Ai / ML services for edge computing assistance in a communications network

Abstract

This disclosure provides a method for assisting edge computing in a communications network. The method comprises transmitting from a first network node to a second network node a request for assistance for edge computing, wherein the request includes at least one of the role of the consumer in an edge computing architecture, the type of edge computing operations and the type of assistance information; determining at the second network node information required for the request, particularly wherein the information comprises any one of downstream entities and services needed, time windows recommendations for computing task distribution or for intermediate output delivery, and candidate execution node list; initiating at the second network node operations to generate assistance information for edge computing, particularly wherein the initiating comprises subscribing or requesting to an Application Data Analytics Enabler Server (ADAES) for edge load analytics, requesting member UE selection, requesting recommended time windows with Quality of Service (QoS), requesting network data analytics, or requesting resource configurations from a Network Resource Management (NRM) Server; and transmitting from the second network node to the first network node the assistance information for edge computing, wherein the assistance information for edge computing includes any one of: the outcomes of the operations initiated by the second network node, the information required for the request, and information for decision making at the consumer on its edge computing operations.

Description

[0001] AI / ML SERVICES FOR EDGE COMPUTING ASSISTANCE IN A COMMUNICATIONS NETWORK

[0002] TECHNICAL FIELD

[0003] The present invention generally relates to the field of telecommunications, mobile or communications networks, and more specifically, the present invention relates to Edge Computing (EC) and Artificial Intelligence / Machine Learning (AI / ML) integration in communications networks.

[0004] BACKGROUND

[0005] Edge computing (EC) is a distributed computing paradigm that brings computation and data storage closer to the location where it is needed, to improve response times and save bandwidth. EC architectures are designed to process data at or near the source of data generation. This aims to address the latency, bandwidth, and processing constraints posed by traditional cloud computing models.

[0006] Artificial Intelligence (Al) and Machine Learning (ML) are technologies that provide systems the ability to automatically learn and improve from experience without being explicitly programmed. AI / ML integration into edge computing scenarios leverages the computational power of AI / ML algorithms directly at the data source, facilitating immediate data processing and decision-making.

[0007] In the context of edge computing, hierarchical and distributed computing architectures are commonly utilized. See Figure 2, showing an example of architecture for hierarchical computing, and Figure 3, showing an example of architecture for distributed computing. Hierarchical computing is characterized by a tiered structure where decision-making and processing responsibilities are divided among different layers of the architecture, typically involving a central root node that communicates with multiple sub-root nodes, which in turn interact with leaf nodes. This model is well-suited for applications requiring organized data flow and aggregation. On the other hand, distributed computing involves a network of equally privileged, intercommunicating nodes that share data and processing tasks among themselves without a predefined hierarchy, ideal for tasks that can be parallelized across multiple nodes to enhance computational efficiency and reliability.

[0008] The role of edge computing in supporting AI / ML tasks involves various components and services that facilitate the execution of these tasks. These components include edge servers and devices equipped with the computational power to run AI / ML algorithms, as well as the necessary software frameworks and protocols for managing the distribution of tasks and the flow of data. The integration of AI / ML into edge computing not only demands robust hardware but also sophisticated software solutions capable of efficiently managing and orchestrating AI / ML tasks across the distributed nodes within the edge computing architecture.

[0009] Third Generation Partnership Project (3GPP) networks address the enhancement of architectural frameworks and functionalities to better accommodate AI / ML services at the application layer, particularly within edge computing environments, to include potential architectural improvements required to support AI / ML services effectively, e.g., by integrating within edge computing scenarios to optimize AI / ML tasks.

[0010] AI / ML tasks, when executed within the context of edge computing, can leverage various computational models. These models include hierarchical computing, characterized by a structured layout of computational nodes (e.g., central, edge, sub-edge) forming a tree-like hierarchy, and distributed computing, which involves a coordination node overseeing multiple execution nodes. The hierarchical model is illustrated in Figure 2, showing a root node (central or edge services), sub-root nodes (sub-edge services), and leaf nodes (edge services) with no descendants, all playing distinct roles in the computational process. Figure 3 depicts the distributed computing model, where a coordination node (central, edge, or extended edge services) assigns and distributes AI / ML sub-tasks among several execution nodes (edge or extended edge services).

[0011] In a hierarchical computing architecture, the processing of AI / ML tasks involves both upward and downward data flows. During upward processing (e.g., Hierarchical Learning), leaf nodes forward their intermediate AI / ML outputs to sub-root nodes for further computation. These sub-root nodes process the received data to generate new intermediate outputs, which are then sent to the root node for final computation. The downward process (e.g., Hierarchical Inference) reverses this flow, with the root node distributing its intermediate outputs to sub-root nodes, which in turn forward these outputs to leaf nodes for the final computation phase. In a distributed computing setup (e.g., Horizontal Federated Learning), the coordination node selects appropriate execution nodes to handle various sub-tasks of an AI / ML project, distributing these tasks accordingly to optimize computational efficiency and resource utilization.

[0012] Relevant components integral to the architecture of edge computing for AI / ML tasks are Cloud Application Server (CAS), Cloud Enabler Server (CES), Edge Configuration Server (ECS), Edge Enabler Server (EES), and Edge Application Server (EAS). CAS acts as the primary server in the cloud environment, orchestrating the deployment and management of applications. CES provides necessary support services to CAS, facilitating cloud-based resources efficient utilization. ECS is tasked with the configuration and management of edge computing resources, while EES and EAS offer enabling services and application deployment at the edge, respectively. A root node may be CAS, CES, EES or EAS. A subroot node may be EES or EAS. A leaf node may be EES or EAS. A coordination node may be CAS, CES, or ECS. An execution node may be EES or EAS.

[0013] A problematic aspect of the existing solutions is that there is no seamless integration to support and accommodate application layer AI / ML services in edge computing scenarios. Thus, leading to suboptimal and inefficient AI / ML services at the application layer in environments that use edge computing technologies.

[0014] A further problematic aspect of the existing solutions is the inefficient management and configuration of AI / ML tasks within edge or distributed systems, and that they do not handle the dynamic nature of edge computing environments, leading to suboptimal resource utilization, increased latency, and potential bottlenecks in data processing and task execution.

[0015] A further problematic aspect of the existing solutions is the inefficient management of the interactions and dependencies between the nodes involved in AI / ML tasks, not considering the dynamic nature of these tasks, which are usually dependent on real-time conditions.

[0016] A further problematic aspect of the existing solutions is the scalability and adaptability to cope with growing volume of data generated by user devices. This leads to degraded network performance. SUMMARY

[0017] The invention is set out in the appended set of claims.

[0018] An object of the invention is to enhance AI / ML Enablement services in a communications network for assisting edge computing operations, enabling efficient management, configuration and execution of execution of AI / ML tasks in edge computing scenarios.

[0019] This disclosure provides a method for assisting edge computing in a communications network. The method comprises transmitting from a first network node to a second network node a request for assistance for edge computing, wherein the request includes at least one of the role of the consumer in an edge computing architecture, the type of edge computing operations and the type of assistance information; determining at the second network node information required for the request, particularly wherein the information comprises any one of downstream entities and services needed, time windows recommendations for computing task distribution or for intermediate output delivery, and candidate execution node list; initiating at the second network node operations to generate assistance information for edge computing, particularly wherein the initiating comprises subscribing or requesting to an Application Data Analytics Enabler Server (ADAES) for edge load analytics, requesting member LIE selection, requesting recommended time windows with QoS, requesting network data analytics, or requesting resource configurations from a Network Resource Management (NRM) Server; and transmitting from the second network node to the first network node the assistance information for edge computing, wherein the assistance information for edge computing includes any one of: the outcomes of the operations initiated by the second network node, the information required for the request, and information for decision making at the consumer on its edge computing operations. In some embodiments, the role of the consumer in an edge computing architecture comprises any one of: root node of a hierarchical computing process, sub-root node of a hierarchical computing process, leaf node of a hierarchical computing process, coordination node of a distributed computing process, and execution node of a distributed computing process. In some embodiments, the type of edge computing operations comprises any one of: task distribution, intermediate output delivery, execution node selection. In some embodiments, the type of assistance information comprises any one of: time window for computing task distribution, intermediate output delivery, and candidate execution node list. In some embodiments, initiating operations at the AI / ML Enablement Server comprises requesting analytics or configurations from network functions. In some embodiments, the assistance information for edge computing comprises any one of: time windows recommendation for computing task distribution, time windows recommendation for intermediate output delivery, and candidate execution node list. In some embodiments, the second network node is an Artificial Intelligence / Machine Learning (AI / ML) Enablement Server, and the first network node is a consumer, particularly wherein the consumer is any one of a Cloud Application Server (CAS), a Cloud Enabler Server (CES), an Edge Configuration Server (ECS), an Edge Enabler Server (EES), and an Edge Application Server (EAS).

[0020] An aspect of the invention relates to a method performed by a first network node for assisting edge computing in a communications network. The method comprises transmitting from a first network node to a second network node a request for assistance for edge computing, wherein the request includes at least one of the role of the consumer in an edge computing architecture, the type of edge computing operations and the type of assistance information; and receiving at the first network node from the second network node the assistance information for edge computing, wherein the assistance information for edge computing includes any one of: the outcomes of the operations initiated by the AI / ML Enablement Server, the information required for the request, and information for decision making at the consumer on its edge computing operations. In some embodiments, the role of the consumer in an edge computing architecture comprises any one of: root node of a hierarchical computing process, sub-root node of a hierarchical computing process, leaf node of a hierarchical computing process, coordination node of a distributed computing process, and execution node of a distributed computing process. In some embodiments, the type of edge computing operations comprises any one of: task distribution, intermediate output delivery, execution node selection. In some embodiments, the type of assistance information comprises any one of: time window for computing task distribution, intermediate output delivery, and candidate execution node list. In some embodiments, the assistance information for edge computing comprises any one of: time windows recommendation for computing task distribution, time windows recommendation for intermediate output delivery, and candidate execution node list. In some embodiments, the second network node is an Artificial Intelligence / Machine Learning (AI / ML) Enablement Server, and the first network node is a consumer, particularly wherein the consumer is any one of a Cloud Application Server (CAS), a Cloud Enabler Server (CES), an Edge Configuration Server (ECS), an Edge Enabler Server (EES), and an Edge Application Server (EAS).

[0021] An aspect of the invention relates to a method performed by a second network node for assisting edge computing in a communications network. The method comprises receiving at a second network node from a first network node a request for assistance for edge computing, wherein the request includes at least one of the role of the consumer in an edge computing architecture, the type of edge computing operations and the type of assistance information; determining at the second network node information required for the request, particularly wherein the information comprises any one of downstream entities and services needed, time windows recommendations for computing task distribution or for intermediate output delivery, and candidate execution node list; initiating at the second network node operations to generate assistance information for edge computing, particularly wherein the initiating comprises subscribing or requesting to an Application Data Analytics Enabler Server (ADAES) for edge load analytics, requesting member UE selection, requesting recommended time windows with QoS, requesting network data analytics, or requesting resource configurations from a Network Resource Management (NRM) Server; and transmitting from the second network node to the first network node the assistance information for edge computing, wherein the assistance information for edge computing includes any one of: the outcomes of the operations initiated by the AI / ML Enablement Server, the information required for the request, and information for decision making at the consumer on its edge computing operations. In some embodiments, the role of the consumer in an edge computing architecture comprises any one of: root node of a hierarchical computing process, sub-root node of a hierarchical computing process, leaf node of a hierarchical computing process, coordination node of a distributed computing process, and execution node of a distributed computing process. In some embodiments, the type of edge computing operations comprises any one of: task distribution, intermediate output delivery, execution node selection. In some embodiments, the type of assistance information comprises any one of: time window for computing task distribution, intermediate output delivery, and candidate execution node list. In some embodiments, initiating operations at the AI / ML Enablement Server comprises requesting analytics or configurations from network functions. In some embodiments, the assistance information for edge computing comprises any one of: time windows recommendation for computing task distribution, time windows recommendation for intermediate output delivery, and candidate execution node list. In some embodiments, the second network node is an Artificial Intelligence / Machine Learning (AI / ML) Enablement Server, and the first network node is a consumer, particularly wherein the consumer is any one of a Cloud Application Server (CAS), a Cloud Enabler Server (CES), an Edge Configuration Server (ECS), an Edge Enabler Server (EES), and an Edge Application Server (EAS). Other aspects of the invention relate to mobile network nodes, particularly a first network node (116, 700), and a second network node (117, 800) configured to perform the respective methods as described herein. Other aspects of the invention relate to computer program and computer program products.

[0022] In some embodiments, the first network node is a consumer 116. In some embodiments, the second network node is an Artificial Intelligence / Machine Learning Enablement Server (AI / ML Enablement Server) 117. The consumer may be any one of a Cloud Application Server (CAS), a Cloud Enabler Server (CES), an Edge Configuration Server (ECS), an Edge Enabler Server (EES), and an Edge Application Server (EAS).

[0023] Advantageously, the solution disclosed herein allows efficient management, configuration and execution of execution of AI / ML tasks in edge computing scenarios, by means of a tailored approach to edge computing assistance within the edge computing architecture, by enhancing AI / ML Enablement services in a communications network for assisting edge computing operations.

[0024] Advantageously, the solution disclosed herein enables efficient allocation of resources and services, optimizing the edge computing operations by providing informed assistance based on the user context and network conditions.

[0025] Advantageously, the solution disclosed herein provides a dynamic and adaptive solution for edge computing operations, leveraging analytics and data to produce analytics and recommendations for improved performance and efficiency.

[0026] Additional objectives, features and advantages of the concepts disclosed herein will be apparent from the following description, claims and drawings, or may be learned by practice of the described technologies and concepts as set forth herein.

[0027] BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to best describe the manner in which the disclosed concepts may be implemented, as well as define other objects, advantages and features of the disclosure, a more particular description is provided below and is illustrated in the appended drawings. Understanding that these drawings depict only exemplary embodiments of the invention and are not therefore to be considered to be limiting in scope, the examples will be described and explained with additional specificity and detail through the use of the accompanying drawings.

[0029] Figure 1 illustrates an example networked system in accordance with particular embodiments of the solution described herein.

[0030] Figure 2 illustrates an example block diagram showing network entities in a mobile communications network according to particular embodiments of the solution described herein.

[0031] Figure 3 illustrates an example block diagram showing network entities in a mobile communications network according to particular embodiments of the solution described herein.

[0032] Figure 4 illustrates an example signaling diagram showing a procedure according to particular embodiments of the solution described herein.

[0033] Figure 5 illustrates an example flowchart showing a method performed by a mobile network node according to particular embodiments of the solution described herein.

[0034] Figure 6 illustrates an example flowchart showing a method performed by a mobile network node according to particular embodiments of the solution described herein.

[0035] Figure 7 illustrates an example block diagram of a mobile network node configured in accordance with particular embodiments of the solution described herein.

[0036] Figure 8 illustrates an example block diagram of a mobile network node configured in accordance with particular embodiments of the solution described herein.

[0037] Figure 9 illustrates an example block diagram of a virtualized environment.

[0038] DETAILED DESCRIPTION

[0039] The invention will now be described in detail hereinafter with reference to the accompanying drawings, in which examples of embodiments or implementations of the invention are shown. The invention may, however, be embodied or implemented in many different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of present invention to those skilled in the art. It should also be noted that these embodiments are not mutually exclusive. Components from one embodiment may be tacitly assumed to be present / used in another embodiment. These embodiments of the disclosed subject matter are presented as teaching examples and are not to be construed as limiting the scope of the disclosed subject matter. For example, certain details of the described embodiments may be modified, omitted, or expanded upon without departing from the scope of the described subject matter.

[0040] The example embodiments described herein arise in the context of a telecommunications network, including but not limited to a telecommunications network that conforms to and / or otherwise incorporates aspects of a fifth generation (5G) architecture. Figure 1 is an example networked system 100 in accordance with example embodiments of the present disclosure. Figure 1 specifically illustrates User Equipment (UE) 101 , which may be in communication with a (Radio) Access Network (RAN) 102 and Access and Mobility Management Function (AMF) 106 and User Plane Function (UPF) 103. The AMF 106 may, in turn, be in communication with core network services including Session Management Function (SMF) 107 and Policy Control Function (PCF) 111. The core network services may also be in communication with an Application Server / Application Function (AS / AF) 113. Other networked services also include Network Slice Selection Function (NSSF) 108, Authentication Server Function (AUSF) 105, User Data Management (UDM) 112, Network Exposure Function (NEF) 109, Network Repository Function (NRF) 110, Unified Data Repository (UDR) 114, Network Data Analytics Function (NWDAF) 115, and Data Network (DN) 104. In some example implementations of embodiments of the present disclosure, each one of the entities in the networked system 100 are considered to be a Network Function (NF). One or more additional instances of the NFs may be incorporated into the networked system.

[0041] The solution described herein aims to enhance AI / ML Enablement services in a communications network for assisting edge computing operations, enabling efficient management, configuration and execution of execution of AI / ML tasks in edge computing scenarios.

[0042] This disclosure provides a method for assisting edge computing in a communications network. The method comprises transmitting from a first network node to a second network node a request for assistance for edge computing, wherein the request includes at least one of the role of the consumer in an edge computing architecture, the type of edge computing operations and the type of assistance information; determining at the second network node information required for the request, particularly wherein the information comprises any one of downstream entities and services needed, time windows recommendations for computing task distribution or for intermediate output delivery, and candidate execution node list; initiating at the second network node operations to generate assistance information for edge computing, particularly wherein the initiating comprises subscribing or requesting to an Application Data Analytics Enabler Server (ADAES) for edge load analytics, requesting member LIE selection, requesting recommended time windows with QoS, requesting network data analytics, or requesting resource configurations from a Network Resource Management (NRM) Server; and transmitting from the second network node to the first network node the assistance information for edge computing, wherein the assistance information for edge computing includes any one of: the outcomes of the operations initiated by the second network node, the information required for the request, and information for decision making at the consumer on its edge computing operations. In some embodiments, the role of the consumer in an edge computing architecture comprises any one of: root node of a hierarchical computing process, sub-root node of a hierarchical computing process, leaf node of a hierarchical computing process, coordination node of a distributed computing process, and execution node of a distributed computing process. In some embodiments, the type of edge computing operations comprises any one of: task distribution, intermediate output delivery, execution node selection. In some embodiments, the type of assistance information comprises any one of: time window for computing task distribution, intermediate output delivery, and candidate execution node list. In some embodiments, initiating operations at the AI / ML Enablement Server comprises requesting analytics or configurations from network functions. In some embodiments, the assistance information for edge computing comprises any one of: time windows recommendation for computing task distribution, time windows recommendation for intermediate output delivery, and candidate execution node list. In some embodiments, the second network node is an Artificial Intelligence / Machine Learning (AI / ML) Enablement Server, and the first network node is a consumer, particularly wherein the consumer is any one of a Cloud Application Server (CAS), a Cloud Enabler Server (CES), an Edge Configuration Server (ECS), an Edge Enabler Server (EES), and an Edge Application Server (EAS).

[0043] An aspect of the invention relates to a method performed by a first network node for assisting edge computing in a communications network. The method comprises transmitting from a first network node to a second network node a request for assistance for edge computing, wherein the request includes at least one of the role of the consumer in an edge computing architecture, the type of edge computing operations and the type of assistance information; and receiving at the first network node from the second network node the assistance information for edge computing, wherein the assistance information for edge computing includes any one of: the outcomes of the operations initiated by the AI / ML Enablement Server, the information required for the request, and information for decision making at the consumer on its edge computing operations. In some embodiments, the role of the consumer in an edge computing architecture comprises any one of: root node of a hierarchical computing process, sub-root node of a hierarchical computing process, leaf node of a hierarchical computing process, coordination node of a distributed computing process, and execution node of a distributed computing process. In some embodiments, the type of edge computing operations comprises any one of: task distribution, intermediate output delivery, execution node selection. In some embodiments, the type of assistance information comprises any one of: time window for computing task distribution, intermediate output delivery, and candidate execution node list. In some embodiments, the assistance information for edge computing comprises any one of: time windows recommendation for computing task distribution, time windows recommendation for intermediate output delivery, and candidate execution node list. In some embodiments, the second network node is an Artificial Intelligence / Machine Learning (AI / ML) Enablement Server, and the first network node is a consumer, particularly wherein the consumer is any one of a Cloud Application Server (CAS), a Cloud Enabler Server (CES), an Edge Configuration Server (ECS), an Edge Enabler Server (EES), and an Edge Application Server (EAS).

[0044] An aspect of the invention relates to a method performed by a second network node for assisting edge computing in a communications network. The method comprises receiving at a second network node from a first network node a request for assistance for edge computing, wherein the request includes at least one of the role of the consumer in an edge computing architecture, the type of edge computing operations and the type of assistance information; determining at the second network node information required for the request, particularly wherein the information comprises any one of downstream entities and services needed, time windows recommendations for computing task distribution or for intermediate output delivery, and candidate execution node list; initiating at the second network node operations to generate assistance information for edge computing, particularly wherein the initiating comprises subscribing or requesting to an Application Data Analytics Enabler Server (ADAES) for edge load analytics, requesting member UE selection, requesting recommended time windows with QoS, requesting network data analytics, or requesting resource configurations from a Network Resource Management (NRM) Server; and transmitting from the second network node to the first network node the assistance information for edge computing, wherein the assistance information for edge computing includes any one of: the outcomes of the operations initiated by the AI / ML Enablement Server, the information required for the request, and information for decision making at the consumer on its edge computing operations. In some embodiments, the role of the consumer in an edge computing architecture comprises any one of: root node of a hierarchical computing process, sub-root node of a hierarchical computing process, leaf node of a hierarchical computing process, coordination node of a distributed computing process, and execution node of a distributed computing process. In some embodiments, the type of edge computing operations comprises any one of: task distribution, intermediate output delivery, execution node selection. In some embodiments, the type of assistance information comprises any one of: time window for computing task distribution, intermediate output delivery, and candidate execution node list. In some embodiments, initiating operations at the AI / ML Enablement Server comprises requesting analytics or configurations from network functions. In some embodiments, the assistance information for edge computing comprises any one of: time windows recommendation for computing task distribution, time windows recommendation for intermediate output delivery, and candidate execution node list. In some embodiments, the second network node is an Artificial Intelligence / Machine Learning (AI / ML) Enablement Server, and the first network node is a consumer, particularly wherein the consumer is any one of a Cloud Application Server (CAS), a Cloud Enabler Server (CES), an Edge Configuration Server (ECS), an Edge Enabler Server (EES), and an Edge Application Server (EAS).

[0045] This disclosure also provides mobile network nodes, particularly a first network node (116, 700), and a second network node (117, 800) configured to perform the respective methods as described herein. In some embodiments, the first network node is a consumer 116. In some embodiments, the second network node is an Artificial Intelligence / Machine Learning Enablement Server (AI / ML Enablement Server) 117. The consumer may be any one of a Cloud Application Server (CAS), a Cloud Enabler Server (CES), an Edge Configuration Server (ECS), an Edge Enabler Server (EES), and an Edge Application Server (EAS).

[0046] This disclosure also provides the corresponding computer program and computer program products comprising code, for example in the form of a computer program, that when run on processing circuitry of the mobile network nodes causes the mobile network nodes to perform the disclosed methods.

[0047] Advantageously, the solution disclosed herein allows efficient management, configuration and execution of execution of AI / ML tasks in edge computing scenarios, by means of a tailored approach to edge computing assistance within the edge computing architecture, by enhancing AI / ML Enablement services in a communications network for assisting edge computing operations.

[0048] Advantageously, the solution disclosed herein enables efficient allocation of resources and services, optimizing the edge computing operations by providing informed assistance based on the user context and network conditions.

[0049] Advantageously, the solution disclosed herein provides a dynamic and adaptive solution for edge computing operations, leveraging analytics and data to produce analytics and recommendations for improved performance and efficiency.

[0050] Hereinafter, drawings showing examples of embodiments of the solution are described in detail.

[0051] Figure 4 is a signaling diagram illustrating a procedure for assisting edge computing in a communications network. The procedure is performed by a first network node (116, 700), and a second network node (117, 800). In some embodiments, the first network node is a consumer 116. In some embodiments, the second network node is an Artificial Intelligence / Machine Learning Enablement Server (AI / ML Enablement Server) 117. The consumer may be any one of a Cloud Application Server (CAS), a Cloud Enabler Server (CES), an Edge Configuration Server (ECS), an Edge Enabler Server (EES), and an Edge Application Server (EAS).

[0052] An AI / ML task can be seen as a special computing task, and edge computing can be used for completing the AI / ML tasks. A CAS, CES, ECS, EES or EAS may have different roles in different types of edge computing, e.g. hierarchical computing (with one root node (e.g., CAS, CES, EES or EAS), the root has one or more children which also known as sub-root node(s) (e.g., EES or EAS), and multiple leaf nodes (e.g., EES or EAS) which with no children), distributed computing (with one coordination node (e.g., CAS, CES, or ECS) and multiple execution nodes (e.g., EES or EAS)).

[0053] The following pre-conditions apply:

[0054] - An AI / ML task can be treated as a special computing task, consumer (e.g. CAS, CES, ECS, EES or EAS) uses edge computing method for completing the AI / ML tasks.

[0055] - The consumer decides its role in the edge computing architecture (e.g. hierarchical computing, distributed computing) for an AI / ML task, and also the type of edge computing operations, based on its local configuration. - The consumer decides that assistance from AI / ML Enablement Server for management and configuration to support the edge computing process is needed.

[0056] The corresponding procedure in detail is as follows:

[0057] In step 1 , the Consumer (e.g. CAS, CES, ECS, EES, EAS) subscribes / requests to the AI / ML Enablement Server for assistance of an edge computing process. The request message includes:

[0058] Role of the consumer in an edge computing architecture (e.g. root node, sub-root node or leaf node of a hierarchical computing process, coordination node or execution node of a distributed computing process).

[0059] - Type of edge computing operations (e.g. task distribution, intermediate output delivery, execution node selection) to indicate the operations that the assistance information be used for.

[0060] - Assistance information type (e.g. time window(s) for computing task distribution and / or intermediate output delivery, candidate execution node list) to indicate the assistance information needed.

[0061] In step 2, the AI / ML Enablement Server derives information for the request, determines downstream entities and services need, for example:

[0062] Time window(s) recommendation for computing task distribution if the consumer is a root node in a hierarchical computing process or a coordination node in a distribution computing process.

[0063] Time window(s) recommendation for intermediate output delivery is the consumer is a leaf node in a hierarchical computing process.

[0064] - Candidate execution node list provisioning if the consumer is a coordination node of a distributed computing process.

[0065] In step 3, the AI / ML Enablement Server performs operations according to the determination in step 2 to generate assistance information. For example, the AI / ML Enablement Server may subscribe / request analytics from ADAE Server (e.g. edge load analytics), request assistance information or configurations from 5GC NFs (e.g. Member UE selection, recommended time windows with QoS, network data analytics), request resource configurations from NRM Server.

[0066] In step 4, the AI / ML Enablement Server notifies / responds to the consumer with the assistance information for the edge computing process. The consumer (e.g. CAS, CES, ECS, EES, EAS) may use the assistance information for decision making on its edge computing operations.

[0067] Hereinafter, flowcharts showing examples of embodiments of the solution are described in detail.

[0068] The embodiments correspond to methods performed by and involving a first network node (116, 700), and a second network node (117, 800). In some embodiments, the first network node is a consumer 116. In some embodiments, the second network node is an Artificial Intelligence / Machine Learning Enablement Server (AI / ML Enablement Server) 117. The consumer may be any one of a Cloud Application Server (CAS), a Cloud Enabler Server (CES), an Edge Configuration Server (ECS), an Edge Enabler Server (EES), and an Edge Application Server (EAS).

[0069] Figure 5 is a flowchart illustrating a method performed by the first network node for assisting edge computing in a communications network.

[0070] In step S-501 , the first network node transmits to a second network node a request for assistance for edge computing, wherein the request includes at least one of the role of the consumer in an edge computing architecture, the type of edge computing operations and the type of assistance information.

[0071] In step S-502, the first network node receives from the second network node the assistance information for edge computing, wherein the assistance information for edge computing includes any one of: the outcomes of the operations initiated by the AI / ML Enablement Server, the information required for the request, and information for decision making at the consumer on its edge computing operations.

[0072] In some embodiments, the role of the consumer in an edge computing architecture comprises any one of: root node of a hierarchical computing process, sub-root node of a hierarchical computing process, leaf node of a hierarchical computing process, coordination node of a distributed computing process, and execution node of a distributed computing process.

[0073] In some embodiments, the type of edge computing operations comprises any one of: task distribution, intermediate output delivery, execution node selection. In some embodiments, the type of assistance information comprises any one of: time window for computing task distribution, intermediate output delivery, and candidate execution node list.

[0074] In some embodiments, the assistance information for edge computing comprises any one of: time windows recommendation for computing task distribution, time windows recommendation for intermediate output delivery, and candidate execution node list.

[0075] In some embodiments, the second network node is an Artificial Intelligence / Machine Learning (AI / ML) Enablement Server, and the first network node is a consumer, particularly wherein the consumer is any one of a Cloud Application Server (CAS), a Cloud Enabler Server (CES), an Edge Configuration Server (ECS), an Edge Enabler Server (EES), and an Edge Application Server (EAS).

[0076] Figure 6 is a flowchart illustrating a method performed by the second network node for assisting edge computing in a communications network.

[0077] In step S-601 , the second network node receives from a first network node a request for assistance for edge computing, wherein the request includes at least one of the role of the consumer in an edge computing architecture, the type of edge computing operations and the type of assistance information.

[0078] In step S-602, the second network node determines information required for the request, particularly wherein the information comprises any one of downstream entities and services needed, time windows recommendations for computing task distribution or for intermediate output delivery, and candidate execution node list.

[0079] In step S-603, the second network node initiates operations to generate assistance information for edge computing, particularly wherein the initiating comprises subscribing or requesting to an Application Data Analytics Enabler Server (ADAES) for edge load analytics, requesting member LIE selection, requesting recommended time windows with QoS, requesting network data analytics, or requesting resource configurations from a Network Resource Management (NRM) Server.

[0080] In step S-604, the second network node transmits to the first network node the assistance information for edge computing, wherein the assistance information for edge computing includes any one of: the outcomes of the operations initiated by the AI / ML Enablement Server, the information required for the request, and information for decision making at the consumer on its edge computing operations. In some embodiments, the role of the consumer in an edge computing architecture comprises any one of: root node of a hierarchical computing process, sub-root node of a hierarchical computing process, leaf node of a hierarchical computing process, coordination node of a distributed computing process, and execution node of a distributed computing process.

[0081] In some embodiments, the type of edge computing operations comprises any one of: task distribution, intermediate output delivery, execution node selection.

[0082] In some embodiments, the type of assistance information comprises any one of: time window for computing task distribution, intermediate output delivery, and candidate execution node list.

[0083] In some embodiments, initiating operations at the AI / ML Enablement Server comprises requesting analytics or configurations from network functions.

[0084] In some embodiments, the assistance information for edge computing comprises any one of: time windows recommendation for computing task distribution, time windows recommendation for intermediate output delivery, and candidate execution node list.

[0085] In some embodiments, the second network node is an Artificial Intelligence / Machine Learning (AI / ML) Enablement Server, and the first network node is a consumer, particularly wherein the consumer is any one of a Cloud Application Server (CAS), a Cloud Enabler Server (CES), an Edge Configuration Server (ECS), an Edge Enabler Server (EES), and an Edge Application Server (EAS).

[0086] Figure 7 is a block diagram illustrating elements of a mobile network node 700 of a mobile communications network. In some embodiments, the mobile network node 700 is a consumer 116. As shown, the mobile network node may include network interface circuitry 701 (also referred to as a network interface) configured to provide communications with other nodes of the core network and / or the network. The mobile network node may also include a processing circuitry 702 (also referred to as a processor) coupled to the network interface circuitry, and memory circuitry 703 (also referred to as memory) coupled to the processing circuitry. The memory circuitry 703 may include computer readable program code that when executed by the processing circuitry 702 causes the processing circuitry to perform operations according to embodiments disclosed herein. According to other embodiments, processing circuitry 702 may be defined to include memory so that a separate memory circuitry is not required. As discussed herein, operations of the mobile network node may be performed by processing circuitry 702 and / or network interface circuitry 701 . For example, processing circuitry 702 may control network interface circuitry 701 to transmit communications through network interface circuitry 701 to one or more other network nodes and / or to receive communications through network interface circuitry from one or more other network nodes. Moreover, modules may be stored in memory 703, and these modules may provide instructions so that when instructions of a module are executed by processing circuitry 702, processing circuitry 702 performs respective operations (e.g., operations discussed below with respect to Example Embodiments relating to core network nodes).

[0087] Figure 8 is a block diagram illustrating elements of a mobile network node 800 of a mobile communications network. In some embodiments, the mobile network node 800 is an AI / ML Enablement Server 117. As shown, the mobile network node may include network interface circuitry 801 (also referred to as a network interface) configured to provide communications with other nodes of the core network and / or the network. The mobile network node may also include a processing circuitry 802 (also referred to as a processor) coupled to the network interface circuitry, and memory circuitry 803 (also referred to as memory) coupled to the processing circuitry. The memory circuitry 803 may include computer readable program code that when executed by the processing circuitry 802 causes the processing circuitry to perform operations according to embodiments disclosed herein. According to other embodiments, processing circuitry 802 may be defined to include memory so that a separate memory circuitry is not required. As discussed herein, operations of the mobile network node may be performed by processing circuitry 802 and / or network interface circuitry 801 . For example, processing circuitry 802 may control network interface circuitry 801 to transmit communications through network interface circuitry 801 to one or more other network nodes and / or to receive communications through network interface circuitry from one or more other network nodes. Moreover, modules may be stored in memory 803, and these modules may provide instructions so that when instructions of a module are executed by processing circuitry 802, processing circuitry 802 performs respective operations (e.g., operations discussed below with respect to Example Embodiments relating to core network nodes).

[0088] Figure 9 is a block diagram illustrating a virtualization environment 900 in which functions implemented by some embodiments may be virtualized. In the present context, virtualizing means creating virtual versions of apparatuses or devices which may include virtualizing hardware platforms, storage devices and networking resources. As used herein, virtualization can be applied to any device described herein, or components thereof, and relates to an implementation in which at least a portion of the functionality is implemented as one or more virtual components. Some or all of the functions described herein may be implemented as virtual components executed by one or more virtual machines (VMs) implemented in one or more virtual environments 900 hosted by one or more of hardware nodes, such as a hardware computing device that operates as a network node, UE, core network node, or host. Further, in embodiments in which the virtual node does not require radio connectivity (e.g., a core network node or host), then the node may be entirely virtualized. In some embodiments, the virtualization environment 900 includes components defined by the O-RAN Alliance, such as an O-Cloud environment orchestrated by a Service Management and Orchestration Framework via an 0-2 interface.

[0089] Applications 902 (which may alternatively be called software instances, virtual appliances, network functions, virtual nodes, virtual network functions, etc.) are run in the virtualization environment Q400 to implement some of the features, functions, and / or benefits of some of the embodiments disclosed herein.

[0090] Hardware 904 includes processing circuitry, memory that stores software and / or instructions executable by hardware processing circuitry, and / or other hardware devices as described herein, such as a network interface, input / output interface, and so forth. Software may be executed by the processing circuitry to instantiate one or more virtualization layers 906 (also referred to as hypervisors or virtual machine monitors (VMMs)), provide VMs 908a and 908b (one or more of which may be generally referred to as VMs 908), and / or perform any of the functions, features and / or benefits described in relation with some embodiments described herein. The virtualization layer 906 may present a virtual operating platform that appears like networking hardware to the VMs 908.

[0091] The VMs 908 comprise virtual processing, virtual memory, virtual networking or interface and virtual storage, and may be run by a corresponding virtualization layer 906. Different embodiments of the instance of a virtual appliance 902 may be implemented on one or more of VMs 908, and the implementations may be made in different ways. Virtualization of the hardware is in some contexts referred to as network function virtualization (NFV). NFV may be used to consolidate many network equipment types onto industry standard high volume server hardware, physical switches, and physical storage, which can be located in data centers, and customer premise equipment.

[0092] In the context of NFV, a VM 908 may be a software implementation of a physical machine that runs programs as if they were executing on a physical, non-virtualized machine. Each of the VMs 908, and that part of hardware 904 that executes that VM, be it hardware dedicated to that VM and / or hardware shared by that VM with others of the VMs, forms separate virtual network elements. Still in the context of NFV, a virtual network function is responsible for handling specific network functions that run in one or more VMs 908 on top of the hardware 904 and corresponds to the application 902.

[0093] Hardware 904 may be implemented in a standalone network node with generic or specific components. Hardware 904 may implement some functions via virtualization. Alternatively, hardware 904 may be part of a larger cluster of hardware (e.g. such as in a data center or CPE) where many hardware nodes work together and are managed via management and orchestration 910, which, among others, oversees lifecycle management of applications 902. In some embodiments, hardware 904 is coupled to one or more radio units that each include one or more transmitters and one or more receivers that may be coupled to one or more antennas. Radio units may communicate directly with other hardware nodes via one or more appropriate network interfaces and may be used in combination with the virtual components to provide a virtual node with radio capabilities, such as a radio access node or a base station. In some embodiments, some signaling can be provided with the use of a control system 912 which may alternatively be used for communication between hardware nodes and radio units.

[0094] Embodiments within the scope of the present invention may also include computer-readable media for carrying or having computer-executable instructions or data structures stored thereon. Such computer-readable media can be any available media that can be accessed by a general purpose or special purpose computer. By way of example, and not limitation, such tangible computer-readable media can comprise RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to carry or store desired program code means in the form of computer-executable instructions or data structures. When information is transferred or provided over a network or another communications connection (either hardwired, wireless, or combination thereof) to a computer, the computer properly views the connection as a computer-readable medium. Thus, any such connection is properly termed a computer- readable medium. Combinations of the above should also be included within the scope of the tangible computer-readable media.

[0095] Computer-executable instructions include, for example, instructions and data which cause a general purpose computer, special purpose computer, or special purpose processing device to perform a certain function or group of functions. Computer-executable instructions also include program modules that are executed by computers in standalone or network environments. Generally, program modules include routines, programs, objects, components, and data structures that perform particular tasks or implement particular abstract data types. Computer executable instructions, associated data structures, and program modules represent examples of the program code means for executing steps of the methods disclosed herein. The particular sequence of such executable instructions or associated data structures represent examples of corresponding acts for implementing the functions described in such steps.

[0096] Those of skill in the art will appreciate that other embodiments of the invention may be practiced in network computing environments with many types of computer system configurations, including personal computers, hand-held devices, multi-processor systems, microprocessor-based or programmable consumer electronics, network PCs, minicomputers, mainframe computers, and the like. Embodiments may also be practiced in distributed computing environments where tasks are performed by local and remote processing devices that are linked (either by hardwired links, wireless links, or by a combination thereof) through a communications network. In a distributed computing environment, program modules may be located in both local and remote memory storage devices.

[0097] Communication at various stages of the described system can be performed through a local area network, a token ring network, the Internet, a corporate intranet, 802.11 series wireless signals, fiber-optic network, radio or microwave transmission, etc. Although the underlying communication technology may change, the fundamental principles described herein are still applicable.

[0098] The various embodiments described above are provided by way of illustration only and should not be construed to limit the invention. For example, the principles herein may be applied to any remotely controlled device. Further, those of skill in the art will recognize that communication between the remote the remotely controlled device need not be limited to communication over a local area network but can include communication over infrared channels, Bluetooth or any other suitable communication interface. Those skilled in the art will readily recognize various modifications and changes that may be made to the present invention without following the example embodiments and applications illustrated and described herein, and without departing from the scope of the present disclosure.

[0099] The terminology used herein is for the purpose of describing various embodiments only and is not intended to be limiting of example embodiments. As used herein, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "includes," "including," "comprises," and "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, or components, and combinations thereof, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, or components, and combinations thereof. Further, all terms used in the claims are to be interpreted according to their ordinary meaning in the technical field, unless explicitly defined otherwise herein. All references to ""a / an / the element, apparatus, component, means, module, step, etc."" are to be interpreted openly as referring to at least one instance of the element, apparatus, component, means, module, step, etc., unless explicitly stated otherwise. The steps of any method disclosed herein do not have to be performed in the exact order disclosed, unless explicitly stated.

Claims

CLAIMS1 . A method for assisting edge computing in a communications network, the method comprising: transmitting (S-501) from a first network node to a second network node a request for assistance for edge computing, wherein the request includes at least one of the role of the consumer in an edge computing architecture, the type of edge computing operations and the type of assistance information; determining (S-602) at the second network node information required for the request, particularly wherein the information comprises any one of downstream entities and services needed, time windows recommendations for computing task distribution or for intermediate output delivery, and candidate execution node list; initiating (S-603) at the second network node operations to generate assistance information for edge computing, particularly wherein the initiating comprises subscribing or requesting to an Application Data Analytics Enabler Server, ADAES, for edge load analytics, requesting member LIE selection, requesting recommended time windows with QoS, requesting network data analytics, or requesting resource configurations from a Network Resource Management, NRM, Server; and transmitting (S-604) from the second network node to the first network node the assistance information for edge computing, wherein the assistance information for edge computing includes any one of: the outcomes of the operations initiated by the second network node, the information required for the request, and information for decision making at the consumer on its edge computing operations.

2. The method of claim 1 , wherein the role of the consumer in an edge computing architecture comprises any one of: root node of a hierarchical computing process, sub-root node of a hierarchical computing process, leaf node of a hierarchical computing process, coordination node of a distributed computing process, and execution node of a distributed computing process.

3. The method of any one of claims from claim 1 to claim 2, wherein the type of edge computing operations comprises any one of: task distribution, intermediate output delivery, execution node selection.

4. The method of any one of claims from claim 1 to claim 3, wherein the type of assistance information comprises any one of: time window for computing task distribution, intermediate output delivery, and candidate execution node list.

5. The method of any one of claims from claim 1 to claim 4, wherein initiating operations at the AI / ML Enablement Server comprises requesting analytics or configurations from network functions.

6. The method of any one of claims from claim 1 to claim 5, wherein the assistance information for edge computing comprises any one of: time windows recommendation for computing task distribution, time windows recommendation for intermediate output delivery, and candidate execution node list.

7. The method of any one of claims from claim 1 to claim 6, wherein the second network node is an Artificial Intelligence / Machine Learning, AI / ML, Enablement Server, and the first network node is a consumer, particularly wherein the consumer is any one of a Cloud Application Server, CAS, a Cloud Enabler Server, CES, an Edge Configuration Server, ECS, an Edge Enabler Server, EES, and an Edge Application Server, EAS.

8. A method performed by a first network node for assisting edge computing in a communications network, the method comprising: transmitting (S-501 ) from a first network node to a second network node a request for assistance for edge computing, wherein the request includes at least one of the role of the consumer in an edge computing architecture, the type of edge computing operations and the type of assistance information; and receiving (S-502) at the first network node from the second network node the assistance information for edge computing, wherein the assistance information for edge computing includes any one of: the outcomes of the operations initiated by the AI / ML Enablement Server, the information required for the request, and information for decision making at the consumer on its edge computing operations.

9. The method of claim 8, wherein the role of the consumer in an edge computing architecture comprises any one of: root node of a hierarchical computing process, sub-root node of a hierarchical computing process, leaf node of a hierarchical computing process, coordination node of a distributed computing process, and execution node of a distributed computing process.

10. The method of any one of claims from claim 8 to claim 9, wherein the type of edge computing operations comprises any one of: task distribution, intermediate output delivery, execution node selection.11 . The method of any one of claims from claim 8 to claim 10, wherein the type of assistance information comprises any one of: time window for computing task distribution, intermediate output delivery, and candidate execution node list.

12. The method of any one of claims from claim 8 to claim 11 , wherein the assistance information for edge computing comprises any one of: time windows recommendation for computing task distribution, time windows recommendation for intermediate output delivery, and candidate execution node list.

13. The method of any one of claims from claim 8 to claim 12, wherein the second network node is an Artificial Intelligence / Machine Learning, AI / ML, Enablement Server, and the first network node is a consumer, particularly wherein the consumer is any one of a Cloud Application Server, CAS, a Cloud Enabler Server, CES, an Edge Configuration Server, ECS, an Edge Enabler Server, EES, and an Edge Application Server, EAS.

14. A method performed by a second network node for assisting edge computing in a communications network, the method comprising: receiving (S-601) at a second network node from a first network node a request for assistance for edge computing, wherein the request includes at least one of the role of the consumer in an edge computing architecture, the type of edge computing operations and the type of assistance information; determining (S-602) at the second network node information required for the request, particularly wherein the information comprises any one of downstream entities and services needed, time windows recommendations for computing task distribution or for intermediate output delivery, and candidate execution node list; initiating (S-603) at the second network node operations to generate assistance information for edge computing, particularly wherein the initiating comprises subscribing or requesting to an Application Data Analytics Enabler Server, ADAES, for edge load analytics, requesting member LIE selection, requesting recommended time windows with QoS, requesting network data analytics, or requesting resource configurations from a Network Resource Management, NRM, Server; andtransmitting (S-604) from the second network node to the first network node the assistance information for edge computing, wherein the assistance information for edge computing includes any one of: the outcomes of the operations initiated by the AI / ML Enablement Server, the information required for the request, and information for decision making at the consumer on its edge computing operations.

15. The method of claim 14, wherein the role of the consumer in an edge computing architecture comprises any one of: root node of a hierarchical computing process, sub-root node of a hierarchical computing process, leaf node of a hierarchical computing process, coordination node of a distributed computing process, and execution node of a distributed computing process.

16. The method of any one of claims from claim 14 to claim 15, wherein the type of edge computing operations comprises any one of: task distribution, intermediate output delivery, execution node selection.

17. The method of any one of claims from claim 14 to claim 16, wherein the type of assistance information comprises any one of: time window for computing task distribution, intermediate output delivery, and candidate execution node list.

18. The method of any one of claims from claim 14 to claim 17, wherein initiating operations at the AI / ML Enablement Server comprises requesting analytics or configurations from network functions.

19. The method of any one of claims from claim 14 to claim 18, wherein the assistance information for edge computing comprises any one of: time windows recommendation for computing task distribution, time windows recommendation for intermediate output delivery, and candidate execution node list.

20. The method of any one of claims from claim 14 to claim 19, wherein the second network node is an Artificial Intelligence / Machine Learning, AI / ML, Enablement Server, and the first network node is a consumer, particularly wherein the consumer is any one of a Cloud Application Server, CAS, a Cloud Enabler Server, CES, an Edge Configuration Server, ECS, an Edge Enabler Server, EES, and an Edge Application Server, EAS.21 . Apparatus for assisting edge computing in a communications network, the apparatus comprising a processor and a memory, the memory containing instructions executable by- T1 - the processor such that the apparatus is operable to perform the method of any one of claims from claim 8 to claim 13.

22. Apparatus for assisting edge computing in a communications network, the apparatus comprising a processor and a memory, the memory containing instructions executable by the processor such that the apparatus is operable to perform the method of any one of claims from claim 14 to claim 20.

23. A system comprising an apparatus as claimed in claim 21 , and an apparatus as claimed in claim 22.

24. A computer-implemented system comprising one or more processors and one or more computer storage media storing computer-usable instructions that, when used by the one or more processors, cause the one or more processors to perform a method according to any one of claims from claim 8 to claim 20.

25. A computer program comprising instructions which, when executed on at least one processor, cause the at least one processor to perform a method according to any of claims from claim 8 to claim 20.

26. A computer program product, embodied on a non-transitory machine-readable medium, comprising instructions which are executable by a processor, causing the processor to perform the method according to any of claims from claim 8 to claim 20.

Images