Method for providing communication and computing service sessions

Abstract

Various embodiments describe a method for providing a communication and computing service session, the method including the steps of one or more control plane functions receiving computation availability information including information and communication availability information including information, and selecting, in response to the computation availability information and the communication availability information, a service provision profile specifying an allocation of communication and computing service tasks among a mobile terminal, one or more other computing devices, and one or more devices of a mobile communications network. Selection diagram: Figure 11

Description

[Technical Field]

[0001] The present disclosure relates to a method for providing a communication and computing services communication session. [Background technology]

[0002] Various services, such as artificial intelligence-based services related to augmented reality and control, require high computational effort. Therefore, it is desirable to distribute them across multiple devices, especially on cloud devices that can provide high computing power. On the other hand, it requires computational resources, for example, when the results of such services are needed by a mobile terminal and need to be transmitted to the mobile terminal, possibly with a certain quality of service, such as latency. However, performing the processing exclusively on the mobile terminal may not be possible due to the limited computing power and undesirable energy consumption of the mobile terminal.

[0003] Therefore, an efficient approach to providing communication and computing services is desirable. Summary of the Invention

[0004] According to various embodiments, a method of providing a communication and computing service session (for a mobile terminal) is provided, the method including: ● one or more control plane functions of a mobile communications network connecting the mobile terminal to one or more other computing devices receive, at least in part, from a distributed computing management component, computing availability information comprising information about what computing resources are available to provide communication and computing service sessions at the mobile terminal, the one or more other computing devices, and one or more devices of the mobile communications network; ● one or more control plane functions receiving, at least in part, communication availability information from one or more user plane components of the mobile communication network, the communication availability information including information about what communication resources are available for providing communication and computing service sessions at the mobile terminal and at one or more devices of the mobile communication network; ● one or more control plane functions selecting, according to the computation availability information and the communication availability information, a service provision profile specifying the distribution of communication and computation service tasks among the mobile terminal, the one or more other computing devices, and one or more devices of the mobile communication network; one or more control plane functions requesting a distributed computing management component to provision computing resources of the mobile terminal, one or more other computing devices, and one or more devices of the mobile communications network in accordance with a selected service provision profile for providing a communications and computing service session; and ● A step in which one or more control plane functions request one or more user plane components of the mobile communications network to provide communication resources for the mobile terminal and one or more devices of the mobile communications network in accordance with a service provision profile selected to provide a communication and computing service session.

[0005] According to a further embodiment, there is provided a communications system (or one or more components thereof, in particular a control plane component of a mobile communications network) configured to perform the above-mentioned method.

[0006] Various examples corresponding to aspects of the present disclosure are described below: Example 1 is a method for providing the above-described communication and computing service session.

[0007] A second embodiment of the present invention relates to the method of the first embodiment, and further includes the step of selecting a service provision profile and requesting provision of computing resources and provision of communication resources for each communication and computing service session.

[0008] Example 3 includes, in the method of example 1 or 2, one or more control plane functions receiving, together with a communications and computing service session establishment request, a portion of computation availability information and / or communications availability information from the mobile terminal, the portion including information about what communications and / or computing resources are available at the mobile terminal to provide the communications and computing service session.

[0009] Example 4 is the method of example 3, wherein the communication and computing service session is a protocol data unit session.

[0010] Example 5 is a method of any one of Examples 1 to 4, including a step in which one or more control plane functions receive a portion of availability information from a radio access network, the portion including information about what communication and computing resources are available to provide communication and computing service sessions in the radio access network of the mobile radio network.

[0011] Example 6 is the method of any one of Examples 1 to 5, wherein the one or more control plane functions are one or more core network control plane functions of the mobile communications network.

[0012] Example 7 is the method of any one of Examples 1 to 6, wherein the mobile communication network is a 6G mobile communication network.

[0013] Example 8 is the method of any one of Examples 1 to 7, wherein the distributed computing management component is a distributed computing agent configured to perform communication and computing service tasks and manages those implemented on the mobile terminal, one or more other computing devices, and / or one or more devices of the mobile communications network.

[0014] Example 9 is the method of any one of Examples 1 to 8, further comprising: End-to-end latency of communication and computation service sessions, and Energy efficiency in delivering communication and computational services and sessions selecting a service provision profile according to a service provision target including at least one of:

[0015] Example 10 is a method of any one of Examples 1 to 9, including a step in which one or more control plane functions receive a plurality of alternative service provision profiles and select a service provision profile from among the plurality of alternative service provision profiles, each of the plurality of alternative service provision profiles specifying a respective distribution of communication and computation service tasks among the mobile terminal, one or more other computing devices, and / or one or more devices of the mobile communications network.

[0016] Example 11 is the method of example 10, including receiving a plurality of alternative service provision profiles from the application layer component.

[0017] Example 12, in the method of any one of Examples 1 to 11, includes a step in which one or more control plane functions of a mobile communication network connecting a mobile terminal to one or more other computing devices receive service requirement information regarding requirements for a communication and computing service session for the mobile terminal from an application and service control function, and select a service provision profile according to the service requirement information.

[0018] Example 13 is the method of example 12, including receiving service requirement information from an application layer component.

[0019] Example 14 is a method of any one of Examples 1 to 13, wherein one or more user plane components of the mobile communications network include a user plane function that connects the mobile terminal to one or more other computing devices.

[0020] Example 15 is the method of example 13, wherein one or more devices of the mobile communication network include one or more further computing devices in addition to the user plane function unit, and the user plane function unit connects the one or more further computing devices to one or more other computing devices.

[0021] Example 16 is the method of any one of Examples 1 to 15, wherein the one or more other computing devices are edge and / or cloud computing devices.

[0022] Example 17 is a method of any one of Examples 1 to 16, wherein one or more devices of the mobile communication network are devices providing a core network function and / or a radio access network function of the mobile communication network.

[0023] Example 18 is a method of any one of Examples 1 to 16, wherein the one or more control plane functions include one or more of an Access and Mobility Management Function, a Session Management Function, a Distributed Computing Controller, and a Policy Control Function.

[0024] Example 19, in the method of any one of Examples 1 to 18, further includes a step in which one or more control plane functions receive an indication of an energy consumption target and select a service provision profile according to the energy consumption target.

[0025] Example 20, in the method of any one of Examples 1 to 19, includes a step in which one or more control plane functions receive energy consumption information including information regarding energy consumption profiles of a mobile terminal, one or more other computing devices, and one or more devices of a mobile communication network connecting the mobile terminal to the one or more other computing devices, and select a service provision profile according to the energy consumption information.

[0026] A twenty-first embodiment is a communication system configured to perform the method of any one of the first to twentieth embodiments.

[0027] It should be noted that one or more features of any of the above embodiments may be combined with any one of the other embodiments. In particular, embodiments described in the context of a device are equally valid for a method.

[0028] According to a further embodiment, there is provided a computer readable medium comprising a computer program and instructions which, when executed by a computer, cause the computer to perform the method of any one of the above embodiments.

[0029] In the drawings, generally, like reference numerals refer to the same parts throughout the various views. The drawings are not necessarily to scale, but rather have been exaggerated with emphasis on illustrating the principles of the invention. In the following description, various aspects are described with reference to the following drawings: [Brief explanation of the drawings]

[0030] [Figure 1] Figure 1 shows a 5G wireless communication system. [Figure 2] Figure 2 shows a 6G communication system. [Figure 3] Figure 3 shows the link and operation profile. [Figure 4] FIG. 4 illustrates the selection of multiple links and operation profiles. [Figure 5]FIG. 5 shows the provision of 3D video as an example of a connectivity and computing service. [Figure 6] Figure 6 shows a flow chart illustrating the procedure for providing connectivity and computational services. [Figure 7] FIG. 7 shows a flow chart illustrating the procedure for providing connectivity and computation services. [Figure 8] FIG. 8 shows a flow chart illustrating the procedure for providing connectivity and computation services. [Figure 9] FIG. 9 shows a flow chart illustrating the procedure for providing connectivity and computation services. [Figure 10] FIG. 10 shows the provision of multiple link and computation profiles of the application layer to the control plane. [Figure 11] FIG. 11 shows a flow chart illustrating a method for providing a communication and computing service session according to an embodiment.

[0031] The following detailed description refers to the accompanying drawings which show, by way of example, specific details and aspects of the present disclosure in which the invention may be practiced. Other aspects may be used, and structural, logical, and electrical changes may be made, without departing from the scope of the present disclosure. Various aspects of the present disclosure are not necessarily mutually exclusive, as some aspects of the present disclosure may be combined with one or more other aspects of the present disclosure to form new aspects.

[0032] Various examples are described in more detail below.

[0033] FIG. 1 shows a wireless (i.e., mobile) communication system 100 configured in accordance with 5G (Fifth Generation).

[0034] The wireless communication system 100 includes a mobile wireless terminal device 102, such as a user equipment (UE), nano equipment (NE), etc. The mobile wireless terminal device 102, also called a subscriber terminal, forms the terminal side, while the other components of the wireless communication system 100 described below are part of the mobile wireless communication network side, i.e., part of a mobile wireless communication network (e.g., Public Land Mobile Network, PLMN), also called a telecommunication network. The telecommunication network can form a connection between the mobile terminal 102 and other computing devices, such as edge devices or cloud devices (e.g., located on the Internet).

[0035] Further, the wireless communication system 100 includes a radio access network 103, which may include multiple radio access network nodes, i.e., base stations, configured to provide wireless access in accordance with fifth generation (5G) radio access technology (5G New Radio). Although 5G is used as an example, the wireless communication system 100 may also be configured in accordance with Long Term Evolution (LTE) or other mobile wireless communication standards. Each radio access network node 103 is capable of providing wireless communication with mobile wireless terminal devices 102 over an air interface. It should be noted that the radio access network 103 may include any number of radio access network nodes.

[0036] The wireless communication system 100 further includes a Core Network (CN, here 5GC) 108 including an Access and Mobility Management Function (AMF) 101 connected to the RAN 103 and a Unified Data Management (UDM) 104. Here, and in the following examples, the UDM may further comprise an actual UE subscription database, known for example as a Unified Data Repository (UDR). The Core Network 108 further includes an Authentication Server Function (AUSF) 109 and one or more Policy Control Functions (PCFs), in this example a first PCF 106 and a second PCF 107.

[0037] The core network 108 further includes multiple Session Management Functions (SMFs), in this example a first Session Management Function (SMF) 110 and a second Session Management Function (SMF) 112, and multiple User Plane Functions (UPFs), in this example a first User Plane Function (UPF) 111 and a second User Plane Function (UPF) 113. The SMFs 110 and 112 are for handling Protocol Data Unit (PDU) sessions, i.e., for creating, updating, and removing PDU sessions and managing session contexts with the User Plane Functions (UPFs).

[0038] The core network 108 further includes an application function (AF) 105. Although the AF 105 is shown as being directly connected to the SMFs 110, 112 and PCFs 106, 107, it may also be connected thereto via a Network Exposure Function (NEF), particularly if the AF 105 is maintained by a third party (i.e., other than the operator of the mobile radio communication system 100).

[0039] The AF 105 allows an application to request the 5G system 100 to support specific Quality of Service (QoS) policies for the UE 102 that establishes a PDU session to provide communication services to that application. The core network 119 may further include components such as a Network Data Analytics Function (NWDAF) and a Network Repository Function (NRF), which are not shown in FIG. 1 . The NWDAF is responsible for providing network analysis and / or forecasting information upon request from a network function. For example, a network function may request specific analysis information regarding the load level of a particular network slice instance. The NRF can be queried by any connected network function (e.g., AMF, SMF, PCF) to obtain information for discovering other network functions.

[0040] The 5G core network control plane, together with the distributed computing (DC) platform, can form the control plane of the 6G core network, as shown in Figure 2.

[0041] 2 illustrates a 6G communication system 200. The communication network 200 includes a 5G control plane 201, which may include, for example, an NEF 202, an AUSF 203, a UDM 204, an NWDAF 205, an AMF 206, an NRF 207, an SMF 208, and a PCF 209.

[0042] The 5GC control plane 201 is coupled to a radio access network 210 to which a mobile terminal (UE) 211 is connected. The 5GC control plane 201, together with a DC controller 212, forms the control plane of a 6G core network 213. One or more UPFs 214 can route 5G user plane traffic between the RAN 210 and one or more server computers 215 that implement service processing functions, e.g., neural network processing layers, to provide the services.

[0043] The DC controller 212, for example, coordinates computing resources on the user side and the service side (e.g., those of a cloud application).

[0044] The DC controller 212 controls DC resources instantiated within the UE 211, the 5G user plane components (RAN 210 and UPF 214), and the application server(s) 215. The DC resources may include accelerators (e.g., GPUs, FPGAs).

[0045] An application may involve computational tasks such as artificial intelligence (i.e., machine learning). Examples include applications for robotics control and augmented reality (for mobile devices), which may require computationally intensive tasks (and therefore energy-intensive tasks). Tasks for such applications may be distributed to multiple components of the communication system 100, such as the UE 102 itself and one or more cloud devices connected to the mobile communication networks 103, 108 (and thus to the mobile terminal 102) via the UPFs 111, 113 (including offloading computationally intensive tasks requiring high energy consumption to network endpoints).

[0046] Thus, providing an application includes performing computing tasks as well as providing communication services (i.e., providing connectivity) to enable communication between the components performing those computing tasks. Accordingly, the services provided by a communication system are referred to herein as communication and computing services (because they include not only communication tasks but also computing tasks).

[0047] According to various embodiments, an application requiring communication and computing services, i.e., the application layer, may indicate (service) requirements for the communication and computing services, such as latency or response time (e.g., specifying the period of time for which a result is required to be provided in a real-time application), reliability (i.e., the limit of the risk that the service will fail) or redundancy level, accuracy or error rate (e.g., due to errors caused by communication errors), etc. These service requirements may be provided, for example, by a mobile terminal (using the application) or, for example, by an AF.

[0048] The control plane of the communication system 100 selects a specific (communication) link and computing profile (also called a service provisioning profile) for a communication-computing service according to the service requirements. The link and computing profile may be selected from a set of link and computing profiles, each of which corresponds to a respective option for dividing tasks for the communication-computing service. The application layer may also directly request one of the link and computing profiles.

[0049] FIG. 3 shows a link and operation profile 300.

[0050] In this example, it is assumed that a UE (generally a mobile terminal) 301, a user plane network function of a communication network 302 (to which the mobile terminal 301 is connected), and one or more hosting components 302 in the communication edge (also referred to as one or more other computing devices (other than the mobile terminal) outside the communication network) should perform computing tasks for the communication and computing services.

[0051] Thus, the link and computing profile 300 defines the (service provisioning) requirements for the computing resources of the UE 301 for the communication and computing services, the requirements for the user plane network functions of the communication network 302, and the requirements for the computing resources of one or more hosting devices 303 in the communication edge for the communication and computing services, i.e., specifies what tasks are performed on the UE 301 and what tasks are performed in the UE 301, the user plane functions (i.e., intra-network components) of the communication network 302, and one or more hosting devices 303 in the communication edge, i.e., specifies the allocation of tasks to provide each service. Furthermore, the link and computing profile 300 can define the required quality (e.g., QoS) of the link 304 between the UE 301 and the user plane network function 302, and the link 305 between the user plane network function 302 and the communication edge 304.

[0052] The one or more hosting devices 303 may include, for example, one or more cloud devices connected to the UE via the UPF. Thus, the requirements for the computing resources of the one or more hosting devices 303 may also be understood as requirements for the computing resources that the UPF should provide (using one or more hosting devices 303 in the communication edge, e.g., edge and / or cloud devices).

[0053] In other words, according to various embodiments, tasks related to communication and computing services are distributed across components, including in-network components, i.e., network functional parts of a communication network, i.e., components that specifically use in-network computing. For example, in-network computing uses programmable network elements to perform computations on the route before traffic reaches an edge server or a cloud server (or mobile device). Thus, data processing can be distributed to include data processing at the edge of the (telecommunications) network (or outside the network), in the network (in-network computing), and at the end user side (e.g., closer to where the data is generated). For example, computationally intensive and energy-consuming portions of a service can be offloaded to network endpoints, and in-network computing power can be used to reduce service latency, e.g., by using hardware accelerators embedded in network devices. This approach can help reduce latency and bandwidth usage by processing data locally rather than sending it to a centralized data center, and can be used in a variety of computationally intensive applications, such as:

[0054] ●Extended Reality (XR) use cases: entertainment and gaming applications, advanced visualization methods, smart homes, emotional computing, autonomous vehicles, and robotics. Computationally intensive artificial intelligence (AI) applications: image recognition tasks, video processing, 3D video streaming, computer vision, using machine learning (ML) and neural networks. ●Web 3.0 (related to the decentralized internet): In-network computing could help reduce latency and bandwidth usage by processing data locally rather than sending it to a centralized data center.

[0055] As described in more detail below, the application layer can request alternative link and computation profiles corresponding to different processing partitioning options (i.e., different task distribution options). The communications network control plane can then select a profile based on constraints on communications and computation resources (e.g., based on what these components can provide, i.e., their available resources) of the mobile terminal 301, the UP NF 302, and the hosting components within the communications edge 303. The computation resources can be features such as support for deep neural network (DNN) layers or various accelerators, e.g., graphic processing units (GPUs), application-specific integrated circuits (ASICs), field programmable gate arrays (FPGAs), to better handle (using logic) DNN operations.

[0056] This selection may be performed, for example, with the goal of optimizing service performance and energy efficiency of the service offering.

[0057] FIG. 4 illustrates the selection of multiple links and operation profiles.

[0058] For example, a PDU session is first established for a UE 401 (or its user) that wishes to use a certain (communication / computing) service.

[0059] To execute a service session including individual application tasks (i.e., tasks for providing a service) executed in the UE 401, for example, in the networks 402, 404 (i.e., by in-network computing), including the RAN and core network, and the telecommunications edge 403 (connected by the UPF 404), an application layer (e.g., an application function 405 receiving a service request) issues alternative link and computing profiles 406 to the (core network) control plane 407 (i.e., one or more CP components) of the (mobile) communications network, i.e., requests that the control plane 407 select (and thus implement) one of the link and computing profiles 406. The alternative link and computing profiles 406 can be considered as an indication of the combined link and computing (service provision) requirements issued by the application layer (and may correspond to the service requirements, because the application layer determines that they satisfy the service requirements).

[0060] The network control plane (CP) 407 selects a link and computing profile from the published link and computing profiles 406 based on resource availability, e.g., based on knowledge of connection resources specified by the user plane NFs 402, 404, and calculates the resources to obtain (at least in part) from a distributed computing (DC) management entity (or component) 408. For example, the control plane 407 retrieves information about the availability of computing resources of elements in the network and communication edges from the DC management component 408. The DC management component 408 may or may not be part of the control plane 407 of the telecommunications network.

[0061] The mobile terminal 401 may provide information about its available computing resources during PDU session establishment.

[0062] The selection of the link and computing profile 406 by the control plane 407 may be based on a combined target of service performance and energy efficiency. Thus, a balance between service performance and energy efficiency may be achieved by the control plane 407. To this end, various components potentially involved in the provision of the service (e.g., the mobile terminal 401 or its components, the intra-network components 402 and 404, and the telecommunications edge component 403) may provide information about their energy consumption profile (in the case of the telecommunications edge component 403, this information may be provided by the UPF 404). The energy consumption profile of a device or component is an indicator or measure of the energy efficiency of the computing components in the UE, network, or edge. It may, for example, specify energy consumption for a particular computing load, i.e., a mapping (or correlation) between computing resource availability and energy consumption. Alternative link and computing profiles 406 may, for example, not include an energy consumption profile.

[0063] Figure 5 shows an example of connectivity and computation services.

[0064] As in the above example, the mobile terminal 501, the intra-network component 502, and the communication edge component 503 are involved in providing a service (i.e., providing connectivity and computation for the service), i.e., providing the service through mobile terminal (UE) resources, intra-network resources, and communication edge resources. The communication edge component 503 is connected to the mobile terminal 501 and the intra-network component 502, for example, via the UPF 504, and the intra-network component 502 is connected to the mobile terminal 501 and the communication edge component 503, for example, via the access network and / or the UPF 505.

[0065] For the provision of application services, the telecommunications edge component 503 provides application service 1; data streams are forwarded to and / or from the intra-network component 502; the intra-network component 502 executes application service 2 based on data streams forwarded to and / or from the mobile terminal 501; and the mobile terminal 501 executes application service 3. Application services 1, 2, and 3 may be processing layers of a neural network model, which is divided among the mobile terminal 501, the network device 502, and the telecommunications edge component 503 and executed in DC agents 506, 507, and 508.

[0066] Different links and computing profiles may correspond to different variations of this distribution: for example, the tasks of application service 2 may be moved from intra-network component 502 to mobile terminal 501 or telecommunications edge component 503 (resulting in different resource requirements in terms of transmission bandwidth, i.e. connection resources).

[0067] To execute distributed application services, a distributed computing (DC) layer is formed by distributed computing agents 506, 507, and 508 provided as part of (i.e., by one or more of) the mobile terminal 501, the in-network component 502, and the communications edge component 503.

[0068] The procedure for providing connection and computing services, e.g., the application services of FIG. 5, including link and computing profile selection, is described in detail below with reference to FIGS. 6, 7, 8 and 9.

[0069] 6-9 show flow charts illustrating procedures for providing connectivity and computing services.

[0070] As described with reference to FIG. 5, the flow includes mobile terminals 601, 701, 801, and 901, intra-network components 602, 702, 802, and 902, and communication edge components 603, 703, 803, and 903.

[0071] Furthermore, the 6G core network control plane 604, 704, 804, 904 (i.e., one or more components implementing the 6G CN CP, e.g., the 6G CN control plane 201 component and the DC controller 212 (see FIG. 2 )) includes application layer components (e.g., AFs) 605, 705, 805, 905, and (central) DC management components 606, 706, 806, 906 (e.g., corresponding to the DC management component 408) in the flow. The DC management components 606, 706, 806, 906 correspond to, for example, the resource management units of the DC controller 212.

[0072] At 607, the mobile terminal 601 sends a PDU establishment request to the 6G core network control plane 604. This request includes information about the computing resources available for the service at the mobile terminal 601.

[0073] Further, at 608, via application signaling (using the established PDU session), the application layer component 605 is informed of the requested service (e.g., the mobile terminal 601 sends a request for the service to the network, which is received by the AF).

[0074] In 609, the application layer component 605 requests the link and operation profile for the service (i.e., the application session of the mobile terminal 601) from the control plane 604, i.e., requests the control plane 604 to provide resources according to the link and operation profile. Furthermore, in 610, the control plane 604 is informed by the DC management component 606, in this example, about the resources available for the service in the intra-network component 602 and the communication edge component 603.

[0075] At 611, the control plane 604 performs coordinated link and operation selection, i.e., selects link and operation profiles for a service based on: Network status (like in 5GS) DC Resource Availability: At the mobile terminal 601 (availability information provided by the UE in the PDU session establishment request) In-network components 602 and communication edge (e.g., cloud) components (availability information retrieved from the DC control layer, e.g., DC management component 606)

[0076] Continuing with Figure 7, at 712, the control plane 704 requests the DC management component 706 to allocate resources for the service according to the selected link and computing profile. The DC management component 706 notifies the (local) distributed computing agent of the mobile terminal 701, the in-network component 702, and the communication edge component 702 to allocate their resources accordingly.

[0077] Continuing with FIG. 8, at 814, the control plane 804 performs user plane control (e.g., as in a 5G communication system).

[0078] Continuing with Figure 9, at 915, the control plane 904 (after completing the link and compute resource control operations of Figure 8) notifies the application layer 905 of the selected link and compute profile. At 916, the DC management component 906 deploys application components (e.g., containers and / or pods) on the local DC agent. At 917, the application layer 905 starts the deployed application components.

[0079] 6-9, the application layer component 605 requests a link and operation profile for a service from the control plane 604. However, as noted above, the application layer component 605 can provide multiple alternative operation and link profiles to the control plane 604, allowing the control plane 604 to select one of them.

[0080] 10 illustrates providing multiple link and compute profiles of the application layer 1005 to the control plane 1004. The profiles may correspond to different performance targets for the application session. The control plane 1004 then selects one of the alternative compute and link profiles (e.g., "profile b").

[0081] Otherwise, the flow (and associated components) is as described with reference to FIG. 6 (and subsequent flows in FIGS. 7-9).

[0082] In summary, according to various embodiments, a method is provided as shown in FIG.

[0083] FIG. 11 illustrates a flow diagram 1100 illustrating a method for providing a communication and computing service session (i.e., a (communication and computing) session for providing communication and computing services) according to an embodiment.

[0084] At 1101, one or more control plane functions of a mobile communications network connecting a mobile terminal to one or more other computing devices receive, at least in part, from a distributed computing management component, computation availability information including information regarding what computing resources are available for providing communication and computing service sessions at the mobile terminal, the one or more other computing devices, and one or more devices of the mobile communications network.

[0085] At 1102, one or more control plane functions receive communication availability information from one or more user plane components of the mobile communications network, the communication availability information including information regarding what communication resources are available for providing communication and computing service sessions at the mobile terminal and one or more devices of the mobile communications network, at least in part.

[0086] At 1103, one or more control plane functions select a service provision profile that specifies the distribution of communication and computation service tasks among the mobile terminal, one or more other computing devices, and one or more devices of the mobile communications network in response to the computation availability information and the communication availability information.

[0087] At 1104, one or more control plane functions: requesting a distributed computing management component to provide computing resources of the mobile terminal, one or more other computing devices, and one or more devices of the mobile communications network in accordance with a selected service provision profile for provision of a communication and computing service session; and ● Request one or more user plane components of the mobile communications network to provide communication resources for the mobile terminal and one or more devices of the mobile communications network in accordance with the service provision profile selected for the provision of a communication and computing service session.

[0088] In other words, according to various embodiments, tasks are distributed among the mobile terminal, the in-network components (i.e., components of the mobile communication network that serve the mobile terminal, i.e., provide mobile communications to the mobile terminal, i.e., provide Internet access to the mobile terminal), and one or more other computing devices (other than the mobile terminal and not belonging to the mobile communication network, the one or more other computing devices, and the mobile communication network (i.e., components belonging to the mobile communication network are separated, for example, by the UPF (of the mobile communication network)). One or more devices of the mobile communication network (i.e., telecommunications network) that connect the mobile terminal to one or more other computing devices, i.e., the in-network components, are, for example, components that transfer data from one or more other computing devices to the mobile terminal and vice versa. Thus, the one or more other computing devices may, for example, be one or more server devices (implementing one or more data servers) that host (or serve) data, i.e., (data) host devices. A service may be, for example, a provision of data provided by one or more other computing devices, where the service providing the data may involve processing distributed across the mobile terminal, components within the network, and one or more other computing devices.

[0089] It should be noted that the computation availability information and the communication availability information are provided by different entities (respectively a distributed computation management component and one or more user plane components). The distributed computation (DC) management component may be controlled by a control plane component, e.g., a DC controller of the mobile communication network.

[0090] The selection may be based on various criteria such as end-to-end latency and energy efficiency: End-to-end latency: For example, distributing tasks across the network helps distribute energy consumption, but can increase end-to-end latency. As different AI inference models are distributed to different nodes, sharing the results and sending them back to the end user will incur a larger end-to-end latency, which can be calculated by summing the total inference time at each node plus the uplink and downlink transmission times: inference time@node_a + inference time @node_b + inference time@UE + inference time@telcoEdge + t_UL + t_DL < t_max (tolerable end-to-end delay) Even if tasks are distributed across the network, better performance can be achieved if there are resources available at the communication network edge and within the network entities so that the offloaded tasks complete faster. Energy efficiency: If there are energy efficiency criteria in the UE and one of the offered profiles requires the UE to perform computationally intensive tasks, that profile can be discarded based on the following additional information held by the CP: Profile a: Computing in UE + in-network computing + computing at the edge of the communication network Profile b: No computation at UE (no_computation@UE) + computation within the network + computation at the edge of the communication network ---> This can be selected when the UE has limited resources / battery, etc.

[0091] The approach in Figure 11 enables QoE optimization while minimizing energy consumption. For example, QoS flows based on QoS rules are improved, and energy consumption is added as an input using analytical data. This allows for flexible profiles that are more suited to a wider range of use cases, which is beneficial for the sustainability and economic viability of energy-intensive services (e.g., AI-based approaches, XR applications, etc.). The approach in Figure 11 enables fair utilization of network resources, taking into account both computational and link conditions. The computational resources of network elements are considered.

[0092] According to various embodiments, among others, one or more of the following are provided: Link and compute profile selection based on a combination of service performance and energy saving criteria The energy consumption profile provides an indication of the energy efficiency of the computing components in the UE or network. Corresponding logic for PDU session establishment Improvements to the corresponding logic and QoS profiles in the SMF and RAN nodes, resulting in additional parameters for policy and charging control (POC) rules.

[0093] The method may be performed, for example, by one or more control plane components of a communications system (which may include mobile terminals and one or more other computing devices), particularly a communications system such as that shown in FIG. 1.

[0094] The method of FIG. 11 , e.g., components of a corresponding communication system (including a mobile terminal and one or more other computing devices), may be implemented by (or each include) one or more circuits, for example. A “circuit” may be understood as any type of logic implementation entity, which may be a processor or dedicated circuit that executes software stored in memory, firmware, or any combination thereof. Thus, a “circuit” may be a hardwired logic circuit or a programmable logic circuit, e.g., a programmable processor, such as a microprocessor. A “circuit” may also be software, e.g., a processor that executes any type of computer program. Any other type of implementation of each of the above functions may also be understood as a “circuit.”

[0095] While particular embodiments have been described, it will be understood by those skilled in the art that various changes in form and detail may be made therein without departing from the spirit and scope of the embodiments of the present disclosure as defined by the appended claims. The scope of the present invention is therefore indicated by the appended claims, and all changes that come within the meaning and range of equivalency of the claims are therefore intended to be embraced.

Claims

1. 1. A method for providing a communication and computing service session, comprising: one or more control plane functions of a mobile communications network connecting a mobile terminal to one or more other computing devices receiving, at least in part, from a distributed computing management component, computational availability information including information about what computing resources are available to provide the communication and computing service session at the mobile terminal, the one or more other computing devices, and one or more devices of the mobile communications network; the one or more control plane functions receiving, at least in part, communication availability information from one or more user plane components of the mobile communications network, the communication availability information including information about what communication resources are available to provide the communication and computing service session at the mobile terminal and one or more devices of the mobile communications network; selecting, by the one or more control plane functions in response to the computation availability information and the communication availability information, a service provision profile that specifies the distribution of tasks of the communication and computation services among the mobile terminal, the one or more other computing devices, and one or more devices of the mobile communication network; the one or more control plane functions requesting the distributed computing management component to provision computing resources of the mobile terminal, the one or more other computing devices, and one or more devices of the mobile communications network in accordance with a service provision profile selected for providing the communications and computing service session; and the one or more control plane functions requesting one or more user plane components of the mobile communications network to provide communication resources for the mobile terminal and one or more devices of the mobile communications network in accordance with a service provision profile selected for providing the communication and computing service session; A method comprising:

2. 2. The method of claim 1, further comprising the step of selecting the service provision profile and requesting provision of computing resources and provision of communications resources for each communications and computing service session.

3. 2. The method of claim 1, further comprising the step of the one or more control plane functions receiving from the mobile terminal, together with a communications and computing service session establishment request, a portion of the computation availability information and / or communications availability information comprising information about what communications and / or computing resources are available at the mobile terminal to provide the communications and computing service session.

4. 4. The method of claim 3, wherein the communication and computing service session is a protocol data unit session.

5. 2. The method of claim 1, comprising the step of the one or more control plane functions receiving from a radio access network of a mobile radio communications network a portion of availability information comprising information about what communication and computing resources are available to provide the communication and computing service session in the radio access network.

6. 2. The method of claim 1, wherein the one or more control plane functions are one or more core network control plane functions of the mobile communications network.

7. 2. The method of claim 1, wherein the mobile communication network is a 6G mobile communication network.

8. 2. The method of claim 1, wherein the distributed computing management component manages distributed computing agents configured to perform the communication and computing service tasks and implemented on the mobile terminal, the one or more other computing devices, and / or one or more devices of the mobile communications network.

9. 10. The method of claim 1, the end-to-end latency of said communication and computing service session; and Energy efficiency in providing said communication and computing service sessions selecting the service provision profile according to a service provision target including at least one of:

10. 2. The method of claim 1, further comprising the step of: one or more control plane functions receiving a plurality of alternative service provision profiles; and selecting a service provision profile from among the plurality of alternative service provision profiles, each of the plurality of alternative service provision profiles specifying a respective distribution of the communication and computing service tasks between the mobile terminal, the one or more other computing devices, and / or one or more devices of the mobile communications network.

11. 11. The method of claim 10, comprising receiving the plurality of alternative service provision profiles from an application layer component.

12. 2. The method of claim 1, further comprising the step of: one or more control plane functions of a mobile communications network connecting the mobile terminal to one or more other computing devices receiving service requirement information about requirements for a communication and computing service session for the mobile terminal from an application service control function; and selecting the service provision profile in response to the service requirement information.

13. 13. The method of claim 12, including receiving the service requirements information from an application layer component.

14. 14. The method of any one of claims 1 to 13, wherein one or more user plane components of the mobile communications network include a user plane function that connects mobile terminals to one or more other computing devices.

15. A communication system configured to carry out a method according to any one of claims 1 to 13.

Images