Method and apparatus for managing pipeline for split operations in communication network system

Abstract

The disclosure relates to a 5G or 6G communication system for supporting a higher data transmission rate. A method performed by an artificial intelligence and machine learning (AIML) enablement client in a communication system includes identifying information about nodes available with an AIML enablement server; selecting, from the nodes, at least one node which takes part in a split operation and deciding an order in which the at least one node performs inference in the split operation; transmitting, to the AIML enablement server, a split operation pipeline creation request message including a list of information about the at least one node in the order; and receiving, from the AIML enablement server, a split operation pipeline creation response message in response to the split operation pipeline creation request message.

Description

METHOD AND APPARATUS FOR MANAGING PIPELINE FOR SPLIT OPERATIONS IN COMMUNICATION NETWORK SYSTEM

[0001] The present disclosure is related to the field of wireless communication. More particularly, the present disclosure is related to a method and system for managing a pipeline for split operations in a communication network system.

[0002] 5G mobile communication technologies define broad frequency bands such that high transmission rates and new services are possible, and can be implemented not only in "Sub 6GHz" bands such as 3.5GHz, but also in "Above 6GHz" bands referred to as mmWave including 28GHz and 39GHz. In addition, it has been considered to implement 6G mobile communication technologies (referred to as Beyond 5G systems) in terahertz bands (for example, 95GHz to 3THz bands) in order to accomplish transmission rates fifty times faster than 5G mobile communication technologies and ultra-low latencies one-tenth of 5G mobile communication technologies.

[0003] At the beginning of the development of 5G mobile communication technologies, in order to support services and to satisfy performance requirements in connection with enhanced Mobile BroadBand (eMBB), Ultra Reliable Low Latency Communications (URLLC), and massive Machine-Type Communications (mMTC), there has been ongoing standardization regarding beamforming and massive MIMO for mitigating radio-wave path loss and increasing radio-wave transmission distances in mmWave, supporting numerologies (for example, operating multiple subcarrier spacings) for efficiently utilizing mmWave resources and dynamic operation of slot formats, initial access technologies for supporting multi-beam transmission and broadbands, definition and operation of BWP (BandWidth Part), new channel coding methods such as a LDPC (Low Density Parity Check) code for large amount of data transmission and a polar code for highly reliable transmission of control information, L2 pre-processing, and network slicing for providing a dedicated network specialized to a specific service.

[0004] Currently, there are ongoing discussions regarding improvement and performance enhancement of initial 5G mobile communication technologies in view of services to be supported by 5G mobile communication technologies, and there has been physical layer standardization regarding technologies such as V2X (Vehicle-to-everything) for aiding driving determination by autonomous vehicles based on information regarding positions and states of vehicles transmitted by the vehicles and for enhancing user convenience, NR-U (New Radio Unlicensed) aimed at system operations conforming to various regulation-related requirements in unlicensed bands, NR UE Power Saving, Non-Terrestrial Network (NTN) which is UE-satellite direct communication for providing coverage in an area in which communication with terrestrial networks is unavailable, and positioning.

[0005] Moreover, there has been ongoing standardization in air interface architecture / protocol regarding technologies such as Industrial Internet of Things (IIoT) for supporting new services through interworking and convergence with other industries, IAB (Integrated Access and Backhaul) for providing a node for network service area expansion by supporting a wireless backhaul link and an access link in an integrated manner, mobility enhancement including conditional handover and DAPS (Dual Active Protocol Stack) handover, and two-step random access for simplifying random access procedures (2-step RACH for NR). There also has been ongoing standardization in system architecture / service regarding a 5G baseline architecture (for example, service based architecture or service based interface) for combining Network Functions Virtualization (NFV) and Software-Defined Networking (SDN) technologies, and Mobile Edge Computing (MEC) for receiving services based on UE positions.

[0006] As 5G mobile communication systems are commercialized, connected devices that have been exponentially increasing will be connected to communication networks, and it is accordingly expected that enhanced functions and performances of 5G mobile communication systems and integrated operations of connected devices will be necessary. To this end, new research is scheduled in connection with eXtended Reality (XR) for efficiently supporting AR (Augmented Reality), VR (Virtual Reality), MR (Mixed Reality) and the like, 5G performance improvement and complexity reduction by utilizing Artificial Intelligence (AI) and Machine Learning (ML), AI service support, metaverse service support, and drone communication.

[0007] Furthermore, such development of 5G mobile communication systems will serve as a basis for developing not only new waveforms for providing coverage in terahertz bands of 6G mobile communication technologies, multi-antenna transmission technologies such as Full Dimensional MIMO (FD-MIMO), array antennas and large-scale antennas, metamaterial-based lenses and antennas for improving coverage of terahertz band signals, high-dimensional space multiplexing technology using OAM (Orbital Angular Momentum), and RIS (Reconfigurable Intelligent Surface), but also full-duplex technology for increasing frequency efficiency of 6G mobile communication technologies and improving system networks, AI-based communication technology for implementing system optimization by utilizing satellites and AI (Artificial Intelligence) from the design stage and internalizing end-to-end AI support functions, and next-generation distributed computing technology for implementing services at levels of complexity exceeding the limit of UE operation capability by utilizing ultra-high-performance communication and computing resources.

[0008] Artificial Intelligence (AI) / Machine Learning (ML) is being used in a range of application domains across industry sectors. In mobile communications systems, mobile devices (e.g. smartphones, automotive, robots) are increasingly replacing conventional algorithms (e.g. speech recognition, image recognition, video processing) with AI / ML models to enable applications. In order to offload the computation-intensive, energy-intensive parts to network endpoints, and to leave the privacy-sensitive and delay-sensitive parts at the end device, the AI / ML operation / model is split into multiple parts according to the current task and environment and computation-intensive, energy-intensive parts are offloaded to network endpoints. The device executes the inference up to a specific layer of the machine learning model (e.g. Convolutional Neural Network (CNN)) and sends the intermediate data to the network server. The split operation pipeline is a list of distributed compute nodes configured sequentially to perform the AIML split operation. Data can be provided at the entry point of the pipeline, and sequentially processed through each node of the pipeline. It is also possible that some of the nodes in the pipeline perform the required split operation in parallel (at same time).

[0009] The 3GPP TS 23.482 defines enabler layer to support AIML operations. The AIML enablement server (as defined in TS 23.482) supports AIML enablement client by providing AIML split operation pipeline by discovering and selecting the required nodes to perform split operation. However, it may be possible that due to security or other policy related concerns, the application client want to select its own pipeline of nodes instead of the AIML enablement server selecting the nodes to perform split operations. The current AIML enablement server does not support application client to select its own pipeline by selecting the appropriate nodes.

[0010] Hence, it is desirable to address the above mentioned problems and disadvantages or at least provide a useful alternative.

[0011] In an embodiment of present disclosure, a method performed by an artificial intelligence and machine learning (AIML) enablement client in a communication system is provided. The method includes identifying information about nodes available with an AIML enablement server; selecting, from the nodes, at least one node which takes part in a split operation and deciding an order in which the at least one node performs inference in the split operation; transmitting, to the AIML enablement server, a split operation pipeline creation request message including a list of information about the at least one node in the order; and receiving, from the AIML enablement server, a split operation pipeline creation response message in response to the split operation pipeline creation request message.

[0012] In an embodiment of present disclosure, a method performed by an AIML enablement server in a communication system is provided. The method includes receiving, from an AIML enablement client, a split operation pipeline creation request message, the split operation pipeline creation request including a list of information about at least one node which takes part in a split operation in an order in which the at least one node performs inference in the split operation, wherein the at least one node is selected from nodes available with the AIML enablement server; identifying that the AIML enablement client is authorized for the request; and transmitting, to the AIML enablement client, a split operation pipeline creation response message in response to the split operation pipeline creation request message.

[0013] In an embodiment of present disclosure, an AIML enablement client in a communication system is provided. The AIML enablement client includes a transceiver and a controller. The controller is configured to identify information about nodes available with an AIML enablement server, select, from the nodes, at least one node which takes part in a split operation and decide an order in which the at least one node performs inference in the split operation, transmit, to the AIML enablement server via the transceiver, a split operation pipeline creation request message including a list of information about the at least one node in the order, and receive, from the AIML enablement server via the transceiver, a split operation pipeline creation response message in response to the split operation pipeline creation request message.

[0014] In an embodiment of present disclosure, an AIML enablement server in a communication system is provided. The AIML enablement server includes a transceiver and a controller. The controller is configured to receive, from an AIML enablement client via the transceiver, a split operation pipeline creation request message, the split operation pipeline creation request including a list of information about at least one node which takes part in a split operation in an order in which the at least one node performs inference in the split operation, wherein the at least one node is selected from nodes available with the AIML enablement server; identify that the AIML enablement client is authorized for the request; and transmit, to the AIML enablement client via the transceiver, a split operation pipeline creation response message in response to the split operation pipeline creation request message.

[0015] In an aspect, the objectives are achieved by providing a method for managing a pipeline for split operations in a communication network system. The method includes determining one or more nodes for taking part in the split operations along with an order for the one or more nodes to perform a split operation inference. Further, the method includes generating a split operation create pipeline request message to create a split operation pipeline upon determination of the one or more nodes for taking part in the split operations. Further, the method includes transmitting the split operation create pipeline request message to a network apparatus comprising an AIML enablement server. Further, the method includes receiving a split operation create pipeline response message from the network apparatus upon validation of the split operation create pipeline request message. The split operation create pipeline response message indicates either a success in creation of the split operation pipeline or a failure in creation of the split operation pipeline.

[0016] In another aspect, the objectives are achieved by providing a method for managing a pipeline for split operations in a communication network system. The method includes receiving a split operation create pipeline request message from a UE comprising at least one of an AIML enablement client and a VAL client to create a split operation pipeline. Further, the method includes determining whether a requestor is authorized to create the split operation pipeline. Further, the method includes generating a pipeline identifier and a pipeline profile for the split operation pipeline upon successful authorization of the requestor. Further, the method includes generating a split operation create pipeline response message upon generation of the pipeline identifier of the split operation pipeline. The split operation create pipeline response message indicates either a success in creation of the split operation pipeline or a failure in creation of the split operation pipeline. Further, the method includes transmitting the split operation create pipeline response message to the UE.

[0017] In another aspect, the objectives are achieved by providing a UE for managing a pipeline for split operations in a communication network system. The UE includes a first processor, a first memory coupled to the first processor, and a split operation pipeline management controller coupled to the first memory and the first processor. The split operation pipeline management controller determines one or more nodes for taking part in the split operations along with an order for the one or more nodes to perform a split operation inference. Further, the split operation pipeline management controller generates a split operation create pipeline request message to create a split operation pipeline upon determination of the one or more nodes for taking part in the split operations. Further, the split operation pipeline management controller transmits the split operation create pipeline request message to a network apparatus comprising an AIML enablement server. Further, the split operation pipeline management controller receives a split operation create pipeline response message from the network apparatus upon validation of the split operation create pipeline request message. The split operation create pipeline response message indicates either a success in creation of the split operation pipeline or a failure in creation of the split operation pipeline.

[0018] In another aspect, the objectives are achieved by providing a network apparatus for managing a pipeline for split operations in a communication network system. The network apparatus includes a second processor, a second memory coupled to the second processor, and a network split operation pipeline management controller coupled to the second memory and the second processor. The network split operation pipeline management controller receives a split operation create pipeline request message from a UE comprising at least one of an AIML enablement client and a VAL client to create a split operation pipeline. Further, the network split operation pipeline management controller determines whether the requestor is authorized to create the split operation pipeline. Further, the network split operation pipeline management controller generates a pipeline identifier and a pipeline profile for the split operation pipeline upon successful authorization of the requestor. Further, the network split operation pipeline management controller generates a split operation create pipeline response message upon generation of the pipeline identifier of the split operation pipeline. The split operation create pipeline response message indicates either a success in creation of the split operation pipeline or a failure in creation of the split operation pipeline. Further, the network split operation pipeline management controller transmits the split operation create pipeline response message to the UE. Further, the network split operation pipeline management controller transmits a notification message to one or more nodes in the split operation pipeline.

[0019] These and other aspects of the embodiments herein will be better appreciated and understood when considered in conjunction with the following description and the accompanying drawings. It should be understood, however, that the following descriptions, while indicating preferred embodiments and numerous specific details thereof, are given by way of illustration and not of limitation. Many changes and modifications be made within the scope of the embodiments herein.

[0020] The embodiments herein is to provide a system and method for managing a pipeline for split operations in a communication network system.

[0021] According to various embodiments of the present disclosure, the AIML enablement client is able to select appropriate nodes and an order in which the selected nodes execute the split operations for creating a split operation pipeline.

[0022] According to various embodiments of the present disclosure, the AIML enablement client is able to share the details of the split operation pipeline created to an AIML enablement server.

[0023] According to various embodiments of the present disclosure the AIML client is able to update or delete the split operation pipeline created, and notify the nodes within the split operation pipeline regarding the update and deletion.

[0024] These and other features, aspects, and advantages of the present embodiments are illustrated in the accompanying drawings, throughout which like reference letters indicate corresponding parts in the various figures. The embodiments herein will be better understood from the following description with reference to the drawings, in which:

[0025] Fig. 1 is a block diagram that illustrates a schematic of a UE implemented to carry out the disclosed subject matter according to an embodiment as disclosed herein.

[0026] Fig. 2 is a block diagram that illustrates a schematic of a network apparatus implemented to carry out the disclosed subject matter according to an embodiment as disclosed herein.

[0027] Fig. 3 is a sequence diagram that illustrates split operation pipeline creation request from an AIML enablement client of the UE according to an embodiment as disclosed herein.

[0028] Fig. 4 is a flow diagram that illustrate a method for managing a pipeline for split operations in a communication network system by an AIML enablement client of the UE according to an embodiment as disclosed herein.

[0029] Fig. 5 is a flow diagram that illustrate a method for managing a pipeline for split operations in a communication network system by the network apparatus according to an embodiment as disclosed herein.

[0030] Fig. 6 is a flow diagram that illustrates a method for updating the split operation pipeline according to an embodiment as disclosed herein.

[0031] Fig. 7 is a flow diagram that illustrates a method for deleting the split operation pipeline according to an embodiment as disclosed herein.

[0032] FIG. 8 illustrates an electronic device operating as an AIML enablement client according to an embodiment as disclosed herein.

[0033] FIG. 9 illustrates a network entity operating as an AIML enablement server according to an embodiment as disclosed herein.

[0034] The embodiments herein and the various features and advantageous details thereof are explained more fully with reference to the non-limiting embodiments that are illustrated in the accompanying drawings and detailed in the following description. Descriptions of well-known components and processing techniques are omitted so as to not unnecessarily obscure the embodiments herein. Also, the various embodiments described herein are not necessarily mutually exclusive, as some embodiments can be combined with a plurality of other embodiments to form new embodiments. The term "or" as used herein, refers to a non-exclusive or, unless otherwise indicated. The examples used herein are intended merely to facilitate an understanding of ways in which the embodiments herein can be practiced and to further enable those skilled in the art to practice the embodiments herein. Accordingly, the examples are not be construed as limiting the scope of the embodiments herein.

[0035] As is existing in the field, embodiments are described and illustrated in terms of blocks that carry out a described function or functions.　These blocks, which referred to herein as managers, units, modules, hardware components or the like, are physically implemented by analog and / or digital circuits such as logic gates, integrated circuits, microprocessors, microcontrollers, memory circuits, passive electronic components, active electronic components, optical components, hardwired circuits, and the like, and optionally be driven by firmware and software. The circuits, for example, be embodied in a plurality of semiconductor chips, or on substrate supports such as printed circuit boards, and the like.　The circuits constituting a block be implemented by dedicated hardware, or by a processor (e.g., a plurality of programmed microprocessors and associated circuitry), or by a combination of dedicated hardware to perform some functions of the block and a processor to perform other functions of the block.Eachblock of the embodiments be physically separated into two or more interacting and discrete blocks without departing from the scope of the proposed method.　Likewise, the blocks of the embodiments be physically combined into more complex blockswithoutdeparting from the scope of the proposed method.

[0036] The accompanying drawings are used to help easily understand various technical features and it is understood that the embodiments presented herein are not limited by the accompanying drawings. As such, the proposed method is construed to extend to any alterations, equivalents and substitutes in addition to those which are particularly set out in the accompanying drawings. Although the terms first, second, etc. used herein to describe various elements, these elements are not be limited by these terms. These terms are generally used to distinguish one element from another.

[0037] In the prior art, the AIML enablement server does not support the AIML enablement client to select its own pipeline by selecting the appropriate nodes.

[0038] The proposed solution discloses a system and method for AIML client to manage pipeline for split operation. The method includes enabling the AIML enablement client and VAL client to select appropriate nodes and their order in which they execute the split operations, and announce the pipeline. The AIML client is enabled to update or delete the AIML split operation pipeline. Upon receiving a list of available nodes from an AIML enablement server, an AIML enablement client and VAL client selects the appropriate nodes to perform split operations in order. The AIML enablement client sends a request to create split operation pipeline to the AIML enablement server, which includes required parameters. The AIML enablement server creates the pipeline and assigns the unique identifier. The AIML enablement server sends response back to the AIML enablement client and notifies the creation of the pipeline to all nodes which are part of the pipeline.

[0039] The AIML enablement client or the AIML enablement server determines that some of the nodes in the split operation pipeline may not be able to perform the required operation, so the AIML enablement client sends request to update the AIML split operation pipeline. The request includes the list of nodes to be removed from the pipeline and the list of nodes to be added into the pipeline. The AIML enablement server validates the pipeline and updates the pipeline by adding and removing the nodes. The AIML enablement server sends response to AIML enablement client indicating result of the update operation. The AIML enablement client sends request to AIML enablement server to delete the pipeline. The AIML enablement server validates the pipeline and deletes the pipeline. The AIML enablement server sends a response to AIML enablement client indicating result of the delete operation.

[0040] The AI / ML operation is split into multiple parts and computation-intensive, energy-intensive parts are offloaded to network endpoints. The 3GPP is defining the enabler layer to support AIML operations. The AIML enablement server supports AIML enablement client by providing AIML split operation pipeline by discovering the required nodes to perform split operation. The present disclosure provides method for the AIML enablement client to create, update and delete the split operation pipeline.

[0041] Fig. 1 is a block diagram that illustrates a schematic of UE (102) implemented to carry out the disclosed subject matter according to anembodimentas disclosed herein. The UE (102) includes at least one of an AIML enablement client (112) or a VAL client. Examples of the UE (102) can include, but are not limited to, Consumer Electronics (such as Mobile Phones and Smartphones), Tablets, Wearable Devices, Computing Devices (such as Laptops, Notebooks, Desktops, Workstations, etc.), IoT Devices, Automotive Systems (such as connected cars, Autonomous Vehicles, Vehicle-to-Everything (V2X) communication devices, etc.), Enterprise Devices such as robotics, Specialized Equipment (such as Medical Devices, Public Safety Devices, etc.), Media Devices (such as Gaming Consoles, Streaming Devices, etc.).

[0042] In an embodiment, in Fig. 1, the UE (102) includes a first processor (104), a first memory (106), a first I / O interface (108), and a split operation pipeline management controller(110) coupled to the first processor (104) and the first memory (106). The components are explained in further detail below.

[0043] The first processor (104) communicates with the first memory (106), the first I / O interface (108), and the split operation pipeline management controller(110). The first processor (104) is configured to execute instructions stored in the first memory (106) and to perform various processes. The first processor (104) includes one or a plurality of processors, is a general-purpose processor such as a central processing unit (CPU), an application processor (AP), or the like, a graphics-onlyprocessing unit such as a graphics processing unit (GPU), a visual processing unit (VPU), and / or an Artificial Intelligence (AI) dedicated processor such as a neural processing unit (NPU).

[0044] The first memory (106) includes storage locations to be addressable through the first processor (104). The first memory (106) is not limited to a volatile memory and / or a non-volatile memory. Further, the first memory (106) includes a plurality of computer-readable storage media. The first memory (106) includes non-volatile storage elements. For example, non-volatile storage elements includes magnetic hard disks, optical disks, floppy disks, flash memories, or forms of electrically programmable memories (EPROM) or electrically erasable and programmable (EEPROM) memories.

[0045] The first I / O interface (108) transmits the information between the first memory (106) and external peripheral devices. The peripheral devices are the input-output devices associated with the UE (102). Further, the split operation pipeline management controller(110) communicates with the first I / O interface (108) and the first memory (106). The split operation pipeline management controller(110) is coupled to the first memory (106) and the first processor (104). The split operation pipeline management controller(110) is an innovative hardware that are realized through the physical implementation of both analog and digital circuits, including logic gates, integrated circuits, microprocessors, microcontrollers, memory circuits, passive and active electronic components, as well as optical components.

[0046] In an embodiment, the split operation pipeline management controller (110) determines or discovers one or more nodes for taking part in the split operations along with an order for the nodes to perform a split operation inference. For instance, the nodes can be determined / discovered based on factors such as the capabilities of each node, the current load on the system, specific requirements of the split operation, and the like. This ensures that the split operations are performed in a synchronized manner, leading to improved throughput and reduced latency.

[0047] In an embodiment, the split operation pipeline management controller (110) generates a split operation create pipeline request message to create a split operation pipeline upon determination of the nodes for taking part in the split operations. The split operation create pipeline request message includes a requestor identifier, security credentials, a model information, a usage information, a pipeline head endpoint, a pipeline tail endpoint, a list of selected nodes in order of a stage to perform the split operation inference, and the like.

[0048] The requestor identifier identifies the entity or user that is making the request. This is essential for tracking and managing requests within the communication network system. The security credentials are important for authenticating the request and ensuring that only authorized entities can initiate the creation of the split operation pipeline. This helps maintain the integrity and security of the communication network system. The model information includes details about the AI / ML models used during the split operations. The usage information provides context on how the split operation pipeline will be used, for example performance expectations and resource requirements. The usage information helps in optimizing the split operation pipeline for efficiency and effectiveness. Further, the pipeline head endpoint marks the starting point of the split operation pipeline where data enters, while the pipeline tail endpoint signifies the endpoint where the processed data exits the split operation pipeline. These endpoints are crucial for defining the flow of data through the split operation pipeline.

[0049] In an embodiment, the split operation management controller (110) transmits the split operation create pipeline request message to a network apparatus. For example, the network apparatus includes an AIML enablement server.

[0050] In an embodiment, the split operation management controller (110) receives a split operation create pipeline response message from the network apparatus upon validation of the split operation create pipeline request message. The split operation create pipeline response message indicates either a success in creation of the split operation pipeline or a failure in creation of the split operation pipeline. The split operation create pipeline response message includes a pipeline identifier upon a success in creation of the split operation pipeline. Else, the split operation create pipeline response message includes a failure cause upon a failure in creation of the split operation pipeline.

[0051] Fig. 2 is a block diagram that illustrates a schematic of the network apparatus (202) implemented to carry out the disclosed subject matter according to anembodimentas disclosed herein. As shown, the network apparatus (202) includes a second processor (204), a second memory (206), a second I / O interface (208), and a network split operation pipeline management controller (210).

[0052] The network apparatus (202) includes various hardware and software components that facilitate communication between user equipment and network infrastructure. Examples of the network apparatus (202) can include, but is not limited to an AIML enablement server (212), Base Stations (such as macro cells, small cells, femtocells, picocells, etc.) for wireless communication, Antennas and RF Units (e.g., MIMO, beamforming) to enhance signal coverage and data throughput, Core Network Equipment (e.g., MMEs, S-GWs, P-GWs in 4G; AMFs, SMFs, UPFs in 5G) for data routing, mobility, and session control, Network Function Virtualization (NFV) and Software-Defined Networking (SDN) for dynamic resource allocation and scalability, Edge Computing Nodes (e.g., MEC servers) for low-latency processing, Backhaul and Transport Equipment (e.g., fiber-optic links, microwave relays, Ethernet switches) to connect base stations to the core network, Network Management Systems (NMS) and Operation Support Systems (OSS) for network configuration, fault management, and optimization, Radio Network Controllers (RNCs) in 3G, Distributed Units (DUs), and Centralized Units (CUs) in 5G, Network Slicing Components for virtualized resource allocation, Security elements (e.g., Firewalls, IDS, AAA Servers) for secure communication.

[0053] The network split operation pipeline management controller (210) is coupled to the second memory (206) and the second processor (204). The network split operation pipeline management controller (210) is an innovative hardware that are realized through the physical implementation of both analog and digital circuits, including logic gates, integrated circuits, microprocessors, microcontrollers, memory circuits, passive and active electronic components, as well as optical components.

[0054] In an embodiment, the network split operation pipeline management controller (210) receives a split operation create pipeline request message from the UE (102) to create a split operation pipeline. The UE (102) includes at least one of the AIML enablement client (112) and the VAL client.

[0055] In an embodiment, the network split operation pipeline management controller (210) determines whether the requestor is authorized to create the split operation pipeline. This maintains the integrity and security of the communication network system while optimizing resource allocation and service delivery.

[0056] In an embodiment, the network split operation pipeline management controller (210) generates a pipeline identifier and a pipeline profile for the split operation pipeline upon successful authorization of requestor. The pipeline identifier serves as a reference for the split operation pipeline associated with the UE (102) and is essential for tracking and managing the split operation pipeline. The pipeline profile contains essential parameters and configurations that define the characteristics of the split operation pipeline. For instance, the pipeline profile can include details such as the types of data to be processed, the processing rules, resource allocation, and the like.

[0057] In an embodiment, the network split operation pipeline management controller (210) generates a split operation create pipeline response message upon generation of the pipeline identifier of the split operation pipeline. The split operation create pipeline response message indicates either a success in creation of the split operation pipeline or a failure in creation of the split operation pipeline. In case of a failure, the split operation create pipeline response message includes the failure cause. The network split operation pipeline management controller (210) then transmits the split operation create pipeline response message to the UE (102).

[0058] In an embodiment, the network split operation pipeline management controller (210) transmits a notification message to one or more nodes in the split operation pipeline. The notification message provides a notification to the in the split operation pipeline about their inclusion within the split operation pipeline.

[0059] In an embodiment, the network split operation pipeline management controller (210) receives a request message from the UE (102) to update the split operation pipeline. The request message can be received upon determination of at least one node within the split operation pipeline that cannot perform the split operations. For instance, the nodes cannot perform the split operations due to factors such as hardware malfunctions, network congestions, resource limitations, and the like.

[0060] In an embodiment, the network split operation pipeline management controller (210) performs a validation of the pipeline identifier of the split operation pipeline upon receiving the request message. This validation process is essential to ensure that the identifier corresponds to an existing and correctly configured pipeline within the communication network system. The network split operation pipeline management controller (210) then generates an update response message upon validation of the pipeline identifier of the split operation pipeline. The update response message is transmitted to the UE (102).

[0061] In an embodiment, the network split operation pipeline management controller (210) transmits a notification message to one or more nodes in the split operation pipeline. The notification message provides an indication to the nodes in the split operation pipeline to update the split operation pipeline. For instance, the update can include either adding nodes or removing nodes within the split operation pipeline.

[0062] In an embodiment, the network split operation pipeline management controller (210) receives a delete request message from the UE (102) to delete the split operation pipeline upon completion of the split operations. This generally occurs after the split operations have been finalized, meaning that all necessary tasks and data transfers associated with the split operation pipeline have been completed successfully.

[0063] In an embodiment, the network split operation pipeline management controller (210) performs a validation of the pipeline identifier of the split operation pipeline upon receiving the delete request message. This validation process is essential to ensure that the pipeline identifier corresponds to an existing and correctly configured pipeline within the communication network system. The network split operation pipeline management controller (210) then generates a delete update response message upon validation of the pipeline identifier of the split operation pipeline. The delete update response message is transmitted to the UE (102).

[0064] In an embodiment, the network split operation pipeline management controller (210) transmits a notification message to one or more nodes in the split operation pipeline. The notification message provides an indication to the in the split operation pipeline that the split operation pipeline has been deleted.

[0065] Fig. 3 is a sequence diagram that illustrates split operation pipeline creation request from the AIML enablement client (112) of the UE (102) according to an embodiment as disclosed herein. As shown in the sequence diagram, the AIML enablement client (112) of the UE (102) is in communication with the AIML enablement server (212) of the network apparatus (202). Each step is explained in further detail below.

[0066] Pre-condition: The AIML enablement client (112) has discovered the nodes which can take part in the split operation. The nodes (having the AIML enablement client (112)), which takes part in the split operation has subscribed to the split operation related events to AIML enablement server (212).

[0067] At step 1, the AIML enablement client (112) and the VAL client selects the nodes which can take part in the split operation and also decides the order in which nodes should perform the split operation inference. The AIML enablement client (112) sends a request to create split operation pipeline to the AIML enablement server (212). The request includes requestor identifier, security credentials, information about the trained AIML models (e.g., identifiers, versions, etc.) to be used at each stage, information about the planned usage of the AIML split operation (e.g., predicted inputs frequency / size, requested output frequency / size, etc.) and AIML split operation profile including the list of selected nodes in-order for the pipeline. The parameters as shown in Table 1 are included in the request.

[0068] Information elementStatusDescriptionRequestor identifierMThe identity of the requestor (e.g., VAL client ID, AIML client ID, UE identifier)Security credentialsMThe security credentials of the requestor.model informationMInformation about the AIML models to be used in each stage (e.g., identifiers, versions, etc.)usage informationOInformation about the planned usage of the AIML split operation pipeline (e.g., inputs frequency / size, output frequency / size, etc.)Pipeline informationOThe information about the split AIML split operation pipeline.> pipeline identifierMIdentifier of the split operation pipeline> pipeline head endpointMEndpoint of the pipeline head node (e.g., for providing inference data).> pipeline tail endpointMEndpoint of the pipeline head node (e.g., for obtaining inference results).> pipeline expected usageOInformation about usage of the AIML split operation pipeline (e.g., inputs frequency / size, output frequency / size, etc.)> list of nodesOList of all discovered node in the order in which they process the data in pipeline.> notification targetOEndpoint information where the result of the split operation is sent by the nodes

[0069] At step 2, upon receiving the request, the AIML enablement server (212) validates if the requestor is authorized to create split operation pipeline. If the requestor is authorized, the AIML enablement server (212) creates the pipeline and assign unique identifier for the pipeline.

[0070] At step 3, the AIML enablement server (212) sends a split operation create pipeline response message to the AIML enablement client (112) indicating success or failure of the request. In case of success, the response includes the pipeline identifier. Further, the AIML enablement server (212) sends notification to all nodes which are added to the AIML split operation pipeline. In case of failure, the response includes the failure cause. The parameters as shown in the Table 2 are included in the response.

[0071] Information elementStatusDescriptionresultMIndicates success or failure of the requestpipeline identifierOIdentifier of the split operation pipeline (when result indicates success)Failure causeOIndicates failure cause

[0072] In an embodiment, the AIML enablement client (112) determines that some of the nodes in the split operation pipeline may not be able to perform the required operation, so the AIML enablement client (112) sends request to update the AIML split operation pipeline. The request includes pipeline identifier, list of nodes to be removed from the pipeline, list of nodes to be added in the pipeline and the pipeline profile. Upon receiving the request, the AIML enablement server (212) validates the pipeline identifier and if valid, the AIML enablement server (212) updates the pipeline and sends response to the AIML enablement client (112). The AIML enablement server (212) sends notification to all nodes which are either added to or removed from the AIML split operation pipeline.

[0073] In an embodiment, the AIML enablement server (212) determines that some of the nodes in the split operation pipeline may not be able to perform the required operation. The AIML enablement server (212) identifies the nodes which can take part in the split operation. The AIML enablement server (212) updates the pipeline by removing the nodes which cannot take part in the split operation and adds the nodes which can take part in the split operation. The AIML enablement server (212) sends notification to all nodes which are either added to or removed from the AIML split operation pipeline.

[0074] In an embodiment, the VAL client indicates the AIML enablement client (112) to delete the pipeline (as the split operation is complete). The AIML enablement client (112) or the VAL server sends request to delete the AIML split operation pipeline. The request includes pipeline identifier. Upon receiving the request, the AIML enablement server (212) validates the pipeline identifier and if valid, the AIML enablement server (212) deletes the pipeline along with its associated profile and sends response to the AIML enablement client (112). The AIML enablement server (212) sends notification to all nodes which are which are part of the AIML split operation pipeline to indicate about deletion of the pipeline.

[0075] In an embodiment, the AIML enablement server (212) determines that the split operation pipeline is not required any more. The AIML enablement server (212) deletes the pipeline along with its associated profile. The AIML enablement server (212) sends notification to all nodes which are which are part of the AIML split operation pipeline to indicate about deletion of the pipeline.

[0076] In an embodiment, the procedure (to create or update or delete) can also be initiated by Application Data Analytics Enablement (ADAE) client, any Service Enabler Architecture Layer (SEAL) client, Edge Enabler Client (EEC), or any other client.

[0077] In an embodiment, the procedure (to create or update or delete) can also be performed by ADAE server, any SEAL server, Edge Enabler Server (EES) or any other server.

[0078] In an embodiment, the procedure can also be performed by a SEAL group management server with list of ordered members as group property.

[0079] Fig. 4 is a flow diagram that illustrate a method for managing a pipeline for split operations in a communication network system by the AIML enablement client (112) of the UE (102) according to an embodiment as disclosed herein. The method includes steps (402-408). Each step is explained in further detail below.

[0080] In step (402), the UE (102) determines one or more nodes for taking part in the split operations along with an order for the nodes to perform a split operation inference. The identification of nodes can be influenced by various factors, including the capabilities of each node, the existing system load, the particular needs of the split operation, and similar considerations. This approach guarantees that split operations are executed in a synchronised manner, resulting in enhanced throughput and minimized latency.

[0081] In step (404), the UE (102) generates a split operation create pipeline request message to create a split operation pipeline upon determination of the nodes for taking part in the split operations. The split operation create pipeline request message includes a requestor identifier, security credentials, a model information, a usage information, a pipeline head endpoint, a pipeline tail endpoint, a list of selected nodes in order of a stage to perform the split operation inference, and the like.

[0082] The requestor identifier pinpoints the entity or user initiating the request. This is essential for monitoring and managing requests within the communication network system. Security credentials play an important role in authenticating the request, ensuring that only authorized users can trigger the creation of the split operation pipeline. Model information encompasses specifics regarding the AI / ML models utilized during the split operations. Usage information offers insights into how the split operation pipeline will be employed, including performance expectations and resource needs. This information is useful in optimizing the split operation pipeline for both efficiency and effectiveness. Additionally, the pipeline head endpoint represents the entry point of the split operation pipeline where data is introduced, while the pipeline tail endpoint indicates where the processed data exits the pipeline. These endpoints are essential for establishing the data flow throughout the split operation pipeline.

[0083] In step (406), the UE (102) transmits the split operation create pipeline request message to the network apparatus (202) including the AIML enablement server (212).

[0084] In step (408), the UE (102) receives a split operation create pipeline response message from the network apparatus (202) upon validation of the split operation create pipeline request message. The split operation create pipeline response message indicates either a success in creation of the split operation pipeline or a failure in creation of the split operation pipeline. The split operation create pipeline response message includes a pipeline identifier upon a success in creation of the split operation pipeline. Else, the split operation create pipeline response message includes a failure cause upon a failure in creation of the split operation pipeline.

[0085] Fig. 5 is a flow diagram that illustrate a method for managing a pipeline for split operations in a communication network system by the network apparatus (202) according to an embodiment as disclosed herein. The method includes steps (502-512). Each step is explained in further detail below.

[0086] In step (502), the network apparatus (202) including the AIML enablement server (212) receives a split operation create pipeline request message from the UE (102) to create a split operation pipeline. The UE (102) includes at least one of the AIML enablement client (112) and the VAL client.

[0087] In step (504), the network apparatus (202) determines whether the requestor is authorized to create the split operation pipeline. This ensures the integrity and security of the communication network system, while enhancing resource allocation and service delivery.

[0088] In step (506), the network apparatus (202) generates a pipeline identifier and a pipeline profile for the split operation pipeline upon successful authorization of the requestor. The pipeline identifier acts as a reference for the split operation pipeline linked to the UE (102) and is crucial for monitoring and overseeing the split operation pipeline. The pipeline profile encompasses key parameters and configurations that outline the features of the split operation pipeline. For example, the pipeline profile contains information regarding the types of data to be handled, the processing guidelines, resource distribution, and the like.

[0089] In step (508), the network apparatus (202) generates a split operation create pipeline response message upon generation of the pipeline identifier of the split operation pipeline. The split operation create pipeline response message indicates either a success in creation of the split operation pipeline or a failure in creation of the split operation pipeline. In case of a failure, the split operation create pipeline response message includes the failure cause. In step (510), the network apparatus (202) then transmits the split operation create pipeline response message to the UE (102).

[0090] In step (512), the network apparatus (202) transmits a notification message to one or more nodes in the split operation pipeline. The notification message provides a notification to the in the split operation pipeline about their inclusion within the split operation pipeline.

[0091] Fig. 6 is a flow diagram that illustrates a method for updating the split operation pipeline according to an embodiment as disclosed herein. The method includes steps (602-610). Each step is explained in further detail below.

[0092] In step (602), the network apparatus (202) including the AIML enablement server (212) receives a request message from the UE (102) to update the split operation pipeline. The request message may be generated when it is identified that at least one node in the split operation pipeline is unable to execute the split operations. This inability may arise from various issues, including hardware failures, network congestion, resource constraints, and the like.

[0093] In step (604), the network apparatus (202) performs a validation of the pipeline identifier of the split operation pipeline upon receiving the request message. This validation process is essential to ensure that the identifier corresponds to an existing and correctly configured pipeline within the communication network system. In step (606), the network apparatus (202) then generates an update response message upon validation of the pipeline identifier of the split operation pipeline. In step (608), the update response message is transmitted to the UE (102).

[0094] In step (610), the network apparatus (202) transmits a notification message to one or more nodes in the split operation pipeline. The notification message provides an indication to the nodes in the split operation pipeline to update the split operation pipeline. For instance, the update can include either adding nodes or removing nodes within the split operation pipeline.

[0095] Fig. 7 is a flow diagram that illustrates a method for deleting the split operation pipeline according to an embodiment as disclosed herein. The method includes steps (702-710). Each step is explained in further detail below.

[0096] In step (702), the network apparatus (202) including the AIML enablement server (212) receives a delete request message from the UE (102) to delete the split operation pipeline upon completion of the split operations. This typically takes place once the split operations are fully completed, indicating that all essential tasks and data transfers related to the split operation pipeline have been successfully carried out.

[0097] In step (704), the network apparatus (202) performs a validation of the pipeline identifier of the split operation pipeline upon receiving the delete request message. This validation process is essential to ensure that the pipeline identifier corresponds to an existing and correctly configured pipeline within the communication network system. In step (706), the network apparatus (202) then generates a delete update response message upon validation of the pipeline identifier of the split operation pipeline. In step (708), the delete update response message is transmitted to the UE (102).

[0098] In step (710), the network apparatus (202) transmits a notification message to one or more nodes in the split operation pipeline. The notification message provides an indication to the in the split operation pipeline that the split operation pipeline has been deleted.

[0099] FIG. 8 illustrates an electronic device operating as an AIML enablement client according to an embodiment as disclosed herein.

[0100] Referring to the FIG. 8, the electronic device 800 may include a processor (or a controller) 810, a transceiver 820 and a memory 830. However, all of the illustrated components are not essential. The electronic device 800 may be implemented by more or less components than those illustrated in FIG. 8. In addition, the processor 810 and the transceiver 820 and the memory 830 may be implemented as a single chip according to another embodiment.

[0101] The electronic device 800 may correspond to electronic device described above. For example, the electronic device 800 may correspond to the UE 102 or the AIML enablement client 112 illustrated in FIGs. 1 and 3.

[0102] The aforementioned components will now be described in detail.

[0103] The processor 810 may include one or more processors or other processing devices that control the proposed function, process, and / or method. Operation of the electronic device 800 may be implemented by the processor 810.

[0104] The transceiver 820 may include a RF transmitter for up-converting and amplifying a transmitted signal, and a RF receiver for down-converting a frequency of a received signal. However, according to another embodiment, the transceiver 820 may be implemented by more or less components than those illustrated in components.

[0105] The transceiver 820 may be connected to the processor 810 and transmit and / or receive a signal. The signal may include control information and data. In addition, the transceiver 820 may receive the signal through a wireless channel and output the signal to the processor 810. The transceiver 820 may transmit a signal output from the processor 810 through the wireless channel.

[0106] The memory 830 may store the control information or the data included in a signal obtained by the electronic device 800. The memory 830 may be connected to the processor 810 and store at least one instruction or a protocol or a parameter for the proposed function, process, and / or method. The memory 830 may include read-only memory (ROM) and / or random access memory (RAM) and / or hard disk and / or CD-ROM and / or DVD and / or other storage devices.

[0107] FIG. 9 illustrates a network entity operating as an AIML enablement server according to an embodiment as disclosed herein.

[0108] Referring to the FIG. 9, the network entity 900 may include a processor (or a controller) 910, a transceiver 920 and a memory 930. However, all of the illustrated components are not essential. The network entity 900 may be implemented by more or less components than those illustrated in FIG. 9. In addition, the processor 910 and the transceiver 920 and the memory 930 may be implemented as a single chip according to another embodiment.

[0109] The network entity 900 may correspond to the gNB described above. For example, the network entity 900 may correspond to the network apparatus 202 or the AIML enablement server 212 illustrated in FIGs. 2 and 3.

[0110] The aforementioned components will now be described in detail.

[0111] The processor 910 may include one or more processors or other processing devices that control the proposed function, process, and / or method. Operation of the network entity 900 may be implemented by the processor 910.

[0112] The transceiver 920 may include a RF transmitter for up-converting and amplifying a transmitted signal, and a RF receiver for down-converting a frequency of a received signal. However, according to another embodiment, the transceiver 920 may be implemented by more or less components than those illustrated in components.

[0113] The transceiver 920 may be connected to the processor 910 and transmit and / or receive a signal. The signal may include control information and data. In addition, the transceiver 920 may receive the signal through a wireless channel and output the signal to the processor 910. The transceiver 920 may transmit a signal output from the processor 910 through the wireless channel.

[0114] The memory 930 may store the control information or the data included in a signal obtained by the network entity 900. The memory 930 may be connected to the processor 910 and store at least one instruction or a protocol or a parameter for the proposed function, process, and / or method. The memory 930 may include read-only memory (ROM) and / or random access memory (RAM) and / or hard disk and / or CD-ROM and / or DVD and / or other storage devices.

[0115] Although this disclosure has been described with an exemplary embodiment, various changes and modifications may be suggested to one skilled in the art. It is intended that this disclosure encompass such changes and modifications as fall within the scope of the appended claims.

[0116] The foregoing description of the specific embodiments will so fully reveal the general nature of the embodiments herein that others can, by applying current knowledge, readily modify and or adapt for various applications such specific embodiments without departing from the generic concept, and, therefore, such adaptations and modifications are intended to be comprehended within the meaning and range of equivalents of the disclosed embodiments. It is to be understood that the phraseology or terminology employed herein is for the purpose of description and not of limitation. Therefore, while the embodiments herein have been described in terms of preferred embodiments, those skilled in the art will recognize that the embodiments herein can be practiced with modification within the scope of the embodiments as described herein.

Claims

1.A method performed by an artificial intelligence and machine learning (AIML) enablement client in a communication system, the method comprising:identifying information about nodes available with an AIML enablement server;selecting, from the nodes, at least one node which takes part in a split operation and deciding an order in which the at least one node performs inference in the split operation;transmitting, to the AIML enablement server, a split operation pipeline creation request message including a list of information about the at least one node in the order; andreceiving, from the AIML enablement server, a split operation pipeline creation response message in response to the split operation pipeline creation request message.2.The method of claim 1, wherein the split operation pipeline creation request further includes at least one of:an identifier of the AIML enablement client,security credentials information of the AIML enablement client,information about a machine learning (ML) model to be used in each stage,information about a planned usage of the split operation,information indicating an endpoint of a head node for providing inference data, andinformation indicating an endpoint of a head node for obtaining inference results.3.The method of claim 1, wherein, in case that the AIML enablement server successfully creates a split operation pipeline, the split operation pipeline creation response message includes an identifier of the split operation pipeline.4.The method of claim 1, wherein, in case that the AIML enablement server fails to create a split operation pipeline, the split operation pipeline creation response message includes information indicating a cause of failure.5.A method performed by an artificial intelligence and machine learning (AIML) enablement server in a communication system, the method comprising:receiving, from an AIML enablement client, a split operation pipeline creation request message, the split operation pipeline creation request including a list of information about at least one node which takes part in a split operation in an order in which the at least one node performs inference in the split operation, wherein the at least one node is selected from nodes available with the AIML enablement server;identifying that the AIML enablement client is authorized for the request; andtransmitting, to the AIML enablement client, a split operation pipeline creation response message in response to the split operation pipeline creation request message.6.The method of claim 5, wherein the split operation pipeline creation request further includes at least one of:an identifier of the AIML enablement client,security credentials information of the AIML enablement client,information about a machine learning (ML) model to be used in each stage,information about a planned usage of the split operation,information indicating an endpoint of a head node for providing inference data, andinformation indicating an endpoint of a head node for obtaining inference results.7.The method of claim 5, wherein, in case that the AIML enablement server successfully creates a split operation pipeline, the split operation pipeline creation response message includes an identifier of the split operation pipeline.8.The method of claim 5, wherein, in case that the AIML enablement server fails to create a split operation pipeline, the split operation pipeline creation response message includes information indicating a cause of failure.9.An artificial intelligence and machine learning (AIML) enablement client in a communication system, the AIML enablement client comprising:a transceiver; anda controller configured to:identify information about nodes available with an AIML enablement server,select, from the nodes, at least one node which takes part in a split operation and decide an order in which the at least one node performs inference in the split operation,transmit, to the AIML enablement server via the transceiver, a split operation pipeline creation request message including a list of information about the at least one node in the order, andreceive, from the AIML enablement server via the transceiver, a split operation pipeline creation response message in response to the split operation pipeline creation request message.10.The AIML enablement client of claim 9, wherein the split operation pipeline creation request further includes at least one of:an identifier of the AIML enablement client,security credentials information of the AIML enablement client,information about a machine learning (ML) model to be used in each stage,information about a planned usage of the split operation,information indicating an endpoint of a head node for providing inference data, andinformation indicating an endpoint of a head node for obtaining inference results.11.The AIML enablement client of claim 9, wherein, in case that the AIML enablement server successfully creates a split operation pipeline, the split operation pipeline creation response message includes an identifier of the split operation pipeline.12.The AIML enablement client of claim 9, wherein, in case that the AIML enablement server fails to create a split operation pipeline, the split operation pipeline creation response message includes information indicating a cause of failure.13.An artificial intelligence and machine learning (AIML) enablement server in a communication system, the AIML enablement server comprising:a transceiver; anda controller configured to:receive, from an AIML enablement client via the transceiver, a split operation pipeline creation request message, the split operation pipeline creation request including a list of information about at least one node which takes part in a split operation in an order in which the at least one node performs inference in the split operation, wherein the at least one node is selected from nodes available with the AIML enablement server;identify that the AIML enablement client is authorized for the request; andtransmit, to the AIML enablement client via the transceiver, a split operation pipeline creation response message in response to the split operation pipeline creation request message.14.The method of claim 13, wherein the split operation pipeline creation request further includes at least one of:an identifier of the AIML enablement client,security credentials information of the AIML enablement client,information about a machine learning (ML) model to be used in each stage,information about a planned usage of the split operation,information indicating an endpoint of a head node for providing inference data, andinformation indicating an endpoint of a head node for obtaining inference results.15.The method of claim 14, wherein:in case that the AIML enablement server successfully creates a split operation pipeline, the split operation pipeline creation response message includes an identifier of the split operation pipeline, andin case that the AIML enablement server fails to create a split operation pipeline, the split operation pipeline creation response message includes information indicating a cause of failure.

Images