sidelink discovery signals along with advanced load, velocity, or Al capability over the PC5 protocol stack. In an embodiment, the 5G ProSe UE-to-UE relay sends aUE-to-UE relay discovery announcement message. The UE-to-UE relay discovery announcement message contains the type of discovery message, User Info ID of the 5G ProSe UE-to-UE Relay, RSC and direct discovery set including list of protected user info (i.e. Application Layer ID) received from the 5G ProSe End UEs supporting the RSC. The U2N Relay UE can perform Relay discovery message transmission and may monitor the sidelink for Relay discovery message while in RRC IDLE, RRC INACTIVE or RRC CONNECTED. The network may broadcast or configure via dedicated RRC signalling a maximum Uu RSRP threshold, a minimum Uu RSRP threshold, or both, which are used by the U2N Relay UE to determine if it can transmit Relay discovery messages to U2N Remote UE. In an embodiment, the UE-to-UE relay discovery announcement message maybe a sidelink discovery message used to advertise relay availability and relay-associated service information to one or more remote UEs. In some embodiments, a Radio Service Code (RSC) may identify a service or application context associated with the relay discovery, and an Application Layer ID may identify an application-layer service context associated with protected user information or discovery authorization. A U2N Relay UE may denote a UE-to-Network relay UE that forwards signaling or data between a remote UE and the network over PC5 and Uu interfaces.
[0110] At step 406, the anchor relay UE 310 may broadcast sidelink discovery signals along with advanced load, velocity, or Al capability over the PC5 protocol stack. The intermediate relay UE 308 and the anchor relay UE 310 may advertise presence, coverage, load, throughput, etc in the sidelink discovery signals. In some embodiments, the sidelink discovery signals may include UE identity / ProSe ID, network coverage status, remaining resources, optional “multi-hop availability” flag and may be broadcasted at specified intervals based on the RL model.[OHl] At step 408, the remote UE 306 may scan advertised discovery signals to gather Reference Signal Received Power (RSRP) and load metrics of the relay UEs and build a candidate list of relay UEs. The remote UE 306 may scan the sidelink resource pool and receive multiple discovery advertisements from potential relay UEs such as the intermediate relay UE 308 and the anchor relay UE 310. If the remote UE 306 is itself out-of-coverage, it may rely on sidelink scanning. Further, the remote UE 306 may extract CandidateRelay i, SNR i, Speed i, Load i, etc. from the sidelink discovery signals and complies them in the candidate list corresponding to each relay UE. In an embodiment, the RSRP may denote a received power measurement associated with a reference signal and may be used as one of the parameters for evaluating relay suitability, coverage condition, or route quality. Signal-to-noise ratio (SNR) may denote a ratio of signal power to noise power associated with a communication link and may likewise be used for determining link quality. In some embodiments, expressions such as CandidateRelay i, SNR i, Speed i, and Load i may represent per-relay candidateentries and corresponding metrics maintained in a candidate list for relay selection processing.
[0112] At step 410, the RL agent 318 of the remote UE 306 may choose a best route for sidelink relay communication based on the candidate list. In an embodiment, the RL agent 318 of the remote UE 306 forms a state S from environment data such as candidate relays, link metrics, etc. Further, the RL agent 318 choose an action such as connect to the intermediate relay UE 308, and if the intermediate relay UE 308 is out-of-coverage, connect with anchor relay UE 310. In an example, the RL agent may choose the intermediate relay UE 308 (IntRelay) and the anchor relay UE 310 (AncRelay) for the sidelink relay communication.
[0113] At step 412, the remote UE 306 initiates a sidelink attachment with the intermediate relay UE 308. The remote UE 306 may transmit a PC5 RRCSetupRequest (Be my Relay) towards the intermediate relay UE 308 over the PC5 interface. The RRCSetupRequest may include a “multi-hop route ID” if a relay chain is being set up. In an embodiment, the L2 U2N remote UE 306 sends the first RRC message (i.e., RRCSetupRequest) for its connection establishment with gNB 316 via the L2 U2N intermediate relay UE 308, using a specified PC5 Relay REC channel configuration. In an embodiment, RRC IDLE may denote a Radio Resource Control state in which no active RRC connection is maintained with the network, RRC INACTIVE may denote a state in which an RRC context is retained without active data transfer, and RRC CONNECTED may denote a state in which the UE maintains an active RRC connection with the network. Thus, when a relay UE receives a forwarded request while in RRC IDLE or RRC INACTIVE, the relay UE may first resume or establish network-side connectivity before forwarding subsequent signaling associated with the remote UE.
[0114] At step 414, the intermediate relay UE 308 may check coverage such as whether the intermediate relay UE 308 is out-of-coverage of the network 106. If the intermediate relay UE 308 is in coverage, it sends SidelinkUEInformationNR to gNB-DU, embedding a new field “RemoteUE multi-hop request” with an ID. In anembodiment, a UE capable of NR sidelink operation that is in RRC CONNECTED may initiate the SidelinkUEInformationNR to report the Destination Layer-2 ID and QoS profile(s) associated with its interested service(s) that sidelink DRX is applied, for NR sidelink groupcast or broadcast reception.
[0115] If the intermediate relay UE 308 is out-of-coverage of the network 106, at step 416, the intermediate relay UE 308 may send a PC5 RRCSetupRequest (UE2 attach procedure to the anchor relay UE 310 for the intermediate relay UE 308 attachment over the PC5 interface. The UE2 may be the intermediate relay UE 308 when the intermediate relay UE 308 is out-of-coverage in the network 106. The UE2 attach an attachment procedure of an intermediate relay UE to an upstream relay UE or to the network, such that the intermediate relay UE obtains relay-assisted connectivity for forwarding signaling and / or data associated with a downstream remote UE.
[0116] At step 418, the anchor relay UE 310 may send a Uu SidelinkUEInformationNR message (UE2 attach) to the gNB-DU 316 via the Uu interface for attaching the intermediate relay UE 308 to the network 106. In an embodiment, the U2N Relay UE withholds the received RRC message and sends the SidelinkUEInformationNR message to the gNB-DU. Before that, if the U2N Relay UE is in RRC IDLE / RRC INACTIVE state, it should trigger the RRC establishment / resume procedure to enter RRC CONNECTED state upon reception of the RRC message.
[0117] At step 420, the gNB-DU 316 send an Fl UL RRC Transfer message (UE2=IntRelay) to the gNB-CU 314 over the Fl interface. The gNB-DU 316 packages the intermediate relay UE’s 308 RRCSetupRequest into the UL RRC Message Transfer containing a “Sidelink Indication,” “Relay ID,” “intermediate relay UE ID.” In an embodiment, the gNB-DU sends the UL RRC MESSAGE TRANSFER message of the U2N Relay UE by encapsulating the SidelinkUEInformationNR message to gNB-CU, and the gNB-CU allocates the local ID of U2N Remote UE. The purpose of the Initial UL RRC Message Transferprocedure is to transfer the initial RRC message to the gNB-CU. The procedure uses UE-associated signalling. The gNB-DU initiates the procedure by sending a UL RRC message transfer message. When the gNB-DU has received from the radio interface an RRC message to which a UE-associated logical Fl -connection for the UE exists, the gNB-DU shall send the UL RRC MESSAGE TRANSFER message to the gNB-CU including the RRC message as a RRC-Container IE.
[0118] At step 422, the gNB-CU 314 send a Fl UE context setup (for IntRelay) message to the gNB-DU 316 for the intermediate relay UE 308. The gNB-CU 314 creates a context for the intermediate relay UE 308, referencing the anchor relay UE 310 context. The anchor relay UE 310 may be a relay-capable User Equipment (UE) that maintains direct connectivity with a gNodeB (gNB) over a Uu interface and forwards signaling and / or data for one or more downstream UEs over a PC5 interface. In a multi -hop relay chain, the anchor relay UE may act as a network-side relay endpoint between the network and one or more intermediate relay UEs or a remote UE. In an embodiment, the gNB-CU sends the UE CONTEXT SETUP REQUEST message to establish the U2N Remote UE context in the gNB-DU. Such message may request the configuration of PC5 Relay RLC channels for the transmission of U2N intermediate relay UE’s SRB2 and DRBs and may also encapsulate the SecurityModeCommand message. In an embodiment, the purpose of the UE Context Setup procedure is to establish the UE Context including, among others, SRB, DRB, BH RLC channel, Uu Relay RLC channel, PC5 Relay RLC channel, and SL DRB configuration. The procedure uses UE-associated signalling. The gNB-CU initiates the procedure by sending UE CONTEXT SETUP REQUEST message to the gNB-DU. If the gNB-DU succeeds to establish the UE context, it replies to the gNB-CU with UE CONTEXT SETUP RESPONSE.
[0119] At step 424, the gNB-DU 316 may send a RRC Reconfiguration message (UE2) to the anchor relay UE 310. In an embodiment, the gNB-DU sends the RRCReconfiguration message to the U2N Relay UE to configure the local ID of the U2N intermediate relay UE, the Uu Relay RLC channel(s) configuration and bearer mapping for relaying of U2N intermediate relay UE’s.
[0120] At step 426, the anchor relay UE 310 send a PC5 RRC setup complete message to the intermediate relay UE 308 corresponding to the successful sidelink attachment of the intermediate relay UE 308 with the network 106.
[0121] At step 428, the intermediate relay UE 308 is recognized by the network 106, and the user-plane data may flow between the intermediate relay UE 308 and the gNB-CU 314 of the network 106 through the anchor relay UE 310.
[0122] At step 430, the remote UE 306 transmit the SidelinkUEInformationNR (Remote UE attach) message to the intermediate relay UE 308, initiating the remote UE 306 sidelink relay procedure.
[0123] At step 432, the intermediate relay UE 308 forwards the SidelinkUEInformationNR (remote UE wants attach) message to the anchor relay UE 310, indicating that the remote UE 306 wants to attach to the network 106.
[0124] At step 434, the anchor relay UE 310 further forward the Uu SidelinkUEInformationNR (Remote UE) message to the gNB-DU 316 similarly as explained in step 418.
[0125] At step 436, the gNB-DU 316 send the Fl UL RRC Transfer (Remote UE Setup) message to the gNB-CU 314. The gNB-DU 316 packages the remote UE’s 306 RRCSetupRequest into the UL RRC Message Transfer containing a “Sidelink Indication,” “Relay ID,” “Remote UE ID.”
[0126] At step 438, the gNB-CU 314 send a Fl UE context modification (Remote UE L2 path) message to the gNB-DU 316 for the remote UE 306 over the Fl interface. The gNB-CU 314 creates a context for the remote relay UE 306, referencing the anchor relay UE 310 context. In an embodiment, the gNB-CU 314 sends the UE context modification request message of the U2N intermediate relay UE to gNB-DU. Such message may request the establishment of Uu Relay RLC channel(s) for the transmission of U2N remote UE’s 306. The purpose of the UE context modification procedure is to modify the established UE Context, e.g.,establishing, modifying and releasing radio resources or sidelink resources. This procedure is also used to command the gNB-DU to stop data transmission for the UE for mobility. The procedure uses UE-associated signalling. Upon reception of the UE context modification request message, the gNB-DU shall perform the modifications, and if successful reports the update in the UE context modification response message.
[0127] At step 440, the gNB-DU 316 may send a RRC Reconfiguration (Remote UE) message to the anchor relay UE 310. In an embodiment, the gNB-DU sends the RRCReconfiguration message to the U2N Relay UE to configure the local ID of the U2N remote UE, the Uu Relay RLC channel(s) configuration and bearer mapping for relaying of U2N remote UE’s.
[0128] At step 442, the anchor relay UE 310 send a PC5 Reconfiguration message to the intermediate relay UE 308 over the PC5 interface, if the sidelink relay is multi-hop such as remote UE 306 to intermediate relay UE 308 to anchor relay UE 310 which has two hops before the remote UE 306 may communicate with the network 106.
[0129] At step 444, the anchor relay UE 310 may transmit a PC5 RRC setup request to the remote UE 306 for establishing a communication channel between the remote UE 306 and the gNB-DU 314 via the intermediate relay UE 308 and the anchor relay UE 310. In an embodiment, the gNB-DU sends the RRCSetup message to the U2N remote UE via the U2N anchor relay UE.
[0130] In an embodiment, the gNB-CU configures the U2N anchor relay UE with PC5 Relay RLC channel, Uu Relay RLC channel and bearer mapping for relaying of U2N remote UE’s SRB1. According to the configuration from gNB-CU, the U2N anchor relay UE establishes a PC5 Relay RLC channel for relaying of U2N remote UE’ s SRB 1 over PC5 interface and establishes a Uu Relay RLC channel for relaying of U2N remote UE’s SRB1 towards gNB-DU if not configured yet, at step 446, the remote UE 306 transmit the RRC setup complete message towards the gNB-DU 314 via the anchor relay UE 310 corresponding to the successful sidelinkattachment of the remote UE 306. In an embodiment, the U2N remote UE sends the RRCSetupComplete message to the gNB-DU via the U2N anchor relay UE.
[0131] Upon successful setup of sidelink relay communication between the remote UE 306, the intermediate UE 308, and the anchor relay UE 310, at step 448, the remote UE 306 may start transmitting data (PC5 data) towards the intermediate relay UE 308 via the PC5 interface. The data may be the uplink data meant for the gNB-DU 316 of the network 106.
[0132] At step 450, the intermediate relay UE 308 may further transmit the data (PC5 data) to the anchor relay UE 310 via the PC5 interface.
[0133] At step 452, the anchor relay UE 310 may further transmit the Uu Uplink (UL) data (Packet Data Convergence Protocol (PDCP) e2e) to the gNB-DU 314 over the Uu interface. In an embodiment, ‘PDCP e2e’ denotes end-to-end Packet Data Convergence Protocol forwarding or transmission between the remote UE and the gNB across the multi-hop relay chain.
[0134] At step 454, the gNB-DU 314 may transmit Uu UL data corresponding to the data towards the anchor relay UE 310 over the Uu interface. The data may be meant for the remote UE 306.
[0135] At step 456, the anchor relay UE 310 may further transmit the downlink data (PC5 DL) to the intermediate relay UE 308 over the PC5 interface.
[0136] At step 458, the intermediate relay UE 308 may further transmit the downlink data (PC5 DL) to the remote UE 306 via the PC5 interface.
[0137] The RL agent 318 of the remote UE 306 observes one or more network parameters associated with the sidelink relay communication. The one or more network parameters may be throughput, latency, packet success, etc. Further, the RL agent 318 evaluate the Quality of Service (QoS) of the data transmission from step 448 to step 458. Further, the RL agent 318 calculate a reward based on the oneor more network parameters. At step 460, the RL agent 318 may then determine that QoS is equal to more than the reward.
[0138] At step 462, the RL agent 318 may update the local RL model and the quality policy (Q-value / policy) based on the calculated reward and the QoS. The RL agent 318 may learn from the data transmission success or failure to update the Quality policy and the local RL model. In some embodiments, the RL agents of the intermediate relay UE 308 and the anchor UE 310 may also update the RL model based on the immediate data transmission with either the remote UE 306 or the gNB-DU 316.
[0139] At step 464A, 464B, and 464C, the remote UE 306, the intermediate relay UE 308, and the anchor relay UE 310 may send the updated RL models (AO local) to the FL coordinator 312. In an embodiment, the remote UE 306, the intermediate relay UE 308, and the anchor relay UE 310 send the updated RL model periodically or on demand.
[0140] At step 466, the FL coordinator 312 aggregate the received updated RL models (FedAvg = > new O global) from the remote UE 306, the intermediate relay UE 308, and the anchor relay UE 310. The updated RL models aggregation may be represented as Oglobal <- FedAvg({ _local}).
[0141] At step 468A, 468B, and 468C, the aggregated RL model (Return improved policy) is then transmitted to the remote UE 306, the intermediate relay UE 308, and the anchor relay UE 310 so that new arriving UEs and untrained UEs benefit from collective experience.
[0142] At step 470, the remote UE 306 may determine better options than the current sidelink relay such as a new sidelink relay with improved coverage or if the current sidelink relay degrades.
[0143] At step 472, the RL agent 318 may re-evaluates and triggers a new multihop attach or local handover.
[0144] At step 474, the new sidelink relay route (IntRelay->AncRelay due to stable link) is established with minimal signalling downtime. In some embodiments, the new establishment of sidelink relays may be performed proactively by the RL agent 318 upon learning the sidelink relays trend and load patterns.
[0145] In some embodiments, RL agent 318 may display explainable Al logs for safety-critical systems. In an embodiment, the RL agent 318 may store a short log for each route decision such as “Chosen Relay X due to strongest expected reward from link stability and moderate load.” Further, the operators may query these logs.
[0146] In yet another embodiment, latest release introduced a single-hop Layer-2 UE-to-Network relay mechanism in NR. While single-hop relay effectively extends coverage for UEs that are immediately out of range of a gNB but within range of an in-coverage Relay UE, many real-world scenarios (e.g., deep rural deployments, disaster areas, search-and-rescue missions, or vehicular convoys) require multiple hops of sidelink relay to reach the network.
[0147] The present disclosure proposes an Enhanced Multi-Hop L2 U2N Relay, which builds upon single-hop procedures to support two or more relay hops in a backward-compatible manner, providing a comprehensive technical overview and outline of the new procedures, focusing on:• Multi-hop chain formation and coordinated configuration.• Topology awareness at the gNB-CU for robust, scalable relay.• Streamlined RRC procedures and minimal interface changes, especially on FL• Backward compatibility with existing single-hop relay implementations.
[0148] Single-hop relay enables coverage extension by allowing an in-coverage Relay UE to forward traffic from a Remote UE over PC5. However:• Range limitation: A single hop covers only the distance from the out- of-coverage UE to one in-coverage Relay UE. Some environments require multiple intermediate hops to reach coverage.• Reliability: A single-hop path might be disrupted if the Relay UE moves or fails; multi-hop can provide alternative paths or at least reconfigurable options.• Evolving use cases: Industrial loT, public safety, and remote coverage expansions increasingly demand multi-hop for robust connectivity.
[0149] Hence, multi-hop U2N relay is identified as a key Rel-19 feature to extend coverage and enhance reliability. The requirement is to:1. Extend the existing single-hop L2 relay architecture to support multi -hop.2. Maintain backward compatibility (do not break single-hop).3. Minimize impact on existing interfaces (notably Fl, Xn).4. Provide a foundation for future intelligent routing (though not mandated in the initial specification).
[0150] Layer-2 approach: As with single-hop, multi-hop relay remains an L2 forwarding concept. Each Relay UE terminates MAC / RLC for both the downstream PC5 link (toward the Remote UE) and the upstream link (which may be another PC5 link to an upstream Relay UE or a Uu link to the gNB).
[0151] End-to-end anchor: The gNB-CU is the anchor for the Remote UE’s RRC and user-plane termination. The multi-hop chain simply acts as a bridging mechanism at L2. Roles of Remote UE, Relay UE(s), and gNB-CU may be:1. Remote UE:o Out of direct coverage.o Discovers potential Relay UEs via sidelink discovery signals.o Initiates RRC connection setup (forwarded over PC5 hops) toward the gNB.2. Relay UE:o In coverage (directly or indirectly via another Relay UE).o Receives and forwards RRC signaling and data traffic.o Maintains two sets of RLC channels: one with the upstream side (another Relay UE or gNB) and one with the downstream side (another Relay UE or the Remote UE).3. gNB-CU:o Maintains an RRC context for each Remote UE, as well as control contexts for each Relay UE.o Allocates radio resources (via the gNB-DU) and configures the sidelink parameters.o Maintains a “topology map” of multi-hop chains to coordinate multi hop resource assignment and adaptation.
[0152] Some examples of multi-hop topology such as (Remote UE) < — PCS — > [Relay UE1] < — PC5 — > [Relay UE2 ] < — Uu — > (gNB) may include:• Relay UE2 is fully in coverage of the gNB (Uu interface).• Relay UE1 is out of direct coverage from gNB but in sidelink range of Relay UE2.• The Remote UE relies on Relay UE1 — Relay UE2 — gNB path.From the gNB’s perspective, it sees:o “UE2” as an in-coverage Relay UE with a normal RRC connection over Uu.o “UE1” as a remote device connected via UE2.o The final “Remote UE” as a remote device connected via UE1 (and transitively via UE2).
[0153] Some enhanced procedures for multi-hop relay may include:Current Single-Hop:• When a Remote UE initiates RRC setup (via the Relay UE), the gNB-CU configures the Relay UE with PC5 / Uu relay channels in several sequential steps (SRB1 first, followed by additional configurations for SRB2 and DRBs).Multi-Hop Challenge:• Cascading these steps over each hop can incur significant delay for the final Remote UE. Each hop might need a back-and-forth exchange before proceeding to the next hop.Proposal:• Use a “chain-level” bulk configuration procedure. When the gNB-CU learns (from the initial RRC Setup Request or from Relay UEs’ measurement reports / discovery info) that a Remote UE requires multiple hops, it prepares a unified configuration container.• This container includes all the required sidelink RLC configurations (PC5 link parameters, logical channel details, IDs, QoS, etc.) for each hop in the chain, plus any relevant Uu modifications for the in-coverage Relay UE.• The gNB-CU sends this container as part of an RRC Reconfigurationmessage to the final in-coverage Relay UE, which then distributes the relevant subparts to the next downstream Relay UE, and so on, until it reaches the Remote UE.Further, the benefits may include:• Reduced latency: Fewer RRC round trips.• Scalability: Allows 2, 3, or more hops without dramatically increasing setup time.• Implementation: The gNB-DU largely sees normal “UE Context Setup” for the in-coverage Relay UE, while the multi-hop specifics are contained in a pass-through container on RRC signalling.
[0154] To orchestrate bulk configuration, the gNB-CU must track the chain structure:Multi -Hop Context: For each Remote UE, the gNB-CU’ s control -plane maintains which Relay UEs are in the path. This includes an ordered list: [Remote UE] Relay UE1 Relay UE2 Relay UEn gNB.
[0155] Discovery: Relay UEs periodically broadcast or scan for discovery messages (PC5). This is consistent with the existing ProSe / discovery framework. Once a potential route is found, the information is sent upstream to the gNB-CU so it can build or update the chain context.
[0156] Maintenance: If any Relay UE fails, moves away, or becomes overloaded, the gNB-CU can adapt the chain or instruct the Remote UE to discover alternative routes.
[0157] Chain Identifier or Tag: The gNB-CU may assign an internal identifier (e.g., ChainlD) to each multi-hop path for ease of reference. This ID can be used in RRC messages to indicate chain membership.
[0158] Advantages may include:
[0159] Coordinated resource allocation: The gNB-CU can schedule resources (indirectly via the DU or via sidelink coordination) more effectively when it knows how many Remote UEs rely on each Relay UE.
[0160] Adaptation: Supports advanced features like route switching or partial chain reconfiguration if a better path becomes available.
[0161] Controlled Hops: The network can impose a max hop limit (e.g., 3 or 4) for performance, ensuring acceptable QoS / latency.
[0162] FIG. 5 illustrates an exemplary process flow for managing multi-hop relay chain in the network 106, in accordance with an embodiment of the present disclosure.
[0163] At step 502, the remote UE and the last relay UE may perform PC5 discovery and setup. In an embodiment, the remote UE may transmit or monitor sidelink discovery signals over a PC5 interface, and the last relay UE may detect the discovery signals and establish a NR PC5 unicast RRC connection with the remote UE, enabling the remote UE to identify the last relay UE as a relay-side access point for onward communication toward the network 106.
[0164] At step 504, the last relay UE and the intermediate relay UE may perform PC5 discovery and setup. In an embodiment, the last relay UE may discover the intermediate relay UE, or the intermediate relay UE may discover the last relay UE, and a corresponding PC5 link may be established between them, creating an additional relay hop for forwarding control-plane signaling and user-plane traffic between the remote UE and the network 106.
[0165] At step 506, the intermediate relay UE and the first relay UE may perform PC5 discovery and setup. In an embodiment, the first relay UE may be an incoverage relay UE having Uu connectivity with the network 106. Establishment of the PC5 link between the intermediate relay UE and the first relay UE may complete the relay-side multi-hop path from the remote UE toward the network-side relayendpoint. In an embodiment, an optional AI / ML-aided relay selection operation may be performed before, during, or after steps 502, 504, and 506. Such operation may optimize selection of one or more relay UEs or one or more configuration parameters for the multi-hop relay chain.
[0166] At step 508, the remote UE may transmit a RRCSetupRequest message, for example over SRB0 on PC5, to the last relay UE to initiate establishment of an end-to-end connection toward the network 106. In an embodiment, the RRCSetupRequest may represent an initial access request of the remote UE through the multi -hop relay chain.
[0167] At step 510, the last relay UE may forward the RRCSetupRequest toward the intermediate relay UE over the established PC5 link. In an embodiment, the last relay UE may relay the initial access signaling without terminating the end-to-end connection establishment procedure associated with the remote UE.
[0168] At step 512, the intermediate relay UE may forward the RRCSetupRequest toward the first relay UE over PC5. In an embodiment, the intermediate relay UE may act as an intermediate forwarding node in the multi-hop relay chain for delivering the remote UE access request to the in-coverage side of the relay path.
[0169] At step 514, the first relay UE may transmit a SidelinkUEInformationNR message to the gNB-DU over the Uu interface. In an embodiment, the SidelinkUEInformationNR message may indicate that a remote UE is requesting connection setup through the relay chain and may include an identifier or context associated with the remote UE.
[0170] At step 516, the gNB-DU may forward the SidelinkUEInformationNR message to the gNB-CU using a Fl UPLINK RRC MESSAGE TRANSFER procedure. In an embodiment, enabling the gNB-CU to become aware of the remote UE request through relay and to create or update a corresponding remote UE context.
[0171] At step 518, the gNB-CU may initiate relay bearer setup by transmitting a UE CONTEXT MODIFICATION REQUEST toward the gNB-DU for the first relay UE context. In an embodiment, the UE CONTEXT MODIFICATION REQUEST may configure a relay radio bearer for the remote UE, including a dedicated relay signaling channel for carrying remote UE RRC messages through the first relay UE.
[0172] At step 520, the gNB-DU may apply the relay bearer configuration and transmit a UE CONTEXT MODIFICATION RESPONSE to the gNB-CU. In an embodiment, confirming that the first relay UE has been configured for forwarding signaling associated with the remote UE.
[0173] At step 522, the gNB-CU may transmit a RRCReconfiguration message, via the gNB-DU, to configure Signaling Radio Bearer 1 (SRB1) across the multi -hop relay chain. In an embodiment, the RRCReconfiguration message may include one or more configuration parameters for corresponding PC5 relay RLC channels between the first relay UE and the intermediate relay UE and between the intermediate relay UE and the last relay UE. The RRCReconfiguration message may further include configuration information enabling the last relay UE to establish SRB1 toward the remote UE.
[0174] At step 524, the first relay UE may forward the RRCReconfiguration message, or a corresponding relevant portion thereof, to the intermediate relay UE over PC5. In an embodiment, the forwarded configuration may enable the intermediate relay UE to configure its corresponding relay-side signaling channel for SRB1.
[0175] At step 526, the intermediate relay UE may forward a corresponding relevant portion of the RRCReconfiguration message to the last relay UE over PC5. In an embodiment, the last relay UE may use the received configuration to set up a PC5 relay channel for SRB1 toward the remote UE.
[0176] At step 528, the last relay UE may transmit a RRCReconfigurationComplete message toward the intermediate relay UE. In an embodiment, the RRCReconfigurationComplete message may indicate that the last relay UE has successfully configured the PC5 link associated with the remote UE for SRB1.
[0177] At step 530, the intermediate relay UE may forward the RRCReconfigurationComplete message toward the first relay UE and / or may generate its own RRCReconfigurationComplete message indicating successful configuration of its corresponding relay-side link. In an embodiment, indicating that the relay-side SRB1 configuration has been successfully applied at the intermediate relay UE.
[0178] At step 532, the first relay UE may forward the one or more RRCReconfigurationComplete messages to the gNB-DU over Uu. In an embodiment, the forwarded completion messages may indicate that the multi-hop relay links for SRB1 have been established.
[0179] At step 534, the gNB-DU may forward the one or more RRCReconfigurationComplete messages to the gNB-CU using a Fl UPLINK RRC MESSAGE TRANSFER procedure. In an embodiment, receipt of the completion information at the gNB-CU may confirm successful establishment of SRB1 across the multi -hop relay chain.
[0180] At step 536, the gNB-DU may initiate a Fl INITIAL UL RRC MESSAGE TRANSFER procedure to deliver the buffered RRCSetupRequest of the remote UE to the gNB-CU as an initial uplink RRC message. In an embodiment, this may create or finalize a remote UE context at the gNB-CU using the established relay bearer.
[0181] At step 538, the gNB-CU may transmit a RRCSetup message for the remote UE toward the gNB-DU using a Fl DOWNLINK RRC MESSAGE TRANSFER procedure. In an embodiment, the RRCSetup message may correspond to a network-side response to the earlier RRCSetupRequest of the remote UE.
[0182] At step 540, the gNB-DU may deliver the RRCSetup message to the first relay UE over the Uu relay bearer. In an embodiment, the first relay UE may act as the in-coverage network-side relay endpoint for onward forwarding of the RRCSetup message.
[0183] At step 542, the first relay UE may forward the RRCSetup message to the intermediate relay UE over PC5. In an embodiment, the forwarding may preserve the end-to-end RRC setup procedure of the remote UE through the multi-hop relay chain.
[0184] At step 544, the intermediate relay UE may forward the RRCSetup message to the last relay UE over PC5. In an embodiment, the intermediate relay UE may continue relay-side forwarding of network-to-remote control-plane signaling.
[0185] At step 546, the last relay UE may forward the RRCSetup message to the remote UE over the PC5 interface. In an embodiment, receipt of the RRCSetup message may enable the remote UE to proceed with completion of RRC connection setup through the multi-hop relay chain.
[0186] At step 548, the remote UE may transmit a RRCSetupComplete message, including a Non-Access Stratum (NAS) message, toward the last relay UE. In an embodiment, the NAS message may correspond to a registration request, service request, or another core-network signaling message associated with admission of the remote UE.
[0187] At step 550, the last relay UE may forward the RRCSetupComplete message to the intermediate relay UE over PC5. In an embodiment, the last relay UE may forward the RRCSetupComplete message without terminating the end-to-end RRC / NAS signaling exchange associated with the remote UE.
[0188] At step 552, the intermediate relay UE may forward the RRCSetupComplete message to the first relay UE over PC5. In an embodiment, the intermediate relayUE may continue relay-side forwarding of the control-plane signaling associated with the remote UE.
[0189] At step 554, the first relay UE may forward the RRCSetupComplete message to the gNB-DU over the Uu interface. In an embodiment, the first relay UE may utilize the previously established relay bearer for forwarding the RRCSetupComplete message and the included NAS message.
[0190] At step 556, the gNB-DU may forward the RRCSetupComplete message to the gNB-CU through a Fl UPLINK RRC MESSAGE TRANSFER procedure. In an embodiment, receipt of the RRCSetupComplete message at the gNB-CU may indicate successful completion of the initial RRC setup phase for the remote UE through the multi -hop relay chain.
[0191] At step 558, the gNB-CU may transmit an INITIAL UE MESSAGE toward the AMF. In an embodiment, the INITIAL UE MESSAGE may carry the NAS message received from the remote UE and may initiate a corresponding corenetwork admission procedure for the remote UE.
[0192] At step 560, the AMF may transmit an INITIAL CONTEXT SETUP REQUEST toward the gNB-CU. In an embodiment, the INITIAL CONTEXT SETUP REQUEST may provide security context information and one or more bearer-establishment parameters associated with the remote UE.
[0193] At step 562, the gNB-CU may transmit a SecurityModeCommand toward the gNB-DU for delivery to the remote UE. In an embodiment, the SecurityModeCommand may initiate activation of access-stratum security for the remote UE while preserving the multi-hop relay chain as the signaling path.
[0194] At step 564, the gNB-DU may forward the SecurityModeCommand to the first relay UE over the Uu relay bearer. In an embodiment, the first relay UE may act as the in-coverage relay endpoint for onward transmission of the security-related signaling.
[0195] At step 566, the first relay UE may forward the SecurityModeCommand to the intermediate relay UE over PC5. In an embodiment, the first relay UE may forward the received security signaling in accordance with the previously established relay configuration.
[0196] At step 568, the intermediate relay UE may forward the SecurityModeCommand to the last relay UE over PC5. In an embodiment, this forwarding may continue security signaling toward the remote UE through the multi-hop relay chain.
[0197] At step 570, the last relay UE may forward the SecurityModeCommand to the remote UE over the PC5 interface. In an embodiment, receipt of the SecurityModeCommand may enable the remote UE to activate one or more security parameters associated with the connection established through relay.
[0198] At step 572, the remote UE may transmit a SecurityModeComplete message toward the last relay UE. In an embodiment, the SecurityModeComplete message may indicate successful application of the security configuration at the remote UE.
[0199] At step 574, the last relay UE may forward the SecurityModeComplete message to the intermediate relay UE over PC5. In an embodiment, the last relay UE may continue relay-side forwarding of the security completion signaling associated with the remote UE.
[0200] At step 576, the intermediate relay UE may forward the SecurityModeComplete message to the first relay UE over PC5. In an embodiment, the intermediate relay UE may act as an intermediate forwarding node for completion of the access-stratum security procedure.
[0201] At step 578, the first relay UE may forward the SecurityModeComplete message to the gNB-DU over the Uu interface. In an embodiment, this forwarding may indicate to the network side that the remote UE has successfully completed security activation through the multi-hop relay chain.
[0202] At step 580, the gNB-DU may forward the SecurityModeComplete message to the gNB-CU through a Fl UPLINK RRC MESSAGE TRANSFER procedure. In an embodiment, receipt of the SecurityModeComplete message at the gNB-CU may complete the access-stratum security stage for the remote UE.
[0203] At step 582, the gNB-CU may transmit a further RRCReconfiguration message for configuring user-plane bearers for the remote UE. In an embodiment, the further RRCReconfiguration message may include configuration for SRB2, if required, and one or more Data Radio Bearers (DRBs), as well as one or more relayspecific bearer parameters associated with the multi-hop relay chain.
[0204] At step 584, the first relay UE may receive and forward the further RRCReconfiguration message toward the intermediate relay UE over PC5. In an embodiment, the first relay UE may use the previously established relay-side channels and context information to support forwarding of the bearer-configuration message.
[0205] At step 586, the intermediate relay UE may forward the further RRCReconfiguration message to the last relay UE over PC5. In an embodiment, the intermediate relay UE may further apply one or more corresponding bearer-related relay parameters associated with its relay hop.
[0206] At step 588, the last relay UE may forward the further RRCReconfiguration message to the remote UE over PC5. In an embodiment, receipt of this message may enable the remote UE to configure SRB2, if required, and the one or more DRBs for user-plane communication through the multi-hop relay chain.
[0207] At step 590, the remote UE may transmit a RRCReconfigurationComplete message toward the last relay UE indicating successful application of the further bearer configuration. In an embodiment, the RRCReconfigurationComplete message may confirm setup of SRB2 and / or the one or more DRBs at the remote UE side.
[0208] At step 592, the last relay UE may forward the RRCReconfigurationComplete message to the intermediate relay UE over PC5. In an embodiment, the forwarding may indicate successful completion of the bearer configuration at the remote UE side.
[0209] At step 594, the intermediate relay UE may forward the RRCReconfigurationComplete message to the first relay UE over PC5. In an embodiment, the intermediate relay UE may continue relay-side forwarding of bearer-completion signaling toward the network.
[0210] At step 596, the first relay UE may forward the RRCReconfigurationComplete message to the gNB-DU over Uu. In an embodiment, the forwarding may indicate that the remote UE-side bearer configuration has been successfully completed across the multi-hop relay chain.
[0211] At step 597, the gNB-DU may receive the forwarded RRCReconfigurationComplete message from the first relay UE. In an embodiment, the gNB-DU may prepare the received completion message for onward transfer to the gNB-CU using an uplink RRC message transfer procedure.
[0212] At step 598, the gNB-DU may forward the RRCReconfigurationComplete message to the gNB-CU through a Fl UPLINK RRC MESSAGE TRANSFER procedure. In an embodiment, receipt of the RRCReconfigurationComplete message at the gNB-CU may indicate successful establishment of SRB2 and the one or more DRBs for the remote UE through the multi-hop relay chain.
[0213] At step 599, the gNB-CU may transmit an INITIAL CONTEXT SETUP RESPONSE to the AMF. In an embodiment, the INITIAL CONTEXT SETUP RESPONSE may indicate that the remote UE RRC connection, security procedures, and bearer establishment procedures have been successfully completed through the multi-hop relay chain. The remote UE may operate in a connected state through the last relay UE, the intermediate relay UE, and the first relay UE, with end-to-end signaling and data communication enabled over the multi-hop relay chain.
[0214] In an embodiment, after completion of step 599, an optional AI / ML-based optimization operation may be performed. Such optimization may include collecting one or more performance measurements from the relay UEs and the remote UE, updating one or more machine learning models, refining relay parameters, or adjusting route-selection behavior for subsequent operation of the multi-hop relay chain. Such optimization may remain optional and may not alter backward compatibility of the baseline relay procedure.
[0215] FIG. 6 illustrates an exemplary process flow for managing multi-hop relay chain in the network 106, in accordance with an embodiment of the present disclosure.
[0216] At step 602, the remote UE and the last relay UE may perform discovery and PC5 link setup. In an embodiment, the remote UE may transmit or monitor sidelink discovery signals over a PC5 interface, and the last relay UE may detect such discovery signals and establish a NR PC5 unicast RRC connection with the remote UE, enabling the remote UE to identify the last relay UE as a relay-side access point for onward communication toward the network 106.
[0217] In an embodiment, an optional AI / ML-aided relay selection operation may be performed after step 602 or in parallel with discovery and setup. Such operation may use one or more relay metrics, route-performance indicators, or learned optimization parameters to select one or more relay UEs and / or configuration parameters for the multi-hop relay chain.
[0218] At step 604, the remote UE may transmit a RRCSetupRequest message to the last relay UE over the PC5 interface. In an embodiment, the RRCSetupRequest message may be transmitted over SRB0 and may indicate that the remote UE seeks establishment of an end-to-end connection toward the network 106 through the multi-hop relay chain.
[0219] At step 606, the last relay UE may forward the RRCSetupRequest message toward the intermediate relay UE over the established PC5 link. In an embodiment,the last relay UE may relay the request without terminating the remote UE’s end-to-end RRC establishment procedure.
[0220] At step 608, the intermediate relay UE may forward the RRCSetupRequest message toward the first relay UE over PC5. In an embodiment, the intermediate relay UE may function as a forwarding relay for delivering the remote UE access request to an in-coverage relay UE having Uu connectivity with the network 106.
[0221] At step 610, the first relay UE may transmit a SidelinkUEInformationNR message to the gNB-DU over the Uu interface. In an embodiment, the SidelinkUEInformationNR message may indicate the presence of the remote UE requesting connection setup through the multi-hop relay chain and may include one or more identifiers or context parameters associated with the remote UE.
[0222] At step 612, the gNB-DU may forward the SidelinkUEInformationNR message to the gNB-CU using a Fl UL RRC MESSAGE TRANSFER procedure. In an embodiment, this step may make the gNB-CU aware of the remote UE request through relay and may enable creation or updating of a corresponding remote UE context.
[0223] At step 614, the gNB-CU may initiate relay bearer setup by transmitting a UE CONTEXT MODIFICATION REQUEST toward the gNB-DU for the first relay UE context. In an embodiment, the UE CONTEXT MODIFICATION REQUEST may configure a relay radio bearer for the remote UE, including a signaling channel for carrying remote UE RRC messages through the first relay UE.
[0224] At step 616, the gNB-DU may apply the relay bearer configuration and transmit a UE CONTEXT MODIFICATION RESPONSE to the gNB-CU. In an embodiment, this response may confirm that the first relay UE has been configured to forward signaling associated with the remote UE.
[0225] At step 618, the gNB-CU may transmit a RRCReconfiguration message, via the gNB-DU, to configure Signaling Radio Bearer 1 (SRB1) across the multi -hoprelay chain. In an embodiment, the RRCReconfiguration message may include one or more parameters for setting up corresponding PC5 relay RLC channels between the first relay UE and the intermediate relay UE, and between the intermediate relay UE and the last relay UE, for SRB1 establishment toward the remote UE.
[0226] At step 620, the first relay UE may forward the RRCReconfiguration message, or a relevant portion thereof, to the intermediate relay UE over PC5. In an embodiment, the forwarded configuration may enable the intermediate relay UE to configure its corresponding relay-side signaling channel.
[0227] At step 622, the intermediate relay UE may forward a corresponding relevant portion of the RRCReconfiguration message to the last relay UE over PC5. In an embodiment, the last relay UE may use the received configuration to establish a PC5 relay channel for SRB1 toward the remote UE.
[0228] At step 624, the first relay UE may apply a corresponding portion of the relay configuration for SRB1 on its side of the multi -hop relay chain. In an embodiment, this may include configuring signaling channels associated with the Uu-facing relay bearer and the downstream PC5 link toward the intermediate relay UE.
[0229] At step 626, the last relay UE may transmit a RRCReconfigurationComplete message toward the intermediate relay UE. In an embodiment, the message may indicate successful configuration of the PC5 link associated with the remote UE for SRB1.
[0230] At step 628, the intermediate relay UE may forward the RRCReconfigurationComplete message toward the first relay UE and / or may provide its own completion indication for the relay configuration. In an embodiment, the step may confirm successful application of the relay-side SRB 1 configuration at the intermediate relay UE.
[0231] At step 630, the first relay UE may forward the one or more RRCReconfigurationComplete messages to the gNB-DU over Uu. In an embodiment, the forwarded completion messages may indicate that the multi-hop relay links for SRB1 have been established.
[0232] At step 632, the gNB-DU may initiate a Fl INITIAL UL RRC MESSAGE TRANSFER procedure to deliver the buffered RRCSetupRequest of the remote UE to the gNB-CU as an initial uplink RRC message, establishing or finalizing a remote UE context at the gNB-CU using the relay bearer configured for the first relay UE.
[0233] At step 634, the gNB-CU may transmit a RRCSetup message for the remote UE toward the gNB-DU using a Fl DL RRC MESSAGE TRANSFER procedure. In an embodiment, the RRCSetup message may correspond to a network-side response to the earlier RRCSetupRequest of the remote UE.
[0234] At step 636, the gNB-DU may deliver the RRCSetup message to the first relay UE over the Uu relay bearer. In an embodiment, the first relay UE may act as the in-coverage network-side relay endpoint for onward forwarding of the RRCSetup message.
[0235] At step 638, the first relay UE may forward the RRCSetup message to the intermediate relay UE over PC5. In an embodiment, the forwarding may preserve the end-to-end RRC setup procedure of the remote UE through the multi-hop relay chain.
[0236] At step 640, the intermediate relay UE may forward the RRCSetup message to the last relay UE over PC5. In an embodiment, the intermediate relay UE may continue relay-side forwarding of network-to-remote control-plane signaling.
[0237] At step 642, the last relay UE may deliver the RRCSetup message to the remote UE over the PC5 interface. In an embodiment, receipt of the RRCSetup message may enable the remote UE to proceed with RRC connection completion through the multi -hop relay chain.
[0238] At step 644, the remote UE may transmit a RRCSetupComplete message, including a Non-Access Stratum (NAS) message, toward the last relay UE. In an embodiment, the NAS message may correspond to a registration request, service request, or another core-network signaling message associated with remote UE admission.
[0239] At step 646, the last relay UE may forward the RRCSetupComplete message to the intermediate relay UE over PC5. In an embodiment, the last relay UE may forward the message without terminating the end-to-end RRC / NAS signaling exchange associated with the remote UE.
[0240] At step 648, the intermediate relay UE may forward the RRCSetupComplete message to the first relay UE over PC5. In an embodiment, the intermediate relay UE may continue relay-side forwarding of the control-plane signaling associated with the remote UE.
[0241] At step 650, the first relay UE may forward the RRCSetupComplete message to the gNB-DU over the Uu interface. In an embodiment, the first relay UE may utilize the previously established relay bearer for forwarding the RRCSetupComplete message and the included NAS message.
[0242] At step 652, the gNB-CU may transmit an INITIAL UE MESSAGE toward the AMF. In an embodiment, the INITIAL UE MESSAGE may carry the NAS message received from the remote UE and may initiate a corresponding corenetwork admission procedure for the remote UE.
[0243] At step 654, the AMF may transmit an INITIAL CONTEXT SETUP REQUEST toward the gNB-CU. In an embodiment, the INITIAL CONTEXT SETUP REQUEST may provide security context information and one or more bearer-establishment parameters associated with the remote UE.
[0244] At step 656, the gNB-CU may transmit a SecurityModeCommand toward the gNB-DU for delivery to the remote UE. In an embodiment, theSecurity ModeCommand may initiate access-stratum security activation for the remote UE while preserving the multi-hop relay chain as the signaling path.
[0245] At step 658, the gNB-DU may forward the SecurityModeCommand to the first relay UE over the Uu relay bearer. In an embodiment, the first relay UE may act as the in-coverage relay endpoint for onward transmission of the security-related signaling.
[0246] At step 660, the first relay UE may forward the SecurityModeCommand to the intermediate relay UE over PC5. In an embodiment, the first relay UE may forward the received security signaling in accordance with the relay configuration previously applied.
[0247] At step 662, the intermediate relay UE may forward the SecurityModeCommand to the last relay UE over PC5. In an embodiment, the forwarding may continue security signaling toward the remote UE through the multi-hop relay chain.
[0248] At step 664, the last relay UE may forward the SecurityModeCommand to the remote UE over the PC5 interface. In an embodiment, receipt of the SecurityModeCommand may enable the remote UE to activate one or more security parameters associated with the connection established through relay.
[0249] At step 666, the remote UE may transmit a SecurityModeComplete message toward the last relay UE. In an embodiment, the SecurityModeComplete message may indicate successful application of the security configuration at the remote UE.
[0250] At step 668, the last relay UE may forward the SecurityModeComplete message to the intermediate relay UE over PC5. In an embodiment, the last relay UE may continue relay-side forwarding of the security completion signaling associated with the remote UE.
[0251] At step 670, the intermediate relay UE may forward the SecurityModeComplete message to the first relay UE over PC5. In an embodiment,the intermediate relay UE may act as an intermediate forwarding node for completion of the access-stratum security procedure.
[0252] At step 672, the first relay UE may forward the SecurityModeComplete message to the gNB-DU over the Uu interface. In an embodiment, the forwarding may indicate to the network side that the remote UE has successfully completed security activation through the multi-hop relay chain.
[0253] At step 674, the gNB-DU may forward the SecurityModeComplete message to the gNB-CU through a Fl UL RRC MESSAGE TRANSFER procedure. In an embodiment, receipt of the SecurityModeComplete message at the gNB-CU may complete the access-stratum security stage for the remote UE.
[0254] At step 676, the gNB-CU may transmit a further RRCReconfiguration message for configuring user-plane bearers for the remote UE. In an embodiment, the further RRCReconfiguration message may include configuration for SRB2, if required, and one or more Data Radio Bearers (DRBs), as well as one or more relayspecific bearer parameters associated with the multi-hop relay chain.
[0255] At step 678, the gNB-DU may deliver the further RRCReconfiguration message to the first relay UE over the Uu relay bearer. In an embodiment, the first relay UE may receive bearer-configuration signaling for onward transmission through the relay chain.
[0256] At step 680, the first relay UE may forward the further RRCReconfiguration message to the intermediate relay UE over PC5. In an embodiment, the first relay UE may use the previously established relay-side channels and context information to support forwarding of the bearer-configuration message.
[0257] At step 682, the intermediate relay UE may forward the further RRCReconfiguration message to the last relay UE over PC5. In an embodiment, the intermediate relay UE may further apply one or more corresponding bearer-related relay parameters associated with its relay hop.
[0258] At step 684, the last relay UE may forward the further RRCReconfiguration message to the remote UE over PC5. In an embodiment, receipt of the message may enable the remote UE to configure SRB2, if required, and one or more DRBs for user-plane communication through the multi-hop relay chain.
[0259] At step 686, the remote UE may transmit a RRCReconfigurationComplete message toward the last relay UE indicating successful application of the further bearer configuration. In an embodiment, the RRCReconfigurationComplete message may confirm setup of SRB2 and / or the one or more DRBs at the remote UE side.
[0260] At step 688, the last relay UE may forward the RRCReconfigurationComplete message to the intermediate relay UE over PC5. In an embodiment, the forwarding may indicate successful completion of bearer configuration at the remote UE side.
[0261] At step 690, the intermediate relay UE may forward the RRCReconfigurationComplete message to the first relay UE over PC5. In an embodiment, the intermediate relay UE may continue relay-side forwarding of bearer-completion signaling toward the network.
[0262] At step 692, the first relay UE may forward the RRCReconfigurationComplete message to the gNB-DU over the Uu interface. In an embodiment, the forwarding may indicate that the remote UE-side bearer configuration has been successfully completed across the multi-hop relay chain.
[0263] At step 694, the gNB-CU may transmit an INITIAL CONTEXT SETUP RESPONSE to the AMF. In an embodiment, the INITIAL CONTEXT SETUP RESPONSE may indicate that the remote UE RRC connection, security procedures, and bearer establishment procedures have been successfully completed through the multi-hop relay chain. Further, the remote UE may operate in a connected state through the last relay UE, the intermediate relay UE, and the first relay UE, withend-to-end signaling and data communication enabled over the multi-hop relay chain.
[0264] In an embodiment, after completion of step 694, an optional AI / ML-based optimization operation may be performed. Such optimization may include collecting one or more performance measurements from the relay UEs and the remote UE, updating one or more machine learning models, refining relay parameters, or adjusting route-selection behavior for subsequent operation of the multi-hop relay chain. Such optimization may remain optional and may not alter backward compatibility of the baseline relay procedure.
[0265] FIG. 7 illustrates an exemplary process flow for managing multi-hop relay chain in the network 106, in accordance with an embodiment of the present disclosure.
[0266] At step 702, an indication that a remote User Equipment (UE) requests access to the network through one or more relay UEs is received. At least one of a RRC setup request, an initial access request message, and a relay request information associated with the remote UE is received through the one or more relay UEs. In an exemplary embodiment, the received indication may correspond to an access-related message initiated by the remote UE over a PC5 interface and forwarded through the one or more relay UEs toward the network node. The indication may further include one or more identifiers, relay context parameters, or route-related information associated with the remote UE, enabling the network node to create or update a remote UE context for relay-assisted access.
[0267] At step 704, a multi-hop relay chain including at least one relay UE between the remote UE and the network node is determined based on the received indication. A machine learning model to at least one of signal quality, relay load, throughput, latency, mobility condition, coverage condition, and quality-of-service requirement associated with the one or more relay UEs is applied to optimize the determination of the multi-hop relay chain. In an exemplary embodiment, determination of the multi-hop relay chain may include identifying one or more candidate relay UEs,selecting an in-coverage relay UE for connectivity with the network 106, and determining an ordered forwarding path between the remote UE and the network node. The machine learning model may process one or more relay-related parameters to select a multi-hop relay chain expected to provide improved coverage extension, throughput, latency performance, route stability, or quality-of-service for the remote UE.
[0268] In an embodiment, the machine learning model is transmitted to the one or more relay UEs for local update. Model update information is received from the one or more relay UEs. The model update information is aggregated to generate an updated machine learning model. The updated machine learning model is used for subsequent determination of the multi-hop relay chain. In an exemplary embodiment, the machine learning model may be distributed by the network node to the one or more relay UEs for local update using locally observed measurements, route outcomes, or traffic conditions. The model update information received from the one or more relay UEs may include updated model parameters, weights, or gradients, and aggregation of the model update information may enable the network node to generate the updated machine learning model for subsequent relay-chain determination events.
[0269] In some embodiments, topology context information identifying an ordered sequence of the remote UE and the at least one relay UE is determined. A multihop relay chain identifier is assigned to the multi-hop relay chain. In an exemplary embodiment, the topology context information may represent a topology map of the multi-hop relay chain identifying an ordered sequence of the remote UE and the at least one relay UE between the remote UE and the network node. The topology context information may further identify upstream and downstream relationships between adjacent relay UEs, enabling coordinated forwarding, hop-wise configuration, and subsequent path update or reconfiguration of the multi -hop relay chain.
[0270] At step 706, a multi-hop configuration container associated with the multihop relay chain is generated. The multi-hop configuration container includes at least one of multi-hop relay chain identifier, remote UE information, hop-wise relay configuration information, and bearer configuration for signaling and data communication associated with the remote UE. In an exemplary embodiment, the multi-hop configuration container may correspond to a chain-level configuration structure for coordinated setup of the multi-hop relay chain. The multi-hop configuration container may further include one or more of per-hop PC5 configuration parameters, logical channel information, radio link control configuration, relay-side forwarding parameters, quality-of-service parameters, identifier information associated with the remote UE, or Uu-side bearer adjustment associated with an in-coverage relay UE.
[0271] At step 708, a Radio Resource Control (RRC) reconfiguration message including the multi-hop configuration container to the remote UE and the one or more relay UEs is transmitted to establish Signaling Radio Bearer (SRB) across the multi-hop relay chain. Each of the hop-wise relay configuration information from the multi-hop configuration container is applied to the corresponding relay UEs based on the topology context information of the multi-hop relay chain. In an exemplary embodiment, the transmitted RRC reconfiguration message may be delivered toward an in-coverage relay UE associated with the multi -hop relay chain, and corresponding portions of the multi-hop configuration container may be forwarded and applied by the one or more relay UEs according to their ordered positions in the topology context information. The hop-wise relay configuration information may be progressively applied across the multi-hop relay chain to establish SRB1 between the remote UE and the network node over one or more PC5 segments and a Uu segment.
[0272] At step 710, an RRC setup complete message including a Non-Access Stratum (NAS) message is received from the remote UE through the multi-hop relay chain. In an exemplary embodiment, the received RRC setup complete message may carry a Non-Access Stratum message associated with a core-networkprocedure of the remote UE, including at least one of registration, service request, authentication, or context setup. Receipt of the RRC setup complete message through the multi-hop relay chain may indicate successful completion of an initial RRC setup phase for the remote UE through relay -assisted access.
[0273] At step 712, a security control message for the remote UE is transmitted through the multi-hop relay chain. In an exemplary embodiment, the transmitted security control message may include a Security Mode Command or another access-stratum security-related message associated with activation of security procedures for the remote UE. The one or more relay UEs may forward the security control message through the multi-hop relay chain and may further forward a corresponding security completion message from the remote UE toward the network node.
[0274] At step 714, one or more data radio bearers for the remote UE is established over the multi-hop relay chain. The one or more data radio bearers provide controlplane signaling and user-plane communication between the remote UE and the network node. In an exemplary embodiment, establishment of the one or more data radio bearers may be performed after establishment of the Signaling Radio Bearer and completion of security activation for the remote UE. The network node may transmit one or more further RRC reconfiguration messages through the multi-hop relay chain to establish SRB2, if required, and one or more DRBs for the remote UE. Bearer-related parameters for the one or more data radio bearers may be preincluded in the multi-hop configuration container, reducing sequential per-hop bearer renegotiation and enabling rapid activation of user-plane communication for the remote UE over the multi-hop relay chain.
[0275] In an embodiment, relay chain selection information associated with determination of the multi-hop relay chain is generated. The relay chain selection information includes at least one of an identity of at least one selected relay UE, an ordered position of the at least one selected relay UE in the multi-hop relay chain, a chain identifier, or one or more relay metrics used for determination of the multi-hop relay chain. In an exemplary embodiment, the relay chain selection information may represent structured information associated with a selected relay path and may be stored, logged, transmitted, or reused for subsequent reconfiguration, performance analysis, route adaptation, or machine-learning-assisted optimization. The relay chain selection information may indicate which relay UEs were selected, ordered positions of the selected relay UEs in the multi-hop relay chain, a corresponding chain identifier, and one or more relay metrics contributing to the selected relay path.
[0276] FIG. 8 illustrates an exemplary computer system 800 in which or with which embodiments of the present disclosure may be implemented. As shown in FIG. 8, the computer system 800 may include an external storage device 810, a bus 820, a main memory 830, a read-only memory 840, a mass storage device 850, communication port(s) 860, and a processor 870. A person skilled in the art will appreciate that the computer system 800 may include more than one processor and communication ports. The processor 870 may include various modules associated with embodiments of the present disclosure. The communication port(s) 860 may be any of an RS-232 port for use with a modem-based dialup connection, a 10 / 100 Ethernet port, a Gigabit or 10 Gigabit port using copper or fiber, a serial port, a parallel port, or other existing or future ports. The communication port(s) 860 may be chosen depending on a network, such a Local Area Network (LAN), Wide Area Network (WAN), or any network to which the computer system 800 connects.
[0277] The main memory 830 may be a Random Access Memory (RAM), or any other dynamic storage device commonly known in the art. The read-only memory 840 may be any static storage device(s) e.g., but not limited to, a Programmable Read Only Memory (PROM) chips for storing static information e.g., start-up or Basic Input / Output System (BIOS) instructions for the processor 870. The mass storage device 850 may be any current or future mass storage solution, which can be used to store information and / or instructions. Exemplary mass storage device 850 includes, but is not limited to, Parallel Advanced Technology Attachment (PATA) or Serial Advanced Technology Attachment (SATA) hard disk drives orsolid-state drives (internal or external, e.g., having Universal Serial Bus (USB) and / or Firewire interfaces), one or more optical discs, Redundant Array of Independent Disks (RAID) storage, e.g. an array of disks.
[0278] The bus 820 communicatively couples the processor 870 with the other memory, storage, and communication blocks. The bus 820 may be, e.g. a Peripheral Component Interconnect (PCI) / PCI Extended (PCI-X) bus, Small Computer System Interface (SCSI), Universal Serial Bus (USB), or the like, for connecting expansion cards, drives, and other subsystems as well as other buses, such a front side bus (FSB), which connects the processor 870 to the computer system 800.
[0279] Optionally, operator and administrative interfaces, e.g. a display, keyboard, joystick, and a cursor control device, may also be coupled to the bus 820 to support direct operator interaction with the computer system. Other operator and administrative interfaces can be provided through network connections connected through the communication port(s) 860. Components described above are meant only to exemplify various possibilities. In no way should the aforementioned exemplary computer system 800 limit the scope of the present disclosure.
[0280] In an embodiment, a method for Al-driven multi-hop real-time relay selection in 5GNR sidelink is disclosed. The UE (e.g., a remote UE, intermediate relay UE or anchor relay UE) retrieves an initial reinforcement learning (RL) policy for multi-hop relay decision from RL model which is downloaded from a federated learning (FL) coordinator (i.e., from gNB). Each UE runs a reinforcement learning agent that discover candidate relays, pick optimal multi-hop routes / selects relay paths, evaluates sidelink metrics and performs adaptive scheduling. The federated learning server or edge node aggregates updated model parameters from multiple UEs, trains a global Al model, and distributes the refined model back to UEs for improved relay management.
[0281] In an embodiment, the present disclosure introduces a system that is not locked to a single relay hop and is able to chain multiple UEs to form a robust sidelink relay route. The RL agents operate on the UEs side to select sidelink relayroutes, resource blocks, and manage flows. Further, the present disclosure aggregates updated local RL models from many UEs resulting in a globally refined RL model, overcoming data scarcity. The present disclosure ensures operators may track the Al logic, and a fallback is available for uncertain conditions.
[0282] While the foregoing description describes various embodiments of the invention, other and further embodiments of the invention may be devised without departing from the basic scope thereof. The scope of the invention is determined by the claims that follow. The invention is not limited to the described embodiments, versions or examples, which are included to enable a person having ordinary skill in the art to make and use the invention when combined with information and knowledge available to the person having ordinary skill in the art.
[0283] The method and system of the present disclosure may be implemented in a number of ways. For example, the methods and systems of the present disclosure may be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware. The above-described order for the steps of the method is for illustration only, and the steps of the method of the present disclosure are not limited to the order specifically described above unless specifically stated otherwise. Further, in some embodiments, the present disclosure may also be embodied as programs recorded in a recording medium, the programs including machine-readable instructions for implementing the methods according to the present disclosure. Thus, the present disclosure also covers a recording medium storing a program for executing the method according to the present disclosure.
[0284] While considerable emphasis has been placed herein on the preferred embodiments, it will be appreciated that many embodiments can be made and that many changes can be made in the preferred embodiments without departing from the principles of the disclosure. These and other changes in the preferred embodiments of the disclosure will be apparent to those skilled in the art from the disclosure herein, whereby it is to be distinctly understood that the foregoingdescriptive matter is to be implemented merely as illustrative of the disclosure and not as a limitation.TECHNICAL ADVANTAGES
[0285] Intelligent Relay Selection: The present disclosure provides a method and a system that utilizes Artificial Intelligence (Al) models to select optimal relay User Equipments (UEs) based on multi-dimensional network parameters, improving decision accuracy over static or heuristic-based methods.
[0286] Dynamic Path Optimization: The present disclosure provides a method and a system that continuously adapts the multi-hop communication path in real-time, accounting for changing network conditions, user mobility, and traffic loads.
[0287] Enhanced Network Reliability: The present disclosure provides a method and a system that reduces the risk of link failure and communication disruption by proactively selecting stable relay nodes and reconfiguring paths as needed.
[0288] Extended Communication Coverage: The present disclosure provides a method and a system that enables communication beyond direct line-of-sight by leveraging intermediate UEs, thereby expanding the effective range of sidelink connectivity.
[0289] Learning-based Adaptability: The present disclosure provides a method and a system that incorporates continuous learning from historical and real-time data to refine relay decisions and improve future performance.
[0290] Reduced Resource Consumption: The present disclosure provides a method and a system that optimizes the number and roles of relays, minimizing redundant transmissions and preserving device energy and bandwidth resources.
Claims
CLAIMS1. A method (700) for managing multi-hop relay chain in a network (106), the method (700) comprising:receiving (702), by a network node (208), an indication that a remote User Equipment (UE) (302) requests access to the network (106) through one or more relay UEs;determining (704), by the network node (208), a multi-hop relay chain comprising at least one relay UE between the remote UE (302) and the network node (208) based on the received indication;generating (706), by the network node (208), a multi-hop configuration container associated with the multi-hop relay chain, wherein the multi-hop configuration container comprises at least one of multi-hop relay chain identifier, remote UE (302) information, hop-wise relay configuration information, and bearer configuration for signaling and data communication associated with the remote UE (302);transmitting (706), by the network node (208), a Radio Resource Control (RRC) reconfiguration message comprising the multi-hop configuration container to the remote UE (302) and the one or more relay UEs to establish Signaling Radio Bearer (SRB) across the multi-hop relay chain;receiving (708), by the network node (208), an RRC setup complete message comprising a Non-Access Stratum (NAS) message from the remote UE (302) through the multi-hop relay chain;transmitting (710), by the network node (208), a security control message for the remote UE (302) through the multi-hop relay chain; andestablishing (712), by the network node (208), one or more data radio bearers for the remote UE (302) over the multi-hop relay chain.
2. The method (700) as claimed in claim 1, wherein receiving the indication, comprising:receiving, by the network node (208), at least one of a RRC setup request, an initial access request message, and a relay request information associated with the remote UE (302) through the one or more relay UEs.
3. The method (700) as claimed in claim 1, wherein determining the multi-hop relay chain, comprising:applying, by the network node (208), a machine learning model to at least one of signal quality, relay load, throughput, latency, mobility condition, coverage condition, and quality-of-service requirement associated with the one or more relay UEs to optimize the determination of the multi-hop relay chain.
4. The method (700) as claimed in claim 1, wherein determining the multi-hop relay chain, comprising:determining, by the network node (208), topology context information identifying an ordered sequence of the remote UE (302) and the at least one relay UE; andassigning a multi-hop relay chain identifier to the multi-hop relay chain.
5. The method (700) as claimed in claim 1, wherein transmitting the RRC reconfiguration message, further comprising:applying each of the hop-wise relay configuration information from the multi-hop configuration container to the corresponding relay UEs based on the topology context information of the multi-hop relay chain.
6. The method (700) as claimed in claim 3, further comprising:transmitting, by the network node (208), the machine learning model to the one or more relay UEs for local update;receiving, by the network node (208), model update information from the one or more relay UEs;aggregating, by the network node (208), the model update information to generate an updated machine learning model; andusing, by the network node (208), the updated machine learning model for subsequent determination of the multi-hop relay chain.
7. The method (700) as claimed in claim 1, further comprising:generating, by the network node (208), relay chain selection information associated with determination of the multi-hop relay chain, wherein the relay chain selection information comprises at least one of an identity of at least one selected relay UE, an ordered position of the at least one selected relay UE in the multi-hop relay chain, a chain identifier, or one or more relay metrics used for determination of the multi-hop relay chain.
8. The method (700) as claimed in claim 1, wherein the one or more data radio bearers provide control-plane signaling and user-plane communication between the remote UE (302) and the network node (208).
9. A system (108) for managing multi-hop relay chain in a network (106), the system (108) comprising:a network node (208) configured to:receive an indication that a remote User Equipment (UE) (302) requests access to the network through one or more relay UEs;determine a multi-hop relay chain comprising at least one relay UE between the remote UE (302) and the network node based on the received indication;generate a multi-hop configuration container associated with the multi-hop relay chain, wherein the multi-hop configuration container comprises at least one of multi-hop relay chain identifier, remote UE information, hop-wise relay configuration information, and bearer configuration for signaling and data communication associated with the remote UE (302);transmit a Radio Resource Control (RRC) reconfiguration message comprising the multi-hop configuration container to the remote UE (302) and the one or more relay UEs to establish Signaling Radio Bearer (SRB) across the multi-hop relay chain;receive an RRC setup complete message comprising a Non-Access Stratum (NAS) message from the remote UE (302) through the multi-hop relay chain;transmit a security control message for the remote UE through the multi-hop relay chain; andestablish one or more data radio bearers for the remote UE (302) over the multi-hop relay chain.
10. The system (108) as claimed in claim 9, wherein the network node (208) is further configured to receive at least one of a RRC setup request, an initial access request message, and a relay request information associated with the remote UE (302) through the one or more relay UEs.
11. The system (108) as claimed in claim 9, wherein the network node (208) is further configured to apply a machine learning model to at least one of signal quality, relay load, throughput, latency, mobility condition, coverage condition, and quality-of-service requirement associated with the one or more relay UEs to optimize the determination of the multi-hop relay chain.
12. The system (108) as claimed in claim 9, wherein the network node (208) is further configured to:determine topology context information identifying an ordered sequence of the remote UE (302) and the at least one relay UE; andassign a multi-hop relay chain identifier to the multi-hop relay chain.
13. The system (108) as claimed in claim 9, wherein the network node (208) is further configured to apply each of the hop-wise relay configuration information from the multi-hop configuration container to the corresponding relay UEs based on the topology context information of the multi-hop relay chain.
14. The system (108) as claimed in claim 11, wherein the network node (208) is further configured to:transmit the machine learning model to the one or more relay UEs for local update;receive model update information from the one or more relay UEs;aggregate the model update information to generate an updated machine learning model; anduse the updated machine learning model for subsequent determination of the multi-hop relay chain.
15. The system (108) as claimed in claim 9, wherein the network node (208) is further configured to generate relay chain selection information associated with determination of the multi-hop relay chain, wherein the relay chain selection information comprises at least one of an identity of at least one selected relay UE, an ordered position of the at least one selected relay UE in the multi -hop relay chain, a chain identifier, or one or more relay metrics used for determination of the multihop relay chain.
16. The system (108) as claimed in claim 9, wherein the one or more data radio bearers provide control-plane signaling and user-plane communication between the remote UE (302) and the network node (208).
17. A computer program product comprising a non-transitory computer-readable medium comprising instructions that, when executed by one or more processors, cause the one or more processors to execute a method for managing multi-hop relay chain in a network (106), the method (700) comprising:receiving (702), by a network node (208), an indication that a remote User Equipment (UE) (302) requests access to the network (106) through one or more relay UEs;determining (704), by the network node (208), a multi-hop relay chain comprising at least one relay UE between the remote UE (302) and the network node (208) based on the received indication;generating (706), by the network node (208), a multi-hop configuration container associated with the multi-hop relay chain, wherein the multi-hop configuration container comprises at least one of multi-hop relay chain identifier, remote UE (302) information, hop-wise relay configuration information, and bearer configuration for signaling and data communication associated with the remote UE (302);transmitting (706), by the network node (208), a Radio Resource Control (RRC) reconfiguration message comprising the multi-hop configuration container to the remote UE (302) and the one or more relay UEs to establish Signaling Radio Bearer (SRB) across the multi-hop relay chain;receiving (708), by the network node (208), an RRC setup complete message comprising a Non-Access Stratum (NAS) message from the remote UE (302) through the multi-hop relay chain;transmitting (710), by the network node (208), a security control message for the remote UE (302) through the multi-hop relay chain; andestablishing (712), by the network node (208), one or more data radio bearers for the remote UE (302) over the multi-hop relay chain.
