Computing power resource management method, system, apparatus, storage medium, and program product

Abstract

A computing power resource management method, a system, an apparatus, a storage medium, and a program product. The method comprises: a computing node sends computing power resource information to a first computing power management function network element.

Description

Computing resource management methods, systems, devices, storage media and software products

[0001] This disclosure claims priority to Chinese patent application No. 202510123545.X, filed on January 24, 2025, the entire contents of which are incorporated herein by reference. Technical Field

[0002] This disclosure relates to the field of communication technology, and in particular to a computing resource management method, system, device, storage medium, and program product. Background Technology

[0003] A computing power network (CPN) is a new type of information infrastructure that allocates and flexibly schedules computing, storage, and network resources on demand across the cloud, network, and edge based on business needs. This network infrastructure possesses the ability to sense, schedule, and orchestrate computing resources, providing converged information and communications technology (ICT) services at the network layer. It represents a new generation of technology architecture and business operation system based on the network.

[0004] The application scenarios of computing power networks include cloud computing, the Internet of Things, smart homes, smart cities, and intelligent transportation, with very wide applications. Through the application of computing power networks, high-speed data transmission and intelligent processing can be achieved, providing efficient, reliable, and secure services for various applications. Summary of the Invention

[0005] Firstly, this disclosure provides a method for managing computing resources, the method comprising:

[0006] The computing node sends computing resource information to the first computing power management function network element.

[0007] Secondly, this disclosure also provides another method for managing computing resources, which includes:

[0008] The first computing power management function network element receives computing resource information sent by the computing nodes;

[0009] The first computing power management function network element manages the computing power resources of computing nodes based on computing power resource information.

[0010] Thirdly, this disclosure provides yet another method for managing computing resources, which includes:

[0011] The first computing power management function network element sends the first information to the first service node. The first information is used to indicate computing power resource information.

[0012] Fourthly, this disclosure provides a communication device, comprising:

[0013] The sending module is used to send computing resource information to the first computing power management function network element.

[0014] Fifthly, this disclosure also provides another communication device, including:

[0015] The receiving module is used to receive computing resource information sent by the computing nodes;

[0016] The management module is used to manage the computing resources of computing nodes based on computing resource information.

[0017] Sixthly, this disclosure provides yet another communication device, comprising:

[0018] The sending module is used to send first information to the first service node. The first information is used to indicate computing power resource information.

[0019] In a seventh aspect, this disclosure provides a computing power management system, which includes a first computing power management function network element for any of the methods provided in the first to third aspects above; or, the computing power management system includes a first computing power management function network element and a second computing power management function network element for any of the methods provided in the first to third aspects above.

[0020] Eighthly, a communication device is provided, comprising: a processor and a memory; the memory storing processor-executable instructions; when the processor is configured to execute the instructions, causing the communication device to implement any of the methods provided in the first to third aspects above.

[0021] A ninth aspect provides a computer-readable storage medium comprising a non-transitory computer-readable storage medium having computer instructions stored thereon, which, when executed on a computer, cause the computer to perform any of the methods provided in the first to third aspects.

[0022] In a tenth aspect, a computer program product comprising computer instructions is provided, which, when executed on a computer, cause the computer to perform any of the methods provided in the first to third aspects. Attached Figure Description

[0023] The accompanying drawings are provided to further understand the technical solutions of this disclosure and constitute a part of the specification. They are used together with the embodiments of this disclosure to explain the technical solutions of this disclosure and do not constitute a limitation on the technical solutions of this disclosure.

[0024] Figure 1 is a computing power distribution diagram of a communication system according to some embodiments.

[0025] Figure 2 is a schematic diagram of a network architecture according to some embodiments.

[0026] Figure 3 is a schematic diagram of another network architecture according to some embodiments.

[0027] Figure 4 is a flowchart of a computing resource management method according to some embodiments.

[0028] Figure 5 is a schematic diagram of a computing resource transmission process according to some embodiments.

[0029] Figure 6 is a schematic diagram of a computing resource transmission process according to some embodiments.

[0030] Figure 7 is a schematic diagram of a computing resource transmission process according to some embodiments.

[0031] Figure 8 is a schematic diagram of a computing resource transmission process according to some embodiments.

[0032] Figure 9 is a schematic diagram of a computing resource transmission process according to some embodiments.

[0033] Figure 10 is a schematic diagram of a computing resource transmission process according to some embodiments.

[0034] Figure 11 is a schematic diagram of a computing resource transmission process according to some embodiments.

[0035] Figure 12 is a schematic diagram of a computing resource transmission process according to some embodiments.

[0036] Figure 13 is a schematic diagram of a computing resource transmission process according to some embodiments.

[0037] Figure 14 is a schematic diagram of a computing resource transmission process according to some embodiments.

[0038] Figure 15 is a schematic diagram of a computing resource transmission process according to some embodiments.

[0039] Figure 16 is a schematic diagram of a computing resource transmission process according to some embodiments.

[0040] Figure 17 is a flowchart of another computing resource management method according to some embodiments.

[0041] Figure 18 is a flowchart of another computing resource management method according to some embodiments.

[0042] Figure 19 is a schematic diagram of a computing resource transmission process according to some embodiments.

[0043] Figure 20 is a schematic diagram of a computing resource transmission process according to some embodiments.

[0044] Figure 21 is a schematic diagram of a computing resource transmission process according to some embodiments.

[0045] Figure 22 is a schematic diagram of a computing resource transmission process according to some embodiments.

[0046] Figure 23 is a schematic diagram of a computing resource transmission process according to some embodiments.

[0047] Figure 24 is a schematic diagram of a computing resource transmission process according to some embodiments.

[0048] Figure 25 is a schematic diagram of a computing resource transmission process according to some embodiments.

[0049] Figure 26 is a schematic diagram of a computing resource transmission process according to some embodiments.

[0050] Figure 27 is a schematic diagram of a computing resource transmission process according to some embodiments.

[0051] Figure 28 is a schematic diagram of a computing resource transmission process according to some embodiments.

[0052] Figure 29 is a schematic diagram of a computing resource transmission process according to some embodiments.

[0053] Figure 30 is a flowchart of another computing resource management method according to some embodiments.

[0054] Figure 31 is a block diagram of a communication device according to some embodiments.

[0055] Figure 32 is a block diagram of another communication device according to some embodiments.

[0056] Figure 33 is a block diagram of another communication device according to some embodiments.

[0057] Figure 34 is a block diagram of a communication device according to some embodiments. Detailed Implementation

[0058] The technical solutions of the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this disclosure, and not all embodiments. Based on the embodiments of this disclosure, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this disclosure.

[0059] Unless the context otherwise requires, throughout the specification and claims, the term "comprise" and its other forms, such as the third-person singular "comprises" and the present participle "comprising," are interpreted as open-ended and encompassing, meaning "including, but not limited to." In the description of the specification, terms such as "one embodiment," "some embodiments," "exemplary embodiments," "example," "specific example," or "some examples," etc., are intended to indicate that a particular feature, structure, material, or characteristic associated with that embodiment or example is included in at least one embodiment or example of this disclosure. The illustrative representations of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics mentioned may be included in any suitable manner in any one or more embodiments or examples.

[0060] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this disclosure, unless otherwise stated, "a plurality of" means two or more.

[0061] In this disclosure, the terms "exemplarily" or "for example" are used to indicate that something is an example, illustration, or description. Any embodiment or design described as "exemplarily" or "for example" in this disclosure should not be construed as being more preferred or advantageous than other embodiments or designs. Rather, the use of the terms "exemplarily" or "for example" is intended to present the relevant concepts in a specific manner.

[0062] In addition, the use of “based on” implies openness and inclusivity, because processes, steps, calculations or other actions “based on” one or more of the stated conditions or values ​​may in practice be based on additional conditions or values ​​beyond those stated.

[0063] Computing power networks are one of the core directions for the development of future mobile networks (such as the future sixth-generation mobile communication technology, 6G). Through the deep integration of communication and computing, computing power networks achieve unified management and dynamic scheduling of distributed computing resources (such as terminal devices, edge servers, cloud computing centers, etc.). This network architecture can provide users or applications with on-demand, real-time, and intelligent computing power services, making "computing power as a service" possible.

[0064] For example, computing power networks include at least the following application scenarios:

[0065] 1) Extended Reality (XR) / Augmented Reality (AR) / Virtual Reality (VR): Computing networks can provide efficient dynamic rendering and real-time computing capabilities for XR / AR / VR, providing high-quality, low-latency rendering services for terminal devices, and enabling seamless interaction between the virtual world and the real world.

[0066] 2) Digital Twin: In the fields of industry, smart cities and healthcare, computing networks can support real-time modeling and simulation of the physical world, enabling prediction, control and optimization of complex systems.

[0067] 3) Autonomous driving and intelligent transportation: The computing network can provide vehicle-road cooperative computing capabilities to realize real-time path planning, environmental perception and fleet collaboration, and support vehicle-to-everything (V2X) communication and edge computing task allocation.

[0068] 4) Industry 4.0 and Smart Manufacturing: Provides localized, low-latency computing power services to support real-time control of industrial equipment. Supports flexible manufacturing and intelligent optimization of production lines.

[0069] Future mobile networks can also be deeply integrated with artificial intelligence (AI) technology, becoming an inherent capability of next-generation networks. This will enable the construction of a more intelligent, efficient, and secure mobile communication network. Here, computing power networks can provide powerful computing support for AI. For example, supporting AI through computing power networks can include at least the following application scenarios:

[0070] 5) AI-enabled networks (AI for net, AI4NET): AI-enabled networks can improve network performance, efficiency, and user service experience through AI models trained on the network. Research on AI-enabled networks mainly includes optimizing traditional algorithms based on AI inference (such as air interface channel coding and modulation), optimizing network functions (such as mobility optimization and session management optimization), and optimizing network operation and maintenance management (such as resource management optimization and planning management optimization).

[0071] 6) Network-enabled AI (NET4AI): This approach leverages networks to provide various support capabilities for AI, enabling more efficient and real-time AI training and inference. NET4AI expands the traditional network scope from connectivity services to computing power, data, and algorithms.

[0072] It is evident that computing networks have a wide range of applications and are one of the core directions for the future development of mobile networks. They aim to provide on-demand, real-time, and efficient computing support for diverse application scenarios through the deep integration of communication and computing.

[0073] To improve the efficiency of computing power management in computing networks, this disclosure provides a computing power management method, including: computing nodes sending computing resource information to a first computing power management function network element. Thus, the computing power management function network element can be used to discover computing resources and collect information from computing nodes, thereby enabling centralized computing resource management, improving resource utilization efficiency, facilitating network performance optimization, and ultimately managing computing resources more efficiently and rationally.

[0074] The technical solutions of the embodiments disclosed herein can be applied to various communication systems, such as Long Term Evolution (LTE), 5th Generation (5G), New Radio (NR), Internet of Things (IoT), Wireless-Fidelity (WiFi), wireless communication related to the 3rd Generation Partnership Project (3GPP), or other wireless communication systems that may emerge in the future, such as the 6th Generation Mobile Communication System (6G), etc. This disclosure does not limit them.

[0075] The technical solutions provided in this disclosure can also be applied to machine-type communication (MTC), device-to-device (D2D) networks, machine-to-machine (M2M) networks, Internet of Things (IoT) networks, or other networks. Here, IoT networks may include, for example, vehicle-to-everything (V2X) networks. The communication methods in V2X systems are collectively referred to as vehicle-to-other-device (V2X), where X can represent anything. For example, V2X may include: vehicle-to-vehicle (V2V) communication, vehicle-to-infrastructure (V2I) communication, vehicle-to-pedestrian (V2P) communication, or vehicle-to-network (V2N) communication, etc.

[0076] Figure 1 is a computing power distribution diagram of a communication system according to some embodiments. As shown in Figure 1, the computing power network may include an application server (AS), an operation, administration and maintenance (OAM) server, a core network data center (CNDC), a radio access network (RAN) pool, an edge server (ES), and user equipment (UE).

[0077] Here, application servers provide computing resources. Taking a 6G system as an example, operators can deploy application servers in the 6G data network. These servers provide computing resources to meet computing demands within the 6G system. For instance, application servers can assist UEs or RANs in training AI models, and also provide computing services to users or external third-party applications. Operators can charge based on the computing resources used by users or external applications.

[0078] The OAM server can be an OAM server for either a RAN node or a core network node. The computing power of the OAM server can be used for training and inference of AI models for network maintenance and optimization. Furthermore, the OAM server in the RAN / core network (CN) can use its additional computing power to train AI models for RAN and CN nodes. The trained AI models can then be transferred to the RAN or CN nodes for AI inference.

[0079] Core Network Data Center: In a Service-Based Architecture (SBA) 6G design, various network functions (NFs) in the core network can be deployed in the cloud and support network virtualization. The core network's computing power is typically concentrated in regional data centers. These data centers not only provide computing services to the 6G system's intranet, such as supporting AI training / inference or other computationally intensive tasks for CN / RAN / UE / AF, but also provide computing power services to external third-party applications.

[0080] Edge servers: Mobile edge computing (MEC) will continue to be deployed in future international mobile telecommunications (IMT) networks. When a user requests low-latency computing services, the network can direct them to the nearest edge computing node. Application scenarios where edge servers provide computing services include AR / VR rendering, autonomous driving, and holographic communication.

[0081] RAN: With the emergence of intelligent computing boards, the computing power of RAN will be enhanced. The concept of computing resource pools can be introduced into the RAN network, which enables RAN nodes to support more powerful computing capabilities to support the computing needs of UE, CN and external third-party applications.

[0082] UE: UE refers to a device with wireless transceiver capabilities, which can be deployed on land, such as indoors or outdoors; on water (such as on ships); and in the air (such as on airplanes, balloons, satellites, and drones). UE can also be called a terminal, terminal device, UE unit, UE station, mobile station, mobile device, UE agent, or UE device, etc. It can be a mobile phone, tablet, computer with wireless transceiver capabilities, VR terminal, AR terminal, wireless terminal in industrial control, wireless terminal in self-driving, wireless terminal in remote medical care, wireless terminal in smart grid, wireless terminal in transportation safety, wireless terminal in smart city, wireless terminal in smart home, etc. This embodiment is not limited to these specific applications. Based on computing power networks, UEs will become more powerful and suitable for performing certain specific computing tasks, such as distributed / joint learning and distributed inference.

[0083] It should be noted that in a communication system, computing power can reside in the UE, RAN, edge server, core network, OAM server, and operator-controlled application server. These computing capabilities can be integrated to support computing power consumers both inside and outside the 6G system. To achieve these requirements, a unified architecture and signaling process for supporting the computing power network needs to be considered and designed to support functions such as computing power discovery, computing power acquisition, computing power request, computing power allocation, computing power usage, and computing power billing.

[0084] Here, computing power refers to the computational capability (or computing resource) of a device. More specifically, computing power is the ability to process information and data to achieve a desired output. Computing power is measured in different units depending on the application scenario: hash operations per second (H / s) for Bitcoin, floating-point operations per second (FLOP / s) for AI and graphics processing, and floating-point operations per second (FLOP / s) for the intelligent society. The demand for computing power in an intelligent society primarily focuses on floating-point operations. Computing power encompasses not only hardware-level computing capabilities but also software algorithm optimization, network architecture design, and data storage and transmission capabilities, making it an indispensable resource in the digital economy era.

[0085] Figure 2 illustrates a network architecture provided in this disclosure. This network architecture can support collaborative control of computing resources.

[0086] As shown in Figure 2, this network architecture introduces a RAN-side computing control entity (CCE), which can also be referred to as the second computing management function network element in this disclosure. The CCE is responsible for the control and management of computing resources on the RAN side. This network architecture also introduces a core network-side computing management function (CMF), which can also be referred to as the first computing management function network element in this disclosure. The CMF is responsible for the control and management of computing resources in the core network and data network. The CCE can connect to multiple xNBs and manage the computing resources of multiple RAN nodes such as next-generation node B (xNB) (e.g., xNB1, xNB2), centralized units (CU), distributed units (DU), radio units (RU), and UEs (e.g., UE1, UE2, UE3, UE4). The CCE further connects with the access and mobility management function (AMF), which can report the computing power status of the RAN side area it is responsible for to the core network, and can also receive computing power resource requests and computing power resource indication information from the core network.

[0087] Here, the CCE is responsible for discovering and recording the computing capabilities of the xNB and UE within its assigned area. Specifically, the UE can report its computing capabilities to the xNB, and the xNB can forward the UE's computing capability information to the CCE. The xNB can also directly report its computing capabilities to the CCE.

[0088] The Computing Function (CMF) is responsible for discovering and recording the computing power information of core network nodes and / or operator-controlled application servers within its assigned area. In some embodiments, the CMF can interact with the Core Network Equipment (CCE) to continuously manage the computing power of xNBs and UEs within the area assigned to each CCE. In some embodiments, the CMF can also interact with application function (AF) elements.

[0089] Alternatively, as shown in Figure 3, which illustrates another network architecture provided in this disclosure, this network architecture can also support collaborative control of computing resources.

[0090] As shown in Figure 3, this network architecture introduces a core network-side CMF, also known as the first computing power management function network element. The CMF is responsible for managing the computing power resources of both the core network and the data network. The CCE can connect to multiple xNBs and manage the computing power resources of multiple RAN nodes such as xNBs, CUs, DUs, RUs, and UEs. The CMF can be deployed as a network function within the core network, interacting with other core network elements to exchange computing power resource information. It can also obtain and / or send computing power resource reports from the RAN side to the RAN through the AMF. Furthermore, the RAN side can directly interact with the CMF to exchange computing power resource information.

[0091] Here, some of the functions of CMF can be referred to in the example shown in Figure 2 above, and will not be repeated here. Compared with Figure 2, the network architecture shown in Figure 3 only introduces CMF network elements on the core network side. This means that CMF needs to be responsible for discovering and recording the computing power information of UEs, RANs, core network nodes, and / or operator-controlled application servers within its area of ​​responsibility. Computing power requests can come from UEs, RANs, core network elements, operator-controlled applications, or third-party applications within the area of ​​responsibility of CMF.

[0092] The technical solution disclosed herein introduces computing power management function network elements (such as CCE, CMF) into the network architecture (Figure 2 or Figure 3). The computing power management function network elements can discover computing power resources and collect information on computing nodes, thereby performing centralized computing power resource management, improving resource utilization efficiency, facilitating network performance optimization, and thus managing computing power resources more efficiently and rationally.

[0093] It should be noted that in the network architecture shown in Figure 2 or Figure 3, the CCE can be an independent RAN-side network element, co-located with RAN nodes, or as part of the RAN functionality. When the CCE is part of the RAN, the xNB can directly report computing power information to the CMF through the AMF, and can also directly report the computing power of the served UEs and / or RAN (CU, DU, RU). The CMF can be an independent core network element, or co-located with existing core network functions, such as as part of the AMF or session management function (SMF). The data plane function (DPF) can be deployed independently of the user plane function (UPF), or co-located with the UPF; furthermore, DPF functionality can be integrated into the UPF. Data transmission between the RAN and CMF can be forwarded through the DPF, or it can be transmitted between the RAN and CMF without passing through the DPF.

[0094] It should be noted that AMF is the access management function of the core network, also known as the mobility management entity (MME), or other core network element functional entities responsible for similar functions. UPF is the user plane management function of the core network, or other core network element functional entities responsible for similar user data forwarding and processing.

[0095] It should be understood that the above-mentioned functions or network elements can be understood as network elements used to implement different functions. For example, they can be combined into network slices as needed. These network elements can be independent devices, or they can be integrated into the same device to implement different functions. They can also be network components in hardware devices, software functions running on dedicated hardware, or virtualization functions instantiated on a platform (e.g., a cloud platform). This disclosure does not limit the specific form of the above-mentioned functions or network elements.

[0096] It should also be understood that the above naming is defined solely for the purpose of distinguishing different functions and should not constitute any limitation on this disclosure. This disclosure does not preclude the possibility of using other naming conventions in future mobile networks. For example, in 6G networks, some or all of the above-mentioned network elements may use the terminology from 5G, or they may use other names, etc.

[0097] It should be noted that Figures 2 and 3 are merely exemplary framework diagrams. The number of network elements included in Figures 2 and 3, as well as the names of each network element, are not limited. In addition to the network elements shown in Figures 2 and 3, the communication system may also include other network elements or devices.

[0098] The application scenarios of the embodiments disclosed herein are not limited. The system architecture and business scenarios described in the embodiments of this disclosure are for the purpose of more clearly illustrating the technical solutions of the embodiments of this disclosure, and do not constitute a limitation on the technical solutions provided by the embodiments of this disclosure. As those skilled in the art will know, with the evolution of network architecture and the emergence of new business scenarios, the technical solutions provided by the embodiments of this disclosure are also applicable to similar technical problems.

[0099] The embodiments provided in this disclosure will now be described in detail with reference to the accompanying drawings.

[0100] As shown in Figure 4, this disclosure provides a method for managing computing resources, the method comprising:

[0101] S101. The computing node sends computing resource information to the first computing power management function network element.

[0102] Here, a computing node refers to a network node with computing capabilities. These nodes can provide data computing, image processing, data analysis, and other related services to meet various business needs. Computing nodes consume computing resources when processing business data; that is, they require resources to process business data. They can also be called computing power nodes, computing resource nodes, or other possible names, which are not limited in this disclosure.

[0103] In some embodiments, the computing node provided in this disclosure may include at least one of the following:

[0104] Terminal equipment, base stations, distributed units, centralized units, radio units, data center nodes, core network functional entities, edge servers, application servers, and nodes dedicated to providing computing resources.

[0105] In some embodiments, computing resource information includes at least one of the following:

[0106] Node identifier, node type, computing resource type, computing resource quantity, available resource quantity, computing location, supported computing service types, computing resource usage status, computing energy characteristics, computing availability time, network status, software capabilities, and security capabilities.

[0107] The following provides a detailed explanation of each computing resource:

[0108] (1) Node Identifier

[0109] Here, the node identifier in the computing resource information is used to indicate the computing node. For example, the node identifier can be an identifier used to uniquely identify the computing node in the network. It can be unique in the communication system and used to distinguish different computing nodes. For example, it can be information such as the node's name, number, or IP address.

[0110] (2) Node Type

[0111] Here, the node type includes at least one of the following:

[0112] Terminal equipment, base stations, distributed units, centralized units, radio units, data center nodes, core network functional entities, edge servers, application servers, and nodes dedicated to providing computing resources.

[0113] (3) Types of computing resources

[0114] Here, the computing resource type is used to indicate the type of computing resources provided by the computing node.

[0115] In some embodiments, the computing resource type includes at least one of the following:

[0116] Central processing unit, graphics processing unit, memory resources, storage resources, acceleration hardware.

[0117] A central processing unit (CPU) is used to perform various computing tasks. This type of computing resource may also include information about the CPU architecture (such as x86, Advanced RISC Machine (ARM), etc.).

[0118] A graphics processing unit (GPU) can perform parallel computing tasks such as graphics rendering and deep learning. This type of computing resource can also include information such as the GPU model.

[0119] Memory resources refer to fast-access storage used to store temporary data.

[0120] Storage resources refer to devices used for long-term data storage, such as hard disk drives (HDDs) and solid-state drives (SSDs). This type of computing resource can also include storage types (such as HDDs and SSDs).

[0121] Accelerated hardware refers to hardware devices specifically designed to accelerate specific types of computing tasks, such as field-programmable gate arrays (FPGAs) and tensor processing units (TPUs).

[0122] (4) Computing resources

[0123] Here, computing power resources can be used to describe the computing power of a computing node.

[0124] In some embodiments, computing resources include at least one of the following:

[0125] Number of central processing unit cores (CPU cores), CPU clock frequency, number of graphics processing unit cores (GPU cores), video memory size, and storage capacity.

[0126] (5) Available resources

[0127] Here, available resources are used to describe the computing power available to a computing node.

[0128] In some embodiments, the amount of available resources includes at least one of the following:

[0129] Computational resource availability, computational resource utilization, available memory size, and available storage.

[0130] (6) Computing power location

[0131] Here, computing power location indicates the geographical location or coverage area of ​​the computing node.

[0132] (7) Supported computing power service types

[0133] Here, the supported computing power service types include at least one of the following:

[0134] Federated learning, distributed learning, distributed inference, AI model training, AI model inference, extended reality rendering, AI data preprocessing, and perceptual data processing.

[0135] For example, federated learning refers to a distributed machine learning framework that allows multiple devices to train models locally and share updates.

[0136] Distributed learning refers to the parallel execution of learning tasks on multiple nodes.

[0137] Distributed reasoning refers to the parallel execution of model reasoning tasks on multiple nodes.

[0138] AI model training refers to the computational task used to train machine learning models.

[0139] XR rendering refers to rendering tasks used in applications such as virtual reality and augmented reality.

[0140] AI data processing refers to the processing of data related to artificial intelligence.

[0141] Sensing data processing refers to the processing of data from sensing devices such as sensors.

[0142] (8) Status of computing resources

[0143] In some embodiments, the computing resource usage status includes at least one of the following:

[0144] Resource congestion or idleness, availability or suspension, resource usage, resource utilization, remaining resources, and response time.

[0145] For example, a resource congestion or idle indicator refers to whether a compute node is currently busy or idle.

[0146] Whether a compute node is available or suspended refers to whether the compute node is currently available or in a suspended state.

[0147] The resource usage indicator refers to the amount of resources currently in use.

[0148] Resource utilization rate refers to the current utilization rate of resources.

[0149] Resource surplus refers to the amount of resources currently remaining.

[0150] Estimated response time refers to the estimated time required to complete the next task.

[0151] Predicted future computing resource status information refers to the future resource status derived from historical data and prediction algorithms.

[0152] In some embodiments, the computing resource usage status includes at least one of the following: the measured computing resource usage status, and the predicted computing resource usage status.

[0153] (9) Computing power characteristics

[0154] In some embodiments, computing power characteristics include at least one of the following:

[0155] Energy consumption, energy efficiency, power status, energy source, energy availability time;

[0156] Here, the power status includes at least one of battery power, remaining power, and unlimited power.

[0157] Energy sources include at least one of renewable energy, non-renewable energy, and renewable energy accounting for a certain percentage.

[0158] Energy availability time includes at least one of the available time periods for renewable energy and the available time periods for non-renewable energy.

[0159] (10) Computing power available time

[0160] Here, computing power availability time refers to the time period or duration during which computing nodes can effectively utilize computing resources.

[0161] (11) Network Status

[0162] In some embodiments, network status includes at least one of the following:

[0163] Aggregate maximum bit rate, uplink bandwidth, downlink bandwidth, latency, packet loss rate, whether remote direct memory access (DMA) is supported, and priority.

[0164] For example, the aggregated maximum bit rate refers to the maximum data transfer rate that a computing node can achieve.

[0165] Uplink bandwidth refers to the rate at which a computing node sends data uplink.

[0166] Downlink bandwidth refers to the rate at which a computing node receives data from the downlink.

[0167] Latency refers to the time required for data to be transmitted in a network.

[0168] Packet loss rate refers to the proportion of data lost during transmission over a network.

[0169] Whether or not RDMA is supported refers to whether the compute node supports remote direct memory access technology.

[0170] Priority refers to the priority of a computing node when processing a task.

[0171] (12) Software capabilities

[0172] In some embodiments, the software capabilities include at least one of the following:

[0173] Operating system name, operating system version, whether virtualization or containerization is supported, and maximum number of concurrent tasks.

[0174] (13) Security capabilities

[0175] In some embodiments, security capabilities include at least one of the following:

[0176] Supported encryption algorithms, supported security isolation mechanisms, and supported privacy protection mechanisms.

[0177] For example, a wireless communication system needs to know the computing resources of a computing node in order to manage the computing resources of the computing node. Therefore, the computing node can send computing resource information to the first computing resource management function network element, so that the first computing resource management function network element can manage the computing resources of the computing node based on the computing resource information sent by the computing node.

[0178] It should be noted that the wireless communication system needs to be able to obtain information about the computing resources of network nodes (dedicated computing nodes, edge servers, operator-controlled data networks, core networks, RAN, UEs), such as computing node identifier, computing resource quantity, computing resource type, location, supported service types, usage status, computing power characteristics, and available time. When there is a computing power request from inside or outside the wireless communication system, the system comprehensively considers the type, quantity, and QoS characteristics of the computing resources required for the computing task, as well as the resource type, quantity, location, supported service types, and available time of the computing node, and schedules the computing task to a suitable computing node, sending the input data of the computing task to the computing node. After the computing node completes the computing task, it sends the output computing results to the computing power requester inside or outside the wireless communication system.

[0179] In this disclosure, the first computing power management function network element can be used to schedule computing power tasks to suitable computing nodes and send the input data of computing power tasks to computing nodes. Thus, based on the first computing power management node, computing power resources can be discovered and information can be collected from computing nodes, thereby enabling centralized management of computing power resources, improving resource utilization efficiency, facilitating network performance optimization, and thus managing computing power resources more efficiently and rationally.

[0180] It should be understood that the first computing power management function network element in this disclosure may also be called the first computing management function network element or the first task management function network element, which can be the CMF provided by this disclosure, and this disclosure does not limit it.

[0181] In one possible implementation, the aforementioned computing node sends computing resource information to the first computing power management function network element, including any one of the following:

[0182] The computing node sends computing resource information to the base station, and the base station sends computing resource information to the first computing resource management function network element.

[0183] The computing node sends computing resource information to the base station, the base station sends computing resource information to the access mobility management function network element, and / or the access mobility management function network element sends computing resource information to the first computing resource management function network element;

[0184] The computing node sends computing resource information to the distributed unit, the distributed unit sends computing resource information to the centralized unit, the centralized unit sends computing resource information to the access mobility management function network element, and / or the access mobility management function network element sends computing resource information to the first computing resource management function network element.

[0185] For example, taking the network architecture shown in Figure 3 above as an example, with the computing node as the terminal device, as shown in Figure 5, the terminal device (UE) sends computing resource information (computing capability or computing resource status report) to the base station (xNB). The base station then sends the computing resource information of the terminal device to the AMF, and the AMF then sends the computing resource information of the terminal device to the first computing power management function network element (CMF).

[0186] For example, the UE can send computing resource information to the CMF. Specifically, the UE can send computing resource information to the AMF via the xNB through non-access stratum (NAS) signaling, and then the AMF can send it to the CMF. Here, the computing resource information can be referred to the detailed description of computing resource information above, and will not be repeated here.

[0187] Alternatively, as shown in Figure 6, the terminal device (UE) sends computing resource information to the base station (xNB), and the base station then sends the computing resource information of the terminal device to the first computing power management function (CMF). That is, the UE can send computing resource information to the xNB, and then the xNB can directly send the computing resource information to the CMF. In some embodiments, before the UE sends computing resource information to the CMF, the CMF can also send computing resource request information to the UE.

[0188] For example, combining the network architecture shown in Figure 3 above, the DU or base station (xNB) can send computing resource information to the CMF. As shown in Figure 7(a), the DU sends computing resource information to the CU, the CU sends the UE's computing resource information to the AMF, and the AMF then sends the UE's computing resources to the CMF. Alternatively, as shown in Figure 7(b), the xNB can send computing resource information to the AMF, and the AMF then sends the xNB's computing resources to the CMF. Furthermore, as shown in Figure 7(c), the xNB directly sends computing resource information to the CMF.

[0189] For example, as shown in Figure 8, a base station (xNB) or CU can send RAN-side computing resource information to the CMF. Alternatively, the base station or CU can send computing resource information (e.g., computing capability or computing resource status report) to the AMF, which then forwards it to the CMF, as shown in Figure 8. Furthermore, the base station or CU can directly send RAN-side computing resource information to the CMF. RAN-side computing resources can originate from dedicated RAN-side computing nodes, RAN-side intelligent computing boards, base stations, CUs, DUs, or RUs. In some embodiments, before the base station or CU sends computing resource information to the CMF, the CMF can also send computing resource request information to the base station or CU.

[0190] For example, combining the network architecture shown in Figure 3 above, as shown in Figure 9, the core network element (NF) sends computing resource information to the computing node (CMF), and the computing nodes also send computing resource information to the CMF. As shown in Figure 9(a), the NF sends computing resource information to the CMF. As shown in Figure 9(b), the computing node sends computing resource information to the CMF.

[0191] In another possible implementation, the computing node sends computing resource information to the first computing power management function network element, including:

[0192] The computing node sends computing resource information to the second computing power management function network element, and / or the second computing power management function network element sends computing resource information to the first computing power management function network element.

[0193] It should be understood that the second computing power management function network element in this disclosure may also be called the second computing management function network element or the second task management function network element, which can be the CCE provided by this disclosure, and this disclosure does not limit it.

[0194] In some embodiments, the first computing power management function network element in this disclosure is a core network element, and the second computing power management function network element is an access network element.

[0195] In some embodiments, the computing node sends computing resource information to the first computing power management function network element, including any one of the following:

[0196] The computing node sends computing resource information to the second computing power function network element, the second computing power function network element sends computing resource information to the access mobility management function network element, and / or the access mobility management function network element sends computing resource information to the first computing power management function network element;

[0197] The computing node sends computing power resource information to the base station, the base station sends computing power resource information to the second computing power function network element, the second computing power function network element sends computing power resource information to the access mobility management function network element, and / or the access mobility management function network element sends computing power resource information to the first computing power management function network element;

[0198] The computing node sends computing resource information to the distributed unit, the distributed unit sends computing resource information to the centralized unit, the centralized unit sends computing resource information to the access mobility management function network element, and / or the access mobility management function network element sends computing resource information to the first computing resource management function network element.

[0199] For example, taking the network architecture shown in Figure 2 above as an example, with the computing node as the terminal device, as shown in Figure 10, the terminal device (UE) can send computing power resource information (computing capability or computing resource status report) to the base station (xNB), and the base station then sends the UE's computing power resource information to the CCE.

[0200] In some embodiments, the base station may simply transmit the UE's computing resource information. Here, transparent transmission refers to the process of transmitting data from one network node to another without changing the data content. Based on the transparent transmission process, the base station's processing flow can be simplified, and the originality and accuracy of the transmitted information can be improved.

[0201] For example, in conjunction with the network architecture shown in Figure 2 above, the DU, base station (xNB), or computing node can send computing resource information to the CCE. As shown in Figure 11(a) or Figure 12(a), the DU sends computing resource information to the CU, and the CU sends the UE's computing resource information to the CCE. Exemplarily, the DU can send computing resource information (e.g., computing capability or computing resource status report) to the CU. The sent computing resource information can be the aforementioned computing resource information; specific details will not be elaborated here. In some embodiments, before the DU sends computing resource information to the CU, the CU can also send computing resource request information to the DU.

[0202] As shown in Figure 11(b) or Figure 12(b), the xNB can send computing resource information to the CCE. Alternatively, as shown in Figure 11(c) or Figure 12(b), the computing node can send computing resource information to the CCE. For example, the base station can send RAN-side computing resource information (e.g., computing capability or computing resource status report) to the CCE. RAN-side computing resources can come from RAN-dedicated computing nodes, RAN-side intelligent computing boards, base stations, CUs, DUs, or RUs.

[0203] It should be noted that before the base station sends computing resource information to the CCE, the base station needs to establish an interface connection with the CCE. The base station can know the CCE's IP address in advance and send an interface establishment request to the CCE. The interface establishment request can contain indications of the computing power supported by the base station. Correspondingly, the CCE can send an interface establishment response to the base station, which may contain indications of computing resource reporting. In some embodiments, the CCE can also send a separate signaling to the base station to request the base station to report computing resource information. In some embodiments, the base station and CCE can be co-located, or the base station can have CCE functionality. In this case, the base station and CCE can share computing resource information without establishing a dedicated interface for computing resource information transmission.

[0204] For example, in conjunction with the network architecture shown in Figure 2 above, the CCE can send computing resource information to the CMF and exchange computing resource information with other CCEs. As shown in Figure 13(a) or Figure 14, the CCE can send computing resource information (e.g., computing capability or computing resource status report) to the AMF, and the AMF will send the computing resource information from the CCE to the CMF. Exemplarily, the CCE can send the collected RAN-side computing resource information to the CMF, and the RAN-side computing resource information can be sent to the AMF first, and then sent by the AMF to the CMF. In some embodiments, the CCE can also directly send the RAN-side computing resource information to the CMF. The detailed description of the computing resource information sent by the CCE to the CMF above may include the computing resource information of the UE, RAN nodes (such as RU, DU, CU, xNB) and RAN-side computing nodes within the area under the responsibility of the CCE.

[0205] Alternatively, as shown in Figure 13(b), the CCE can directly send computing resource information to the CMF. Or, as shown in Figure 13(c), the CCE can also exchange computing resource information with other CCEs.

[0206] In some embodiments, before the CCE sends the RAN-side computing resources to the CMF, the CMF may also send computing resource request information to the CCE. The computing resource request information may include at least one of the following: computing resource indication information, perceived computing resource type, node type, node identifier, energy characteristics, available time, network status, computing location, computing service type, periodic reporting, event-triggered reporting, or one-time reporting, reporting period, reporting event type, reporting event triggering threshold, etc. Here, perceived computing resource type, node type, node identifier, energy characteristics, available time, network status, computing location, computing service type, etc., are used to indicate the computing resource information that the CCF is interested in and wants the CCE to report.

[0207] For example, combining the network architecture shown in Figure 2 above, as shown in Figure 9 or Figure 15, the core network element (NF) sends computing resource information to the CMF, and computing nodes send computing resource information (such as computing capability or computing resource status reports) to the CMF. As shown in Figure 9(a), the NF sends computing resource information to the AMF. As shown in Figure 9(b), the computing node sends computing resource information to the CMF. Exemplarily, core network elements or computing nodes can send computing resource information to the CMF. Specifically, the computing node can be a core network computing node, a data network computing node, an edge server, an application server, a UE, a RAN node, a core network node, or a node specifically providing computing resources.

[0208] In some embodiments, before the core network element or computing node sends computing resource information to the CMF, the CMF may also send computing resource request information to the core network element or computing node.

[0209] In some embodiments, before the computing node sends computing resource information to the first computing power management function network element, the method may further include step S100, whereby the computing node receives computing resource request information.

[0210] Here, the computing resource request information is used to request computing node computing resource information.

[0211] In this disclosure, the computing resource request information may also be referred to as computing resource reporting request information, computing resource reporting request, computing resource reporting instruction information, or other names that have the same or similar meanings, and this disclosure does not limit it in this way.

[0212] In some embodiments, the computing resource request information includes at least one of the following:

[0213] Computing power indication information, indication information of the type of computing power resource of interest, indication information of the reporting method, and parameter information of the reporting method;

[0214] Here, the reporting method indication information is used to indicate the periodic reporting method or the event-triggered reporting method; the parameter information of the reporting method includes the reporting period or the triggering event information.

[0215] For example, the computing resource request information includes at least one of the following: computing resource indication information, perceived computing resource type, node type, node identifier, energy characteristics, available time, network status, computing location, computing service type, periodic reporting, event-triggered reporting, or one-time reporting, reporting period, reporting event type, and reporting event triggering threshold. Here, the perceived computing resource type, node type, node identifier, energy characteristics, available time, network status, computing location, and computing service type are used to indicate the computing resource information that the CMF is interested in requesting from core network elements or computing nodes to report.

[0216] In some embodiments, before the computing node sends computing resource information to the first computing power management function network element, the computing node may also receive computing resource request information sent by the first computing power management function network element or the second computing power management function network element.

[0217] In one example, the first computing power management function network element can send computing power resource request information to the base station, and the base station sends computing power resource request messages to the computing nodes.

[0218] In another example, the first computing power management function network element can send computing power resource request information to the second computing power management function network element, and the second computing power management function network element sends computing power resource request messages to the computing nodes.

[0219] In another example, the first computing power management function network element can send computing power resource request information to the second computing power management function network element, the second computing power management function network element can send computing power resource request information to the base station, and the base station sends computing power resource request messages to the computing nodes.

[0220] For example, as shown in Figure 16, taking the computing node as a terminal device (UE), before the UE sends computing resource information (such as computing capability or computing resource status report) to the base station (xNB), the base station may send computing resource request information (computing report indication) to the UE. The computing resource request information may further include at least one of the following: computing power indication information, indication of the type of computing resource of interest, periodic reporting, event-triggered reporting, or one-time reporting, reporting period, reporting event type, reporting event triggering threshold, etc.

[0221] After receiving the computing resource information reported by the UE, the base station can also send the corresponding UE computing resource information to the second computing resource management function network element (CCE). Upon receiving the UE's computing resource information, the CCE can also save the computing resource information for subsequent computing resource scheduling of computing tasks.

[0222] Based on the technical solution disclosed herein, computing power management function network elements can be used to discover computing power resources and collect information on computing nodes, thereby enabling centralized management of computing power resources, improving resource utilization efficiency, facilitating network performance optimization, and thus managing computing power resources more efficiently and rationally.

[0223] In some embodiments, this disclosure also provides another computing resource management method, as shown in Figure 17, the method comprising:

[0224] S201, The first computing power management function network element receives computing power resource information sent by the computing node.

[0225] In some embodiments, a computing node includes at least one of the following:

[0226] Terminal equipment, base stations, distributed units, centralized units, radio units, data center nodes, core network functional entities, edge servers, application servers, and nodes dedicated to providing computing resources.

[0227] In some embodiments, computing resource information includes at least one of the following:

[0228] Node identifier, node type, computing resource type, computing resource quantity, available resource quantity, computing location, supported computing service types, computing resource usage status, computing energy characteristics, computing availability time, network status, software capabilities, and security capabilities.

[0229] In some embodiments, the node type includes at least one of the following:

[0230] Terminal equipment, base stations, distributed units, centralized units, radio units, data center nodes, core network functional entities, edge servers, application servers, and nodes dedicated to providing computing resources.

[0231] In some embodiments, the computing resource type includes at least one of the following:

[0232] Central processing unit, graphics processing unit, memory resources, storage resources, acceleration hardware.

[0233] In some embodiments, computing resources include at least one of the following:

[0234] Number of CPU cores, CPU clock frequency, number of GPU cores, video memory size, and storage capacity.

[0235] In some embodiments, the amount of available resources includes at least one of the following:

[0236] Computational resource availability, computational resource utilization, available memory size, and available storage.

[0237] In some embodiments, computing power location indicates the geographical location or coverage area of ​​the computing node.

[0238] In some embodiments, the supported computing power service types include at least one of the following:

[0239] Federated learning, distributed learning, distributed inference, AI model training, AI model inference, extended reality rendering, AI data preprocessing, and perceptual data processing.

[0240] In some embodiments, the computing resource usage status includes at least one of the following:

[0241] Resource congestion or idleness, availability or suspension, resource usage, resource utilization, remaining resources, and response time.

[0242] In some embodiments, the computing resource usage status includes at least one of the following: the measured computing resource usage status, and the predicted computing resource usage status.

[0243] In some embodiments, computing power characteristics include at least one of the following:

[0244] Energy consumption, energy efficiency, power status, energy source, energy availability time;

[0245] Here, the power status includes at least one of battery power, remaining power, and unrestricted power.

[0246] Energy sources include at least one of renewable energy, non-renewable energy, and renewable energy as a percentage of total energy consumption.

[0247] Energy availability time includes at least one of the available time periods for renewable energy and the available time periods for non-renewable energy.

[0248] In some embodiments, network status includes at least one of the following:

[0249] Aggregate maximum bit rate, uplink bandwidth, downlink bandwidth, latency, packet loss rate, whether remote direct memory access is supported, and priority.

[0250] In some embodiments, the software capabilities include at least one of the following:

[0251] Operating system name, operating system version, whether virtualization or containerization is supported, and maximum number of concurrent tasks.

[0252] In some embodiments, security capabilities include at least one of the following:

[0253] Supported encryption algorithms, supported security isolation mechanisms, and supported privacy protection mechanisms.

[0254] S202. The first computing power management function network element manages the computing power resources of computing nodes based on computing power resource information.

[0255] In some embodiments, the first computing power management function network element receives computing power resource information sent by the computing node, including any one of the following:

[0256] The base station receives computing resource information sent by the computing node, and / or the first computing resource management function network element receives computing resource information sent by the base station;

[0257] The base station receives computing resource information sent by the computing node, the access mobility management function network element receives computing resource information sent by the base station, and / or the first computing resource management function network element receives computing resource information sent by the access mobility management function network element.

[0258] The centralized unit receives computing resource information sent by the computing nodes, the access mobility management function network element receives computing resource information sent by the centralized unit, and / or the first computing resource management function network element receives computing resource information sent by the access mobility management function network element.

[0259] In some embodiments, the first computing power management function network element receives computing resource information sent by the computing node, including:

[0260] The second computing power management function network element receives computing power resource information sent by the computing node, and the first computing power management function network element receives computing power resource information sent by the second computing power management function network element.

[0261] In some embodiments, the first computing power management function network element is a core network element, and the second computing power management function network element is an access network element.

[0262] In some embodiments, the first computing power management function network element receives computing power resource information sent by the computing node, including any one of the following:

[0263] The second computing power management function network element receives computing power resource information sent by the computing node, the access mobility management function network element receives computing power resource information sent by the second computing power management function network element, and / or the first computing power management function network element receives computing power resource information sent by the access mobility management function network element.

[0264] The base station receives computing resource information sent by the computing node, the second computing resource management function network element receives computing resource information sent by the base station, the access mobility management function network element receives computing resource information sent by the second computing resource management function network element, and / or the first computing resource management function network element receives computing resource information sent by the access mobility management function network element.

[0265] The centralized unit receives computing resource information sent by the computing node, the second computing resource management function network element receives computing resource information sent by the centralized unit, the access mobility management function network element receives computing resource information sent by the second computing resource management function network element, and / or the first computing resource management function network element receives computing resource information sent by the access mobility management function network element.

[0266] In some embodiments, before the first computing power management function network element receives the computing power resource information sent by the computing node, the first computing power management function network element may also send computing power resource request information to the computing node.

[0267] In some embodiments, the computing resource request information includes at least one of the following:

[0268] Computing power indication information, indication information of the type of computing power resource of interest, indication information of the reporting method, and parameter information of the reporting method;

[0269] Here, the reporting method indication information is used to indicate the periodic reporting method or the event-triggered reporting method; the parameter information of the reporting method includes the reporting period or the triggering event information.

[0270] In some embodiments, the first computing power management function network element sends computing power resource request information to the computing node, including:

[0271] The first computing power management function network element sends computing power resource request information to the second computing power management function network element, and / or the second computing power management function network element sends computing power resource request information to the computing node.

[0272] Furthermore, for a detailed description of steps S201-S202, please refer to the relevant descriptions of steps S100-S101 above, which will not be repeated here.

[0273] Based on the above embodiments, computing power management function network elements can be used to discover computing power resources and collect information on computing nodes, thereby enabling centralized management of computing power resources, improving resource utilization efficiency, facilitating network performance optimization, and thus managing computing power resources more efficiently and rationally.

[0274] In some embodiments, as shown in FIG18, this disclosure provides another computing resource management method, including:

[0275] S301. The first computing power management function network element sends the first information to the first service node. The first information is used to indicate computing power resource information.

[0276] In some embodiments, the first information may also be a computing resource query response, a computing power resource query response, or other possible names, which includes computing power resource information.

[0277] In some embodiments, the first service node may be a terminal device, an application (e.g., a third-party application), an access node, or a core network function. The first service node may also be referred to as a first task node, a first computing power task node, or other possible names, which are not limited in this disclosure.

[0278] For example, the computing power network can expose computing power resource information to terminals and external third-party applications. Furthermore, the computing power resource information can also be exposed to internal network elements of the wireless communication network. For instance, network elements within the wireless network system (such as UE, RAN, CN, etc.) can obtain computing power resource information from the second computing power management function network element (CCE) or the first computing power management function network element (CMF). This information can be used by the network elements within the wireless network system to determine whether there are suitable computing power resources to fulfill the computing power requirements within the wireless network system.

[0279] In some embodiments, the first computing power management function network element may determine the first information based on at least one of the following: overall computing power information in the computing power network, available computing power information, computing power information required by the first service node, or computing power information that can be allocated to the first service node, and send the first information to the first service node.

[0280] For example, the computing resource information includes at least one of the following:

[0281] Node identifier, node type, computing resource type, computing resource quantity, available resource quantity, computing location, supported computing service types, computing resource usage status, computing energy characteristics, computing availability time, network status, software capabilities, and security capabilities.

[0282] For a detailed description of the various computing resources, please refer to the relevant description in step S101 above. It will not be repeated here.

[0283] In some embodiments, computing resource information may also include computing task status, etc.

[0284] For example, the computing task status further includes at least one of the following information: computing task identifier, computing task start time, computing task end time, computing resource type, computing resource usage, computing node identifier, computing node type, computing energy characteristics, etc.

[0285] Alternatively, the first information may also be used to indicate: the status of computing tasks and / or computing resource usage information.

[0286] In some embodiments, the computing task state includes at least one of the following:

[0287] Computing task identifier, start time of computing task, end time of computing task, type of computing resource, amount of computing resource used, computing node identifier, type of computing node, and characteristics of computing energy.

[0288] In some embodiments, the first computing power management function network element sends first information to the first service node (in conjunction with the network architecture shown in Figure 3 above), including any one of the following:

[0289] The first computing power management function network element sends the first information to the application function network element (AF), and / or the application function network element sends the first information to the first service node;

[0290] The first computing power management function network element sends the first information to the network open function network element (NEF), the network open function network element sends the first information to the application function network element, and / or the application function network element sends the first information to the first service node;

[0291] The first computing power management function network element sends the first information to the base station, and / or the base station sends the first information to the first service node;

[0292] The first computing power management function network element sends the first information to the access mobility management function network element, the access mobility management function network element sends the first information to the network device, and / or the network device sends the first information to the first service node.

[0293] In some embodiments, the first computing power management function network element sends first information to the first service node (in conjunction with the network architecture shown in Figure 2 above), including:

[0294] The first computing power management function network element sends the first information to the second computing power management function network element and / or the second computing power management function network element sends the first information to the first service node.

[0295] For example, the first computing power management function network element is a core network function, and the second computing power management function network element is an access network node.

[0296] In some embodiments, the first computing power management function network element sends first information to the first service node, including any one of the following:

[0297] The first computing power management function network element sends the first information to the second computing power management function network element, the second computing power management function network element sends the first information to the network opening function network element, and / or the network opening function network element sends the first information to the first service node;

[0298] The first computing power management function network element sends the first information to the second computing power management function network element, the second computing power management function network element sends the first information to the network opening function network element, the network opening function network element sends the first information to the application function network element, and / or the application function network element sends the first information to the first service node.

[0299] The first computing power management function network element sends the first information to the second computing power management function network element, the second computing power management function network element sends the first information to the access mobility management function network element, the access mobility management function network element sends the first information to the network opening function network element, the network opening function network element sends the first information to the application function network element, and / or the application function network element sends the first information to the first service node.

[0300] The first computing power management function network element sends the first information to the access mobility management function network element, the access mobility management function network element sends the first information to the second computing power management function network element, the second computing power management function network element sends the first information to the network opening function network element, and / or the network opening function network element sends the first information to the first service node.

[0301] In one example (referring to the network architecture shown in Figure 2 or Figure 3 above), taking a third-party application as the first service node, the first computing power management function (CMF) can send the computing power resource information within the system to the AF based on the request or subscription of the third-party application, and then the AF can send it to the third-party application. As shown in Figure 19(a), if the third-party application is trusted, the CMF can send the computing power resource information directly to the AF. Alternatively, as shown in Figure 19(b), if the third-party application is untrusted, the CMF can send the computing power resource information to the AF through the NEF.

[0302] In another example (referring to the network architecture shown in Figure 2 above), taking a third-party application as the first service node, the second computing power management function network element (CCE) can send computing power resource information to the AF. The CCE can send the computing power resource information within the system to the AF based on the request or subscription of the third-party application, and then the AF will send it to the third-party application. As shown in Figure 20(a), if the third-party application is trusted, the CCE can directly send the computing power resource information to the AF. Alternatively, as shown in Figure 20(b) or (c), if the third-party application is untrusted, the CCE will send the computing power resource information to the AF via REF or NEF. In some embodiments, as shown in Figure 20(d), the CCE can also first send the computing power resource information to the AMF, and then the AMF will send it to the AF via NEF.

[0303] In some embodiments, before the first computing power management function network element sends the first information to the first service node, the first computing power management function network element may also receive a computing power resource query request from the first service node.

[0304] In this disclosure, the computing resource query request may also be referred to as computing resource subscription information, computing resource status request, or other names that have the same or similar meanings, and this disclosure does not limit it in this way.

[0305] In some embodiments, a computing resource query request includes at least one of the following:

[0306] Instructions for requesting computing resource information, instructions for subscribing to computing resource information, indicators of computing resources of interest, identifiers of computing tasks of interest, format of computing resource information, and instructions for reporting methods;

[0307] Here, the reporting method indicator is used to indicate the periodic reporting method or the event-triggered reporting method; the computing power resource indicators of interest are used to indicate the computing power resource information that third-party applications are interested in and want the first computing power management function network element to report; the computing power resource information format is used to indicate the computing power resource information that the first computing power management function network element wants to report.

[0308] In some embodiments, the computing resource metrics of interest include at least one of the following:

[0309] Computing resource type, node type, node identifier, energy characteristics, available time, network status, computing region, computing service type.

[0310] In some embodiments, the computing resource information format includes at least one of the following:

[0311] Node identifier, node type, computing resource type, computing resource quantity, available resource quantity, computing location, supported computing service types, computing resource usage status, computing energy characteristics, computing availability time, network status, software capabilities, security capabilities, and billing information.

[0312] In one example, as shown in Figure 21, taking a third-party application as an example, the first computing power management function (CMF) can expose computing power resource information to the third-party application (the first service node) through the NEF. The exemplary NEF can provide computing power resource information to the third-party application in the form of an application programming interface (API) through the SBI interface (e.g., sending a computing resource query response, which includes computing power resource information). For example, the third-party application can call the NEF's API to request computing power resource information from the CMF, and the corresponding CMF can feed back the computing power resource information to the third party through the NEF.

[0313] In addition, third-party applications can also call the API provided by NEF to subscribe to computing resource information from CMF (for example, by sending a computing resource query request to CMF), so that CMF can send computing resource information to third-party applications when necessary according to the subscription requirements.

[0314] Here, the computing resource request information or computing resource subscription information may include at least one of the following: computing resource information request indication, computing resource information subscription indication, resource indicators of interest, computing task identifiers of interest, computing resource information format, periodic reporting, event-triggered reporting, or one-time reporting, reporting period, reporting event type, reporting event trigger threshold, etc. The computing resource indicators of interest here include at least one of the following: computing resource type, node type, node identifier, energy characteristics, available time, network status, computing region, computing service type. Computing resource indicators are used to indicate the computing resource information that third-party applications are interested in and wish to have reported by the CMF. The computing resource information format is used to indicate the specific computing resource information that the CMF wishes to report, and may include at least one of the following: node identifier, node type, computing resource type, computing resource quantity, available resource quantity, computing location, supported computing service types, computing resource usage status, computing energy characteristics, computing available time, network status, software capabilities, security capabilities, billing information, etc.

[0315] Therefore, third-party applications can also obtain the status of computing tasks and / or computing resource usage information from the CMF through computing resource request information or computing resource subscription information. Specifically, the computing resource request information or computing resource subscription information may also include computing task identifier, computing task time, computing resource type, computing resource usage, computing node identifier, computing node type, computing energy characteristics, etc. After receiving computing resource request information or computing resource subscription information from a third-party application, the CMF can send specific computing resource information to the third-party application through NEF.

[0316] It should be noted that, taking the 6G system as an example, when a third-party application requests computing power from the 6G system, if it is a trusted third-party application, it can directly interact with the CMF to initiate the computing power request; otherwise, the third-party application initiates the computing power request with the CMF through the NEF (Network Exposure Function). Similarly, when a third-party application requests computing power from the 6G system, if it is a trusted third-party application, it can directly interact with the CCE to initiate the computing power request; otherwise, the third-party application initiates the computing power request with the CCE through the NEF or REF (RAN Exposure Function).

[0317] In another example, as shown in Figure 22, the second computing power management function network element (CCE) can also send computing power resource information to third-party applications via NEF or REF (e.g., sending a computing resource query response, which includes computing power resource information). Exemplarily, NEF or REF can provide computing power resource information to third-party applications via the SBI interface in the form of an API, or via interface signaling. In some embodiments, third-party applications can also call the API provided by NEF to subscribe to computing power resource information from the CCE, and the CCE will send the computing power resource information to the third-party application as needed, according to the subscription requirements.

[0318] In another example, as shown in Figure 23, the second computing power management function network element CCE can also first send computing power resource information (for example, send a computing resource query response, which includes computing power resource information) to AMF, and then AMF sends it to a third-party application through NEF.

[0319] In one example, taking a terminal device (UE) as the first service node, as shown in Figure 24, the UE can obtain computing resource information from the base station (xNB). Exemplarily, the UE can send a computing resource query request to the base station (xNB). After receiving this request, the base station can send computing resource information (e.g., sending a computing resource query response, which includes the computing resource information) to the UE. In some embodiments, the base station can also send a computing indication to the UE.

[0320] In another example, as shown in Figure 25, the base station (xNB) or central unit (CU) can send a computing resource query request to the CCE, and the CCE sends computing resource information (e.g., sending a computing resource query response including computing resource information) to the base station (xNB) or central unit (CU) via a computing resource query response. And / or, as shown in Figure 26, the CCE can obtain computing resource information from the CMF. Exemplarily, the CCE sends a computing resource query request to the CMF via the AMF, and the CMF, upon receiving the request, sends a computing resource query response to the CCE via the AMF. In some embodiments, the CCE can also directly send computing resource query requests and responses to the CMF.

[0321] In some embodiments, in conjunction with the network architecture shown in Figure 3 above, as shown in Figure 27, the base station (xNB) can also obtain computing resource information from the CMF through the AMF. For example, the base station sends a computing resource query request to the CMF through the AMF, and after receiving the request, the CMF sends computing resource information to the base station through the AMF (e.g., sending a computing resource query response, which includes computing resource information).

[0322] In another example, as shown in Figure 28, the DU can also send a computing resource query request to the CU, and the CU sends the computing resource information to the DU through a computing resource query response. In some embodiments, the CU can also send a computing indication to the DU. As shown in Figure 29, a core network function (e.g., NF) can also send a computing resource query request to the CMF, and the CMF sends the computing resource information to the core network function NF through a computing resource query response.

[0323] Based on the above embodiments, computing power management function network elements can be used to open up computing power resources in the system to first service nodes, such as terminals, applications, access nodes, core network functions, etc., thereby reasonably carrying out centralized computing power resource management, improving resource utilization efficiency, facilitating network performance optimization, and thus managing computing power resources more efficiently and reasonably.

[0324] In some embodiments, as shown in FIG30, this disclosure provides another method for managing computing resources, including:

[0325] S401, The first service node receives the first information sent by the first computing power management function network element, the first information being used to indicate computing power resource information.

[0326] In some embodiments, the first service node is a terminal device, application, access node, or core network function.

[0327] In some embodiments, before the first service node receives the first information sent by the first computing power management function network element, the method further includes:

[0328] S400, the first service node sends a computing resource query request to the first computing power management function network element.

[0329] In some embodiments, a computing resource query request includes at least one of the following:

[0330] Instructions for requesting computing resource information, instructions for subscribing to computing resource information, indicators of computing resources of interest, identifiers of computing tasks of interest, format of computing resource information, and instructions for reporting methods;

[0331] Here, the reporting method indicator is used to indicate the periodic reporting method or the event-triggered reporting method; the computing power resource indicators of interest are used to indicate the computing power resource information that third-party applications are interested in and want the first computing power management function network element to report; the computing power resource information format is used to indicate the computing power resource information that the first computing power management function network element wants to report.

[0332] In some embodiments, the computing resource metrics of interest include at least one of the following:

[0333] Computing resource type, node type, node identifier, energy characteristics, available time, network status, computing region, computing service type.

[0334] In some embodiments, the computing resource information format includes at least one of the following:

[0335] Node identifier, node type, computing resource type, computing resource quantity, available resource quantity, computing location, supported computing service types, computing resource usage status, computing energy characteristics, computing availability time, network status, software capabilities, security capabilities, and billing information.

[0336] In some embodiments, the first information is also used to indicate: the status of the computing task and / or computing resource usage information.

[0337] In some embodiments, the computing task state includes at least one of the following:

[0338] Computing task identifier, start time of computing task, end time of computing task, type of computing resource, amount of computing resource used, computing node identifier, type of computing node, and characteristics of computing energy.

[0339] Furthermore, for a detailed description of steps S400-S401, please refer to the relevant description of step S301 above, which will not be repeated here.

[0340] Based on the above embodiments, computing power management function network elements can be used to open up computing power resources in the system to first service nodes, such as terminals, applications, access nodes, core network functions, etc., thereby reasonably carrying out centralized computing power resource management, improving resource utilization efficiency, facilitating network performance optimization, and thus managing computing power resources more efficiently and reasonably.

[0341] The above primarily describes the solutions provided in this disclosure from the perspective of interaction between various network elements or devices. It is understood that each network element or device, in order to achieve the above functions, includes corresponding hardware structures and / or software modules for executing each function. Those skilled in the art should readily recognize that, based on the algorithm steps of the examples described in conjunction with the embodiments disclosed herein, this disclosure can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed in hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this disclosure.

[0342] Figure 31 is a block diagram of a communication device according to some embodiments. As shown in Figure 31, the communication device 3100 is applied to a computing node and includes a transmitting module 3101. In some embodiments, the communication device 3100 further includes a receiving module 3102.

[0343] Here, the sending module 3101 is used to send computing resource information to the first computing power management function network element.

[0344] In some embodiments, a computing node includes at least one of the following: a terminal device, a base station, a distributed unit, a centralized unit, a radio unit, a data center node, a core network functional entity, an edge server, an application server, or a node dedicated to providing computing resources.

[0345] In some embodiments, the computing resource information includes at least one of the following: node identifier, node type, computing resource type, computing resource quantity, available resource quantity, computing location, supported computing service type, computing resource usage status, computing energy characteristics, computing availability time, network status, software capabilities, and security capabilities.

[0346] In some embodiments, the node type includes at least one of the following: terminal device, base station, distributed unit, centralized unit, radio unit, data center node, core network functional entity, edge server, application server, and node dedicated to providing computing resources.

[0347] In some embodiments, the computing resource type includes at least one of the following: central processing unit, graphics processing unit, memory resources, storage resources, and acceleration hardware.

[0348] In some embodiments, computing resources include at least one of the following: number of central processing unit cores, clock frequency of central processing unit, number of graphics processing unit cores, video memory size, and storage capacity.

[0349] In some embodiments, the amount of available resources includes at least one of the following: available computing resources, computing resource utilization, available memory size, and available storage.

[0350] In some embodiments, computing power location indicates the geographical location or coverage area of ​​the computing node.

[0351] In some embodiments, the supported computing power service types include at least one of the following: federated learning, distributed learning, distributed inference, artificial intelligence model training, artificial intelligence model inference, extended reality rendering, artificial intelligence data preprocessing, and perceptual data processing.

[0352] In some embodiments, the computing resource usage status includes at least one of the following: resource congestion or idleness, availability or suspension, resource occupancy, resource utilization, resource remaining amount, and response time.

[0353] In some embodiments, the computing resource usage status includes at least one of the following: the measured computing resource usage status, and the predicted computing resource usage status.

[0354] In some embodiments, computing power energy characteristics include at least one of the following: energy consumption, energy efficiency, power state, energy source, and energy availability time; here, power state includes at least one of battery power, remaining power, and unrestricted power; energy source includes at least one of renewable energy, non-renewable energy, and the proportion of renewable energy; energy availability time includes at least one of the available time period of renewable energy and the available time period of non-renewable energy.

[0355] In some embodiments, network status includes at least one of the following: aggregated maximum bit rate, uplink bandwidth, downlink bandwidth, latency, packet loss rate, whether remote direct memory access is supported, and priority.

[0356] In some embodiments, software capabilities include at least one of the following: operating system name, operating system version, whether virtualization or containerization is supported, and maximum number of concurrent tasks.

[0357] In some embodiments, security capabilities include at least one of the following: supported encryption algorithms, supported security isolation mechanisms, and supported privacy protection mechanisms.

[0358] In some embodiments, the sending module 3101 is specifically used to send computing power resource information to the base station, and the base station sends computing power resource information to the first computing power management function network element.

[0359] The sending module 3101 is specifically used to send computing power resource information to the base station, the base station sends computing power resource information to the access mobility management function network element, and / or the access mobility management function network element sends computing power resource information to the first computing power management function network element;

[0360] The sending module 3101 is specifically used to send computing resource information to the distributed unit, the distributed unit to the centralized unit, the centralized unit to the access mobility management function network element, and / or the access mobility management function network element to the first computing resource management function network element.

[0361] In some embodiments, the sending module 3101 is specifically used to send computing resource information to the second computing power management function network element, and / or the second computing power management function network element sends computing resource information to the first computing power management function network element.

[0362] In some embodiments, the first computing power management function network element is a core network element, and the second computing power management function network element is an access network element.

[0363] In some embodiments, the sending module 3101 is specifically used to send computing power resource information to the second computing power function network element, the second computing power function network element sends computing power resource information to the access mobility management function network element, and / or the access mobility management function network element sends computing power resource information to the first computing power management function network element;

[0364] The sending module 3101 is specifically used to send computing power resource information to the base station, the base station sends computing power resource information to the second computing power function network element, the second computing power function network element sends computing power resource information to the access mobility management function network element, and / or the access mobility management function network element sends computing power resource information to the first computing power management function network element;

[0365] The sending module 3101 is specifically used to send computing resource information to the distributed unit, the distributed unit to the centralized unit, the centralized unit to the access mobility management function network element, and / or the access mobility management function network element to the first computing resource management function network element.

[0366] In some embodiments, the receiving module 3102 is used to receive computing resource request information.

[0367] In some embodiments, the computing power resource request information includes at least one of the following: computing power indication information, indication information of the type of computing power resource of interest, reporting method indication information, and parameter information of the reporting method; here, the reporting method indication information is used to indicate a periodic reporting method or an event-triggered reporting method; the parameter information of the reporting method includes the reporting period or the triggering event information.

[0368] In some embodiments, the receiving module 3102 is specifically used to receive computing resource request information sent by the first computing power management function network element or the second computing power management function network element.

[0369] For a more detailed description of the above-mentioned sending module 3101 and receiving module 3102, as well as a more detailed description of their respective technical features and beneficial effects, please refer to the corresponding method embodiment section above, which will not be repeated here.

[0370] Figure 32 is a block diagram of another communication device according to some embodiments. As shown in Figure 32, the communication device 3200 is applied to a first computing power management function network element and includes a receiving module 3201. In some embodiments, the communication device 3200 further includes a management module 3202 and a transmitting module 3203.

[0371] Here, the receiving module 3201 is used to receive computing resource information sent by the computing node.

[0372] The management module 3202 is used to manage the computing resources of computing nodes based on computing resource information.

[0373] In some embodiments, the sending module 3203 is used to send computing resource request information to the computing node.

[0374] For a more detailed description of the receiving module 3201, management module 3202, and sending module 3203, as well as a more detailed description of their respective technical features and beneficial effects, please refer to the corresponding method embodiment section above, which will not be repeated here.

[0375] Figure 33 is a block diagram of another communication device according to some embodiments. As shown in Figure 33, the communication device 3300 is applied to a first computing power management function network element and includes a transmitting module 3301. In some embodiments, the communication device 3300 further includes a receiving module 3302.

[0376] Here, the sending module 3301 is used to send first information to the first service node, and the first information is used to indicate computing power resource information.

[0377] In some embodiments, the sending module 3301 is specifically configured to perform any of the following:

[0378] Send the first information to the application function network element, and / or send the first information to the first service node;

[0379] Send the first information to the network open function network element, send the first information to the application function network element, and / or send the first information to the first service node;

[0380] Send the first information to the base station, and / or send the first information to the first service node;

[0381] The first information is sent to the access mobility management function network element, the access mobility management function network element sends the first information to the network device, and / or the network device sends the first information to the first service node.

[0382] In some embodiments, the first service node is a terminal device, application, access node, or core network function.

[0383] In some embodiments, the sending module 3301 is specifically used to send first information to the second computing power management function network element and / or the second computing power management function network element sends first information to the first service node.

[0384] In some embodiments, the first computing power management function network element is a core network function, and the second computing power management function network element is an access network node.

[0385] In some embodiments, the sending module 3301 is specifically configured to perform any of the following:

[0386] Send the first information to the second computing power management function network element, the second computing power management function network element sends the first information to the network opening function network element, and / or the network opening function network element sends the first information to the first service node;

[0387] Send the first information to the second computing power management function network element, the second computing power management function network element sends the first information to the network opening function network element, the network opening function network element sends the first information to the application function network element, and / or the application function network element sends the first information to the first service node;

[0388] Send the first information to the second computing power management function network element; the second computing power management function network element sends the first information to the access mobility management function network element; the access mobility management function network element sends the first information to the network opening function network element; the network opening function network element sends the first information to the application function network element; and / or the application function network element sends the first information to the first service node.

[0389] The first information is sent to the access mobility management function network element, the access mobility management function network element sends the first information to the second computing power management function network element, the second computing power management function network element sends the first information to the network opening function network element, and / or the network opening function network element sends the first information to the first service node.

[0390] In some embodiments, the receiving module 3302 is configured to receive a computing resource query request from the first service node.

[0391] In some embodiments, a computing resource query request includes at least one of the following: a computing resource information request instruction, a computing resource information subscription instruction, an interested computing resource indicator, an interested computing task identifier, a computing resource information format, and a reporting method instruction; here, the reporting method instruction is used to indicate a periodic reporting method or an event-triggered reporting method; the interested computing resource indicator is used to indicate the computing resource information that a third-party application is interested in and wants the first computing power management function network element to report; the computing resource information format is used to indicate the computing resource information that the first computing power management function network element wants to report.

[0392] In some embodiments, the computing resource metrics of interest include at least one of the following: computing resource type, node type, node identifier, energy characteristics, availability time, network status, computing region, and computing service type.

[0393] In some embodiments, the computing resource information format includes at least one of the following: node identifier, node type, computing resource type, computing resource quantity, available resource quantity, computing location, supported computing service type, computing resource usage status, computing energy characteristics, computing availability time, network status, software capabilities, security capabilities, and billing information.

[0394] In some embodiments, the first information is also used to indicate: the status of the computing task and / or computing resource usage information.

[0395] In some embodiments, the computing task status includes at least one of the following: computing task identifier, computing task start time, computing task end time, computing resource type, computing resource usage, computing node identifier, computing node type, and computing energy characteristics.

[0396] For a more detailed description of the above-mentioned transmitting module 3301, receiving module 3302, and their respective technical features, as well as the description of their beneficial effects, please refer to the corresponding method embodiment section above, which will not be repeated here.

[0397] It should be noted that the modules in Figures 31-33 can also be called units; for example, the transmitting module can be called a transmitting unit. Furthermore, in the embodiments shown in Figures 31-33, the names of the modules may not be those shown in the figures; for example, the transmitting module can also be called a communication module, and the receiving module can also be called a communication module.

[0398] If the units or modules in Figures 31-33 are implemented as software functional modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the embodiments of this disclosure, in essence, or the parts that contribute to the prior art, or all or part of the technical solutions, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor to execute all or part of the steps of the methods of the various embodiments of this disclosure. Storage media for storing computer software products include: USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, optical disks, and other media capable of storing program code.

[0399] In the case of implementing the functions of the integrated modules described above in hardware, this disclosure provides a block diagram of a communication device. As shown in FIG34, the communication device 3400 includes: a processor 3402, a communication interface 3403, and a bus 3404. In some embodiments, the communication device 3400 may further include a memory 3401.

[0400] Processor 3402 may implement or execute the various illustrative logic blocks, modules, and circuits described in connection with this disclosure. Processor 3402 may be a central processing unit, a general-purpose processor, a digital signal processor, an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It may implement or execute the various illustrative logic blocks, modules, and circuits described in connection with this disclosure. Processor 3402 may also be a combination that implements computational functions, such as a combination of one or more microprocessors, a digital signal processor (DSP), and a microprocessor.

[0401] The communication interface 3403 is used to connect to other devices via a communication network. This communication network can be Ethernet, wireless access network, wireless local area network (WLAN), etc.

[0402] The memory 3401 may be a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, or electrically erasable programmable read-only memory (EEPROM), disk storage medium or other magnetic storage device, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but is not limited thereto.

[0403] As one possible implementation, the memory 3401 can exist independently of the processor 3402. The memory 3401 can be connected to the processor 3402 via a bus 3404 and is used to store instructions or program code. When the processor 3402 calls and executes the instructions or program code stored in the memory 3401, it can implement the method provided in the embodiments of this disclosure.

[0404] In another possible implementation, the memory 3401 can also be integrated with the processor 3402.

[0405] Bus 3404 can be an extended industry standard architecture (EISA) bus, etc. Bus 3404 can be divided into address bus, data bus, control bus, etc. For ease of representation, only one thick line is used in Figure 34, but this does not mean that there is only one bus or one type of bus.

[0406] Through the above description of the implementation methods, those skilled in the art can clearly understand that, for the sake of convenience and brevity, only the division of the above functional modules is used as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the equipment or device can be divided into different functional modules to complete all or part of the functions described above.

[0407] This disclosure also provides a computer-readable storage medium, which includes a non-transitory computer-readable storage medium storing computer instructions. All or part of the processes in the above method embodiments can be executed by computer instructions instructing related hardware. The program can be stored in the above computer-readable storage medium, and when executed, the program can include the processes of the above method embodiments. The computer-readable storage medium can be any of the foregoing embodiments or memory. The above computer-readable storage medium can also be an external storage device of the above device or apparatus, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the above device or apparatus. Further, the above computer-readable storage medium can also include both internal storage units of the above device or apparatus and external storage devices. The above computer-readable storage medium is used to store the above computer program and other programs and data required by the above device or apparatus. The above computer-readable storage medium can also be used to temporarily store data that has been output or will be output.

[0408] This disclosure also provides a computing power management system, which includes a first computing power management function network element for use with the present disclosure; or, the computing power management system includes a first computing power management function network element and a second computing power management function network element provided by the present disclosure.

[0409] This disclosure also provides a computer program product comprising a computer program that, when run on a computer, causes the computer to perform any of the methods provided in the above embodiments.

[0410] Although this disclosure has been described herein in conjunction with various embodiments, those skilled in the art will understand and implement other variations of the disclosed embodiments by reviewing the accompanying drawings, the disclosure, and the appended claims in carrying out the claimed disclosure. In the claims, the word "comprising" does not exclude other components or steps, and "a" or "an" does not exclude a plurality. A single processor or other unit can implement several functions listed in the claims. While different dependent claims may recite certain measures, this does not mean that these measures cannot be combined to produce a good effect.

[0411] Although this disclosure has been described in conjunction with specific features and embodiments, it will be apparent that various modifications and combinations can be made therein without departing from the spirit and scope of this disclosure. Accordingly, this specification and drawings are merely exemplary illustrations of the disclosure as defined by the appended claims and are to be considered as covering any and all modifications, variations, combinations, or equivalents within the scope of this disclosure. It is obvious that those skilled in the art can make various alterations and modifications to this disclosure without departing from its spirit and scope. Thus, this disclosure is also intended to include any such modifications and modifications that fall within the scope of the claims of this disclosure and their equivalents.

[0412] The above description is merely a specific embodiment of this disclosure, but the scope of protection of this disclosure is not limited thereto. Any changes or substitutions within the technical scope disclosed in this disclosure should be included within the scope of protection of this disclosure. Therefore, the scope of protection of this disclosure should be determined by the scope of the claims.

Claims

1. A method for managing computing resources, characterized in that, The method includes: The computing node sends computing resource information to the first computing power management function network element.

2. The method according to claim 1, characterized in that, The computing node includes at least one of the following: Terminal equipment, base stations, distributed units, centralized units, radio units, data center nodes, core network functional entities, edge servers, application servers, and nodes dedicated to providing computing resources.

3. The method according to claim 1 or 2, characterized in that, The computing resource information includes at least one of the following: Node identifier, node type, computing resource type, computing resource quantity, available resource quantity, computing location, supported computing service types, computing resource usage status, computing energy characteristics, computing availability time, network status, software capabilities, and security capabilities.

4. The method according to claim 3, characterized in that, The node type includes at least one of the following: Terminal equipment, base stations, distributed units, centralized units, radio units, data center nodes, core network functional entities, edge servers, application servers, and nodes dedicated to providing computing resources.

5. The method according to claim 3 or 4, characterized in that, The computing power resource type includes at least one of the following: Central processing unit, graphics processing unit, memory resources, storage resources, acceleration hardware.

6. The method according to any one of claims 3-5, characterized in that, The computing power resources include at least one of the following: Number of CPU cores, CPU clock frequency, number of GPU cores, video memory size, and storage capacity.

7. The method according to any one of claims 3-6, characterized in that, The available resources include at least one of the following: Computational resource availability, computational resource utilization, available memory size, and available storage.

8. The method according to any one of claims 3-7, characterized in that, The computing power location indicates the geographical location or coverage area of ​​the computing node.

9. The method according to any one of claims 3-8, characterized in that, The supported computing power service types include at least one of the following: Federated learning, distributed learning, distributed inference, AI model training, AI model inference, extended reality rendering, AI data preprocessing, and perceptual data processing.

10. The method according to any one of claims 3-9, characterized in that, The computing resource usage status includes at least one of the following: Resource congestion or idleness, availability or suspension, resource usage, resource utilization, remaining resources, and response time.

11. The method according to claim 3 or 10, characterized in that, The computing resource usage status includes at least one of the following: the measured computing resource usage status, and the predicted computing resource usage status.

12. The method according to any one of claims 3-11, characterized in that, The computing power energy characteristics include at least one of the following: Energy consumption, energy efficiency, power status, energy source, energy availability time; The power state includes at least one of battery power, remaining power, and unrestricted power. The energy source includes at least one of renewable energy, non-renewable energy, and renewable energy as a percentage. The energy availability time includes at least one of the available time periods for renewable energy and the available time periods for non-renewable energy.

13. The method according to any one of claims 3-12, characterized in that, The network state includes at least one of the following: Aggregate maximum bit rate, uplink bandwidth, downlink bandwidth, latency, packet loss rate, whether remote direct memory access is supported, and priority.

14. The method according to any one of claims 3-13, characterized in that, The software capabilities include at least one of the following: Operating system name, operating system version, whether virtualization or containerization is supported, and maximum number of concurrent tasks.

15. The method according to any one of claims 3-14, characterized in that, The security capabilities include at least one of the following: Supported encryption algorithms, supported security isolation mechanisms, and supported privacy protection mechanisms.

16. The method according to any one of claims 1-15, characterized in that, The computing node sends computing resource information to the first computing power management function network element, including any one of the following: The computing node sends the computing power resource information to the base station, and / or the base station sends the computing power resource information to the first computing power management function network element; The computing node sends the computing power resource information to the base station, the base station sends the computing power resource information to the access mobility management function network element, and / or the access mobility management function network element sends the computing power resource information to the first computing power management function network element; The computing node sends the computing power resource information to the distributed unit, the distributed unit sends the computing power resource information to the centralized unit, the centralized unit sends the computing power resource information to the access mobility management function network element, and / or the access mobility management function network element sends the computing power resource information to the first computing power management function network element. The computing node sends the computing resource information to the second computing power management function network element, and / or the second computing power management function network element sends the computing resource information to the first computing power management function network element.

17. The method according to claim 16, characterized in that, The first computing power management function network element is a core network element, and the second computing power management function network element is an access network element.

18. The method according to any one of claims 1-15, characterized in that, The first computing power management function network element is a core network element or an access network element.

19. The method according to any one of claims 1-15, characterized in that, The computing node sends computing resource information to the first computing power management function network element, including any one of the following: The computing node sends computing resource information to the second computing power function network element, the second computing power function network element sends the computing resource information to the access mobility management function network element, and / or the access mobility management function network element sends computing resource information to the first computing power management function network element. The computing node sends computing resource information to the base station, the base station sends computing resource information to the second computing power function network element, the second computing power function network element sends the computing resource information to the access mobility management function network element, and / or the access mobility management function network element sends computing resource information to the first computing power management function network element.

20. The method according to any one of claims 1-19, characterized in that, Before the computing node sends computing resource information to the first computing power management function network element, the method further includes: The computing node receives computing resource request information.

21. The method according to claim 20, characterized in that, The computing resource request information includes at least one of the following: Computing power indication information, indication information of the type of computing power resource of interest, indication information of the reporting method, and parameter information of the reporting method; The reporting method indication information is used to indicate a periodic reporting method or an event-triggered reporting method; the parameter information of the reporting method includes the reporting period or the information of the triggering event to be reported.

22. The method according to claim 20, characterized in that, The computing node receives computing resource request information, including: The computing node receives the computing resource request information sent by the first computing power management function network element or the second computing power management function network element.

23. A method for managing computing resources, characterized in that, The method includes: The first computing power management function network element receives computing resource information sent by the computing nodes; The first computing power management function network element manages the computing power resources of the computing node based on the computing power resource information.

24. The method according to claim 23, characterized in that, The computing node includes at least one of the following: Terminal equipment, base stations, distributed units, centralized units, radio units, data center nodes, core network functional entities, edge servers, application servers, and nodes dedicated to providing computing resources.

25. The method according to claim 23 or 24, characterized in that, The computing resource information includes at least one of the following: Node identifier, node type, computing resource type, computing resource quantity, available resource quantity, computing location, supported computing service types, computing resource usage status, computing energy characteristics, computing availability time, network status, software capabilities, and security capabilities.

26. The method according to claim 25, characterized in that, The node type includes at least one of the following: Terminal equipment, base stations, distributed units, centralized units, radio units, data center nodes, core network functional entities, edge servers, application servers, and nodes dedicated to providing computing resources.

27. The method according to claim 25 or 26, characterized in that, The computing power resource type includes at least one of the following: Central processing unit, graphics processing unit, memory resources, storage resources, acceleration hardware.

28. The method according to any one of claims 25-27, characterized in that, The computing power resources include at least one of the following: Number of CPU cores, CPU clock frequency, number of GPU cores, video memory size, and storage capacity.

29. The method according to any one of claims 25-28, characterized in that, The available resources include at least one of the following: Computational resource availability, computational resource utilization, available memory size, and available storage.

30. The method according to any one of claims 25-29, characterized in that, The computing power location indicates the geographical location or coverage area of ​​the computing node.

31. The method according to any one of claims 25-30, characterized in that, The supported computing power service types include at least one of the following: Federated learning, distributed learning, distributed inference, AI model training, AI model inference, extended reality rendering, AI data preprocessing, and perceptual data processing.

32. The method according to any one of claims 25-31, characterized in that, The computing resource usage status includes at least one of the following: Resource congestion or idleness, availability or suspension, resource usage, resource utilization, remaining resources, and response time.

33. The method according to claim 25 or 32, characterized in that, The computing resource usage status includes at least one of the following: the measured computing resource usage status, and the predicted computing resource usage status.

34. The method according to any one of claims 25-33, characterized in that, The computing power energy characteristics include at least one of the following: Energy consumption, energy efficiency, power status, energy source, energy availability time; The power state includes at least one of battery power, remaining power, and unrestricted power. The energy source includes at least one of renewable energy, non-renewable energy, and renewable energy as a percentage. The energy availability time includes at least one of the available time periods for renewable energy and the available time periods for non-renewable energy.

35. The method according to any one of claims 25-34, characterized in that, The network state includes at least one of the following: Aggregate maximum bit rate, uplink bandwidth, downlink bandwidth, latency, packet loss rate, whether remote direct memory access is supported, and priority.

36. The method according to any one of claims 25-35, characterized in that, The software capabilities include at least one of the following: Operating system name, operating system version, whether virtualization or containerization is supported, and maximum number of concurrent tasks.

37. The method according to any one of claims 25-36, characterized in that, The security capabilities include at least one of the following: Supported encryption algorithms, supported security isolation mechanisms, and supported privacy protection mechanisms.

38. The method according to any one of claims 23-37, characterized in that, The first computing power management function network element receives computing power resource information sent by the computing node, including any one of the following: The base station receives the computing power resource information sent by the computing node, and / or the first computing power management function network element receives the computing power resource information sent by the base station; The base station receives the computing power resource information sent by the computing node, the access mobility management function network element receives the computing power resource information sent by the base station, and / or the first computing power management function network element receives the computing power resource information sent by the access mobility management function network element; The centralized unit receives the computing power resource information sent by the computing node, the access mobility management function network element receives the computing power resource information sent by the centralized unit, and / or the first computing power management function network element receives the computing power resource information sent by the access mobility management function network element; The second computing power management function network element receives the computing power resource information sent by the computing node, and the first computing power management function network element receives the computing power resource information sent by the second computing power management function network element.

39. The method according to claim 38, characterized in that, The first computing power management function network element is a core network element, and the second computing power management function network element is an access network element.

40. The method according to any one of claims 23-37, characterized in that, The first computing power management function network element is a core network element or an access network element.

41. The method according to any one of claims 23-37, characterized in that, The first computing power management function network element receives computing power resource information sent by the computing node, including any one of the following: The second computing power management function network element receives the computing power resource information sent by the computing node, the access mobility management function network element receives the computing power resource information sent by the second computing power management function network element, and / or the first computing power management function network element receives the computing power resource information sent by the access mobility management function network element. The base station receives the computing power resource information sent by the computing node, the second computing power management function network element receives the computing power resource information sent by the base station, the access mobility management function network element receives the computing power resource information sent by the second computing power management function network element, and / or the first computing power management function network element receives the computing power resource information sent by the access mobility management function network element. The centralized unit receives the computing resource information sent by the computing node, the second computing resource management function network element receives the computing resource information sent by the centralized unit, the access mobility management function network element receives the computing resource information sent by the second computing resource management function network element, and / or the first computing resource management function network element receives the computing resource information sent by the access mobility management function network element.

42. The method according to any one of claims 23-41, characterized in that, Before the first computing power management function network element receives the computing power resource information sent by the computing node, the method further includes: The first computing power management function network element sends computing power resource request information to the computing node.

43. The method according to claim 42, characterized in that, The computing resource request information includes at least one of the following: Computing power indication information, indication information of the type of computing power resource of interest, indication information of the reporting method, and parameter information of the reporting method; The reporting method indication information is used to indicate a periodic reporting method or an event-triggered reporting method; the parameter information of the reporting method includes the reporting period or the information of the triggering event to be reported.

44. The method according to claim 42, characterized in that, The first computing power management function network element sends computing power resource request information to the computing node, including: The first computing power management function network element sends computing power resource request information to the second computing power management function network element, and / or the second computing power management function network element sends computing power resource request information to the computing node.

45. A method for managing computing resources, characterized in that, The method includes: The first computing power management function network element sends the first information to the first service node, and the first information is used to indicate computing power resource information.

46. ​​The method according to claim 45, characterized in that, The first computing power management function network element sends first information to the first service node, including any one of the following: The first computing power management function network element sends the first information to the application function network element, and / or the application function network element sends the first information to the first service node; The first computing power management function network element sends the first information to the network open function network element, the network open function network element sends the first information to the application function network element, and / or the application function network element sends the first information to the first service node; The first computing power management function network element sends the first information to the base station, and / or the base station sends the first information to the first service node; The first computing power management function network element sends the first information to the access mobility management function network element, the access mobility management function network element sends the first information to the network device, and / or the network device sends the first information to the first service node.

47. The method according to claim 45 or 46, characterized in that, The first service node is a terminal device, application, access node, or core network function.

48. The method according to claim 45, characterized in that, The first computing power management function network element sends first information to the first service node, including: The first computing power management function network element sends the first information to the second computing power management function network element and / or the second computing power management function network element sends the first information to the first service node.

49. The method according to claim 48, characterized in that, The first computing power management function network element is a core network function, and the second computing power management function network element is an access network node.

50. The method according to claim 48 or 49, characterized in that, The first computing power management function network element sends first information to the first service node, including any one of the following: The first computing power management function network element sends the first information to the second computing power management function network element, the second computing power management function network element sends the first information to the network opening function network element, and / or the network opening function network element sends the first information to the first service node; The first computing power management function network element sends the first information to the second computing power management function network element, the second computing power management function network element sends the first information to the network opening function network element, the network opening function network element sends the first information to the application function network element, and / or the application function network element sends the first information to the first service node; The first computing power management function network element sends the first information to the second computing power management function network element, the second computing power management function network element sends the first information to the access mobility management function network element, the access mobility management function network element sends the first information to the network opening function network element, the network opening function network element sends the first information to the application function network element, and / or the application function network element sends the first information to the first service node. The first computing power management function network element sends the first information to the access mobility management function network element, the access mobility management function network element sends the first information to the second computing power management function network element, the second computing power management function network element sends the first information to the network opening function network element, and / or the network opening function network element sends the first information to the first service node.

51. The method according to any one of claims 45-50, characterized in that, Before the first computing power management function network element sends the first information to the first service node, the method further includes: The first computing power management function network element receives a computing power resource query request from the first service node.

52. The method according to claim 51, characterized in that, The computing resource query request includes at least one of the following: Instructions for requesting computing resource information, instructions for subscribing to computing resource information, indicators of computing resources of interest, identifiers of computing tasks of interest, format of computing resource information, and instructions for reporting methods; The reporting method indication information is used to indicate the periodic reporting method or the event-triggered reporting method; the computing power resource indicators of interest are used to indicate the computing power resource information that third-party applications are interested in and want the first computing power management function network element to report; the computing power resource information format is used to indicate the computing power resource information that the first computing power management function network element is expected to report.

53. The method according to claim 52, characterized in that, The computing resource metrics of interest include at least one of the following: Computing resource type, node type, node identifier, energy characteristics, available time, network status, computing region, computing service type.

54. The method according to claim 52, characterized in that, The computing resource information format includes at least one of the following: Node identifier, node type, computing resource type, computing resource quantity, available resource quantity, computing location, supported computing service types, computing resource usage status, computing energy characteristics, computing availability time, network status, software capabilities, security capabilities, and billing information.

55. The method according to any one of claims 45-54, characterized in that, The first information is also used to indicate: the status of computing tasks and / or computing resource usage information.

56. The method according to claim 55, characterized in that, The state of the computing power task includes at least one of the following: Computing task identifier, start time of computing task, end time of computing task, type of computing resource, amount of computing resource used, computing node identifier, type of computing node, and characteristics of computing energy.

57. A computing power management system, characterized in that, The computing power management system includes a first computing power management function network element for executing the computing power resource management method according to any one of claims 23-56; or, the computing power management system includes a first computing power management function network element and a second computing power management function network element for executing the computing power resource management method according to any one of claims 23-56.

58. A communication device, characterized in that, include: Memory and processor; Memory and processor are coupled; The memory is used to store instructions that can be executed by the processor; When the processor executes the instructions, it performs the method as described in any one of claims 1 to 56.

59. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a non-transitory computer-readable storage medium on which computer instructions are stored, which, when executed on a computer, cause the computer to perform the method as described in any one of claims 1 to 56.

60. A computer program product, characterized in that, The computer program product includes computer instructions that, when executed on a computer, cause the computer to perform the method as described in any one of claims 1 to 56.

Images