Communication method and device

Abstract

The invention provides a communication method and device. The method comprises the steps that a first network element receives a first message from a second network element; the first message is used for requesting a machine learning model; the first message comprises energy consumption indication information; and the first network element sends model information of at least one machine learning model to the second network element, wherein the at least one machine learning model is determined according to the energy consumption indication information and energy consumption used for operating the at least one machine learning model. According to the method, when the second network element requests the machine learning model from the first network element, the second network element indicates the energy consumption indication information which the machine learning model needs to meet, so that the first network element determines at least one machine learning model according to the energy consumption indication information. Therefore, when the second network element operates the machine learning model, the energy consumption of each machine learning model can be considered, and the network energy saving is realized when the machine learning model is prevented from generating relatively high energy consumption in the operation process.

Description

Technical Field

[0001] This application relates to the field of communication technologies, and in particular, to a communication method and apparatus. Background Art

[0002] Currently, many use cases for using machine learning (ML) models to assist network analysis are defined in wireless networks, such as load analysis, user experience analysis, network performance analysis, user equipment (UE) mobility and communication feature analysis, user data congestion analysis, etc. In order to obtain an ML model, network elements such as the access and mobility management function (AMF) network element or the policy control function (PCF) network element in the network can act as consumers to request one or more ML models that meet the requirements from the network data analytics function (NWDAF) network element.

[0003] Since each ML model requires a certain amount of energy consumption when running inferences, when the energy consumption generated by the ML model obtained by the consumer during inference is high, it will greatly increase the energy consumption of the network. Summary of the Invention

[0004] This application provides a communication method and apparatus to save the energy consumption of the network.

[0005] In a first aspect, a communication method is provided, including: a first network element receives a first message from a second network element; the first message is used to request an ML model; the first message includes energy consumption indication information; the first network element sends model information of at least one ML model to the second network element, and the at least one ML model is determined according to the energy consumption indication information and the energy consumption for running the at least one ML model.

[0006] Through the above method, when the second network element requests an ML model from the first network element, it indicates the energy consumption indication information that the ML model needs to meet, so that the first network element determines at least one ML model according to the energy consumption indication information. In this way, the ML model requested by the second network element is related to the energy consumption indication information. When the second network element runs the ML model, it can consider the energy consumption of each ML model, and avoid high energy consumption during the running process of the ML model, thereby saving the energy consumption of the network.

[0007] In a possible implementation manner, the method further includes: the first network element determines the at least one machine learning model according to the energy consumption indication information and the energy consumption for running each machine learning model in the at least one machine learning model.

[0008] In a possible implementation manner, the energy consumption indication information indicates that the second network element is in an energy-saving state; the first message further includes an analysis identifier, and the analysis identifier is used to identify an analysis task; among the machine learning models for implementing the analysis task, the energy consumption for running the at least one machine learning model is the smallest.

[0009] By means of the energy consumption indication information, the machine learning model with the smallest energy consumption is obtained, so as to obtain the analysis result of the analysis task with the smallest energy consumption and achieve energy consumption saving of the network.

[0010] In a possible implementation manner, the energy consumption indication information includes an energy consumption threshold; the energy consumption for running each machine learning model in the at least one machine learning model is less than or equal to the energy consumption threshold.

[0011] By means of the energy consumption threshold, the machine learning model with the energy consumption for running less than or equal to the energy consumption threshold is obtained, so that the situation of high energy consumption of the running machine learning model can be avoided and the energy consumption of the network can be saved.

[0012] In a possible implementation manner, the method further includes: the first network element determines the energy consumption for running the at least one machine learning model according to the configuration information of the third network element; wherein, the third network element is used to run the machine learning model in the at least one machine learning model.

[0013] In a possible implementation manner, the first message further includes the configuration information of the third network element.

[0014] In a possible implementation manner, the first message further includes the identifier of the third network element; the method further includes: the first network element sends the identifier of the third network element to the fourth network element; the first network element receives the configuration information of the third network element from the fourth network element.

[0015] In a possible implementation manner, the model information includes first energy consumption information, and the first energy consumption information indicates the energy consumption for running the at least one machine learning model.

[0016] By indicating the energy consumption for running each machine learning model through the first energy consumption information, the energy consumption of each machine learning model can be considered when running the machine learning model, so that the network energy consumption can be saved.

[0017] In a possible implementation, the method further includes: the first network element sends a registration request message to the fifth network element, where the registration request message includes capability information, and the capability information indicates that the first network element has the capability to determine the energy consumption for running a machine learning model.

[0018] In a second aspect, a communication method is provided, including: a second network element sends a first message to a first network element; the first message is used to request a machine learning model; the first message includes energy consumption indication information; the second network element receives model information of at least one machine learning model from the first network element, and the at least one machine learning model is determined according to the energy consumption indication information and the energy consumption for running the at least one machine learning model.

[0019] In a possible implementation, before sending the first message, the method further includes:

[0020] The second network element receives an analysis request message from a sixth network element, where the analysis request message includes energy consumption request information, and the energy consumption request information is used to indicate the energy consumption for requesting to determine an analysis result.

[0021] In a possible implementation, the energy consumption indication information is determined by the second network element according to the energy consumption request information.

[0022] In a possible implementation, the model information includes first energy consumption information, and the first energy consumption information indicates the energy consumption for running the at least one machine learning model.

[0023] In a possible implementation, the method further includes:

[0024] The second network element determines a first machine learning model from the at least one machine learning model according to the first energy consumption information;

[0025] The second network element determines the analysis result according to the first machine learning model;

[0026] The second network element sends the analysis result and second energy consumption information to the sixth network element, and the second energy consumption information indicates the energy consumption for determining the analysis result.

[0027] In a possible implementation, the second energy consumption information is determined according to the first energy consumption consumed for obtaining the analysis result by running the first machine learning model; or, the second energy consumption information is determined according to a second energy consumption, and the second energy consumption is the energy consumption indicated by the first energy consumption information for running the first machine learning model.

[0028] In a possible implementation, the energy consumption indication information indicates that the second network element is in an energy-saving state; the first message further includes an analysis identifier for identifying an analysis task; among the machine learning models for implementing the analysis task, the energy consumption for running the at least one machine learning model is the smallest.

[0029] In a possible implementation, the energy consumption indication information includes an energy consumption threshold; the energy consumption for running each of the at least one machine learning model is less than or equal to the energy consumption threshold.

[0030] In a possible implementation, the first message further includes at least one of the following: configuration information of a third network element or an identifier of the third network element; the third network element is used to run the machine learning model in the at least one machine learning model.

[0031] In a possible implementation, the method further includes: the second network element sends a second message to a fifth network element, and the second message is used to request a network element with the ability to determine the energy consumption for running a machine learning model;

[0032] The second network element receives the address information of the first network element from the fifth network element; the second network element sends the first message to the first network element according to the address information of the first network element.

[0033] In a third aspect, a communication method is provided, including: a second network element sends a first message to a first network element; the first message is used to request a machine learning model; the first message includes energy consumption indication information; the first network element receives the first message from the second network element; the first network element sends model information of at least one machine learning model to the second network element, and the at least one machine learning model is determined according to the energy consumption indication information and the energy consumption for running the at least one machine learning model; the second network element receives the model information of the at least one machine learning model from the first network element.

[0034] In a possible implementation, the method further includes: the first network element determines the at least one machine learning model according to the energy consumption indication information and the energy consumption for running each of the at least one machine learning model.

[0035] In a possible implementation, the energy consumption indication information indicates that the second network element is in an energy-saving state; the first message further includes an analysis identifier for identifying an analysis task; among the machine learning models for implementing the analysis task, the energy consumption for running the at least one machine learning model is the smallest.

[0036] In a possible implementation, the energy consumption indication information includes an energy consumption threshold; the energy consumption for running each machine learning model among the at least one machine learning model is less than or equal to the energy consumption threshold.

[0037] In a possible implementation, the method further includes: the first network element determines the energy consumption for running the at least one machine learning model according to the configuration information of the third network element; wherein, the third network element is used to run the machine learning model among the at least one machine learning model.

[0038] In a possible implementation, the first message further includes the configuration information of the third network element.

[0039] In a possible implementation, the first message further includes the identifier of the third network element; the method further includes: the first network element sends the identifier of the third network element to the fourth network element; the first network element receives the configuration information of the third network element from the fourth network element.

[0040] In a possible implementation, the model information includes first energy consumption information, and the first energy consumption information indicates the energy consumption for running the at least one machine learning model.

[0041] In a possible implementation, the method further includes: the first network element sends a registration request message to the fifth network element, and the registration request message includes capability information, and the capability information indicates that the first network element has the capability to determine the energy consumption for running the machine learning model.

[0042] In a possible implementation, the method further includes: the second network element sends a second message to the fifth network element, and the second message is used to request a network element with the capability to determine the energy consumption for running the machine learning model; the second network element receives the address information of the first network element from the fifth network element; the second network element sends the first message to the first network element according to the address information of the first network element.

[0043] In a fourth aspect, the present application further provides a communication device, and this communication device can implement any method provided in any one of the first aspect to the second aspect above. This communication device can be implemented by hardware or by hardware executing corresponding software. The hardware or software includes one or more units or modules corresponding to the above functions.

[0044] In a possible implementation, the communication device includes a processor configured to support the communication device in performing the corresponding functions of the first network element or the second network element in the method shown above. The communication device may further include a memory, which may be coupled to the processor and stores the necessary program instructions and data of the communication device. Optionally, the communication device further includes an interface circuit for supporting communication between the communication device and other devices.

[0045] In a possible implementation, the communication device includes corresponding functional modules respectively for implementing the steps in the above method. The functions may be implemented by hardware or by hardware executing corresponding software. The hardware or software includes one or more modules corresponding to the above functions.

[0046] In a possible implementation manner, the structure of the communication device includes a processing unit and a communication unit, and these units can perform the corresponding functions in the above method examples. For specific details, refer to the descriptions in the methods provided in any one of the first aspect to the second aspect, and details will not be elaborated here.

[0047] In a fifth aspect, a communication device is provided, which includes a processor and an interface circuit. The interface circuit is configured to receive signals from other communication devices outside the communication device and transmit them to the processor or send signals from the processor to other communication devices outside the communication device. The processor, through logic circuits or by executing computer programs or instructions, implements the functional modules of the methods in any possible implementation manner in any one of the first aspect to the second aspect. Optionally, the communication device further includes a memory for storing computer programs or instructions.

[0048] In a sixth aspect, a computer program product storing instructions is provided. When a computer reads and executes the computer program product, the methods in any possible implementation manner in any one of the first aspect to the second aspect are implemented.

[0049] In a seventh aspect, a circuit is provided, which is used to execute the methods in any possible implementation manner in any one of the first aspect to the second aspect. The circuit may include a chip circuit. Optionally, the circuit may also be coupled to a memory.

[0050] In an eighth aspect, a chip is provided, which includes a processor. When the processor executes computer programs or instructions, it is used to implement the methods in any possible implementation manner in any one of the first aspect to the second aspect. Optionally, the chip may further include a memory. The chip may be composed of chips or may include chips and other discrete devices.

[0051] In a ninth aspect, a communication device is provided, including a processor that implements the method in any possible implementation manner of any one of the foregoing first aspect to second aspect through a logic circuit or by executing a computer program or instruction.

[0052] In a tenth aspect, a communication device is provided, including a unit or module for executing the method in any possible implementation manner of any one of the foregoing first aspect to second aspect.

[0053] In an eleventh aspect, a computer-readable storage medium is provided, in which a computer program or instruction is stored, and when the computer program or instruction is executed by a processor, the method in any possible implementation manner of any one of the foregoing first aspect to second aspect is implemented.

[0054] In a twelfth aspect, an embodiment of the present application further provides a communication system. The communication system includes: a first network element for implementing the method in the foregoing first aspect and any possible implementation manner of the first aspect; a second network element for implementing the method in the foregoing second aspect and any possible implementation manner of the second aspect. Description of the Drawings

[0055] Figure 1 A schematic diagram of a network architecture applicable to an embodiment of the present application;

[0056] Figure 2 A schematic diagram of a model subscription process provided by an embodiment of the present application;

[0057] Figure 3 A schematic diagram of a communication method process provided by an embodiment of the present application;

[0058] Figure 4 A schematic diagram of a communication method process provided by an embodiment of the present application;

[0059] Figure 5 A schematic diagram of a communication method process provided by an embodiment of the present application;

[0060] Figure 6 A schematic diagram of a communication device structure provided by an embodiment of the present application;

[0061] Figure 7 A schematic diagram of a communication device structure provided by an embodiment of the present application;

[0062] Figure 8 A schematic diagram of a communication device structure provided by an embodiment of the present application. Detailed Embodiments

[0063] The technical solutions in the embodiments of the present application will be described below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. The terms "first", "second" and the corresponding term numbers in the present application are used to distinguish similar objects, and do not have to be used to describe a specific order or sequence. It should be understood that such terms can be interchanged under appropriate circumstances, which is only a way of distinguishing objects with the same attributes when describing the embodiments of the present application. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, so that a process, method, system, product or device including a series of units does not have to be limited to those units, but may include other units not clearly listed or inherent to these processes, methods, products or devices. The methods and devices provided in the embodiments of the present application are based on the same or similar technical concepts. Since the principles of solving problems by the methods and devices are similar, the implementation of the device and the method can be referred to each other, and the repeated parts will not be described again.

[0064] The method provided in the embodiments of the present application can be applied to various mobile communication systems. For example, it can be the Internet of Things (IoT), Narrow Band Internet of Things (NB-IoT), the 4th generation (4G) communication system (such as Long Term Evolution (LTE)), or the 5th generation (5G) communication system (such as 5G New Radio (NR)). It can also be a hybrid architecture of LTE and NR, or 6G or a new communication system emerging in the future development of communication. The communication system can also include a Machine-to-Machine (M2M) network, Machine Type Communication (MTC), or other networks.

[0065] Figure 1 Schematic diagram of a 5G network architecture based on a service-based architecture. Figure 1In the 5G network architecture shown, it may include terminal devices, access network devices, and core network devices. The terminal devices access the data network (DN) through the access network devices and core network devices. Among them, the core network devices include multiple network functions (NFs) or network elements. For example, it includes some or all of the following network elements: operations administration management (OAM) network element, unified data management (UDM) network element, unified data repository (UDR) network element, application function (AF) network element, policy control function (PCF) network element, access and mobility management function (AMF) network element, session management function (SMF) network element, user plane function (UPF) network element, network data analytics function (NWDAF) network element, network exposure function (NEF) network element, binding support function (BSF) network element, network repository function (NRF) network element (not shown in the figure), etc.

[0066] The following is a brief introduction to some core network devices:

[0067] The AMF network element, abbreviated as AMF, includes functions such as performing mobility management, access authentication / authorization, etc. In addition, it is also responsible for transmitting user policies between the terminal device and the PCF.

[0068] The SMF network element, abbreviated as SMF, includes functions such as performing session management, executing the control policies issued by the PCF, selecting the UPF, and allocating the Internet protocol (IP) address of the terminal device.

[0069] The UPF network element, abbreviated as UPF, as the interface to the data network, includes functions such as completing user plane data forwarding, session / flow-level billing statistics, and bandwidth limitation.

[0070] The UDM network element, abbreviated as UDM, includes functions such as executing management subscription data and user access authorization.

[0071] The UDR network element, abbreviated as UDR, includes functions for accessing various types of data such as subscription data, policy data, and application data.

[0072] The NEF network element, abbreviated as NEF, is used to support the opening of capabilities and events.

[0073] The AF network element, abbreviated as AF, transmits the requirements from the application side to the network side. For example, quality of service (QoS) requirements or user status event subscriptions, etc. AF can be a third-party functional entity or an application server deployed by the operator.

[0074] The PCF network element, abbreviated as PCF, includes policy control functions such as being responsible for charging at the session and service flow levels, QoS bandwidth guarantee, mobility management, and terminal device policy decision-making.

[0075] The NRF network element, abbreviated as NRF, can be used to provide network element discovery functions. Based on requests from other network elements, it provides network element information corresponding to the network element type. The NRF network element also provides network element management services, such as network element registration, update, deregistration, and network element status subscription and push, etc.

[0076] The NWDAF network element, abbreviated as NWDAF, is mainly used to collect data (including one or more of terminal device data, access network device data, core network element data, and third-party application device data). Among them, these data can be the data of the terminal device, access network device, core network element, or third-party application device itself, or the data of the terminal device on the access network device, the core network element, or the third-party application device. Then, it performs data analysis based on the collected data and outputs the data analysis results for use by the network, network management devices, and application execution policy decision-making. NWDAF can use machine learning models for data analysis. In the embodiments of this application, a NWDAF can be a separate network element or co-located with other network elements. For example, NWDAF can be set in the PCF network element or the AMF network element.

[0077] In the 3rd generation partnership project (3GPP) Release 17, the training function and inference function of NWDAF are split. A NWDAF can only support the model training function, or only support the data inference function, or support both the model training function and the data inference function at the same time.

[0078] In this application, the NWDAF that supports the model training function, i.e., NWDAF(MTLF), can also be referred to as the training NWDAF, or the NWDAF that supports the model training logical function (MTLF), simply abbreviated as MTLF. Exemplarily, MTLF can perform model training based on the acquired data to obtain a trained model.

[0079] The NWDAF that supports the data inference function, i.e., NWDAF(AnLF), can also be referred to as the inference NWDAF, or the NWDAF that supports the analytics logical function (AnLF), simply abbreviated as AnLF.

[0080] It can be understood that MTLF can be regarded as the NWDAF that at least supports the model training function. As a possible implementation method, MTLF can also support the data inference function. AnLF can be regarded as the NWDAF that at least supports the data inference function. As a possible implementation method, AnLF can also support the model training function.

[0081] It can be understood that the above network elements are examples of one implementation method. This application does not exclude the existence of network elements or devices with the functions of the above network elements in a 6G or newer wireless communication system having other names or other forms.

[0082] It can be understood that the above network elements or functions can be either network elements in hardware devices, software functions running on dedicated hardware, or virtualized functions instantiated on a platform (e.g., a cloud platform). As a possible implementation method, the above network elements or functions can be implemented by one device, jointly implemented by multiple devices, or can also be a functional module within a device. The embodiments of this application do not make specific limitations in this regard.

[0083] Figure 1 Among them, Nudr, Npcf, Namf, Nudm, Nsmf, Naf, and Nnwdaf are service - based interfaces provided by the above - mentioned UDR, PCF, AMF, UDM, SMF, AF, and NWDAF respectively, for invoking corresponding service - based operations; N2 is the service - based interface between the RAN and the AMF; N3, N4, and N6 are the service - based interfaces between the RAN, SMF, DN, and the UPF respectively.

[0084] Hereinafter, some terms in the embodiments of this application will be explained first to facilitate understanding by those skilled in the art. The explanations of these terms are only examples and do not represent limitations on such terms.

[0085] In the embodiments of the present application, the access network device may be a device in a wireless network, and the access network device may also be referred to as an access network apparatus or a radio access network device. For example, the access network device may be a radio access network (RAN) node that connects a terminal device to a wireless network. The access network device includes but is not limited to: a base station, an evolved NodeB (eNodeB), a transmission reception point (TRP), a next-generation NodeB (gNB) in a fifth-generation (5G) mobile communication system, an access network device in an open radio access network (O-RAN), a next-generation NodeB in a sixth-generation (6G) mobile communication system, a base station in a future mobile communication system, or an access node in a wireless fidelity (WiFi) system, etc.; or it may be a module or unit that completes some functions of the base station. For example, it may be a central unit (CU), a distributed unit (DU), a central unit control plane (CU-CP) module, or a central unit user plane (CU-UP) module. The access network device may be a macro base station, a micro base station, an indoor station, a relay node, a donor node, etc. In the present application, the specific technologies and specific device forms adopted by the access network device are not limited.

[0086] In some implementations, the access network device may include a centralized unit (CU) and a distributed unit (DU). The RAN device including the CU node and the DU node splits the protocol layers of the gNB in the NR system. The functions of some protocol layers are centrally controlled by the CU, and the functions of the remaining part or all protocol layers are distributed in the DU, and the DU is centrally controlled by the CU. Further, the CU can be further divided into a control plane (CU-CP) and a user plane (CU-UP). Among them, CU-CP is responsible for the control plane functions, mainly including radio resource control (RRC) and the packet data convergence protocol (PDCP) corresponding to the control plane (i.e., PDCP-C). PDCP-C is mainly responsible for encryption, decryption, integrity protection, data transmission, etc. of the control plane data. CU-UP is responsible for the user plane functions, mainly including the service data adaptation protocol (SDAP) and the PDCP corresponding to the user plane (i.e., PDCP-U). Among them, SDAP is mainly responsible for processing the data of the core network and mapping the flow to the bearer. PDCP-U is mainly responsible for encryption, decryption, integrity protection, header compression, sequence number maintenance, data transmission, etc. of the data plane. Among them, CU-CP and CU-UP are connected through the E1 interface. CU-CP represents the gNB and is connected to the core network through the NG interface, and is connected to the DU through the control plane of the F1 interface (i.e., F1-C). CU-UP is connected to the DU through the user plane of the F1 interface (i.e., F1-U). Of course, there is also a possible implementation where PDCP-C is also in CU-UP.

[0087] It can be understood that in different systems, the CU (including CU-CP or CU-UP), or the DU may also have different names, but those skilled in the art can understand their meanings. For example, in an open radio access network (O-RAN) system, the CU may also be referred to as O-CU (open CU), the DU may also be referred to as O-DU, the CU-CP may also be referred to as O-CU-CP, and the CU-UP may also be referred to as O-CU-UP. For the convenience of description, in this application, the CU, CU-CP, CU-UP, and DU are taken as examples for description. The access network device may further include an active antenna unit (AAU). The CU implements some functions of the gNB, and the DU implements some functions of the gNB. For example, the CU is responsible for processing non-real-time protocols and services and implementing the functions of the RRC layer. The DU is responsible for processing physical layer protocols and real-time services and implementing the functions of the radio link control (RLC) layer, media access control (MAC) layer, and physical (PHY) layer. In some deployments, the CU may also be divided into a centralized unit control plane (CU-CP) node and a centralized unit user plane (CU-UP) node. Among them, the CU-CP is responsible for the control plane function, and the CU-UP is responsible for the user plane function.

[0088] The terminal device involved in the embodiments of this application can be a wireless terminal device capable of receiving scheduling and indication information from a network device. The terminal device can be referred to as a terminal device, and can also be referred to as a user equipment (UE), a terminal, a mobile station (MS), a mobile terminal (MT), etc. The terminal device can be a device with wireless communication capabilities (providing voice / data connectivity to users). For example, a handheld device with wireless connection capabilities, or an in-vehicle device, an in-vehicle module, etc. Currently, some examples of terminal devices are: mobile phones, tablet computers, laptop computers, palmtop computers, mobile internet devices (MIDs), wearable devices, virtual reality (VR) devices, augmented reality (AR) devices, wireless terminals in industrial control, wireless terminals in vehicle networking, wireless terminals in self-driving, wireless terminals in remote medical surgery, wireless terminals in smart grids, wireless terminals in transportation safety, wireless terminals in smart cities, or wireless terminals in smart homes, device-to-device (D2D) terminal devices, vehicle-to-everything (V2X) communication terminal devices, intelligent vehicles, in-vehicle systems (or in-vehicle sending units) (telematics boxes, T-boxes), machine-to-machine / machine-type communications (M2M / MTC) terminal devices, Internet of Things (IoT) terminal devices, etc. For example, the terminal device can be an in-vehicle device, a vehicle device, an in-vehicle module, a vehicle, an on-board unit (OBU), a roadside unit (RSU), a T-box, a chip, or a system on chip (SOC), etc. The above-mentioned chip or SOC can be installed in a vehicle, an OBU, an RSU, or a T-box. The wireless terminal in industrial control can be a camera, a robot, etc. The wireless terminal in a smart home can be a TV, an air conditioner, a floor sweeper, a speaker, a set-top box, etc.The terminal device can also be a V2X device. For example, a smart car (or intelligent car), a digital car, an unmanned car (or driverless car or pilotless car or automobile), a self-driving car (or autonomous car), a pure electric vehicle (pure EV or Battery EV), a hybrid electric vehicle (HEV), a range extended EV (REEV), a plug-in HEV (PHEV), a new energy vehicle, or a road site unit (RSU). The terminal device can also be a device in device-to-device (D2D) communication, such as an electricity meter, a water meter, etc. In addition, in the embodiments of this application, the terminal device can also be a terminal device in an IoT system. IoT is an important part of the future development of information technology. Its main technical feature is to connect items to the network through communication technology, so as to realize an intelligent network of human-machine interconnection and thing-thing interconnection.

[0089] In this application, the predefined content generally refers to the information that is defined by standards and does not require configuration by other devices, and is pre-recorded / written in the hardware and / or software of the terminal device itself. Or it can be understood as information that cannot be changed by the network device or other terminal devices. The pre-configured content generally refers to the information pre-recorded / written in the hardware and / or software of the terminal device itself, which is determined by the device manufacturer at the factory and can be changed through software or hardware.

[0090] The analysis ID can be used to indicate an analysis task, and the analysis task can also be referred to as an analysis service or an analysis business. This analysis task is related to a machine learning model, that is, the machine learning model can be used to execute the analysis task.

[0091] Or it can also be understood that the MTLF is related to the analysis ID, that is, the machine learning model provided by the MTLF supports the execution of the analysis task corresponding to the analysis ID. Exemplarily, the MTLF can be related to one or more analysis IDs. It can be understood that the MTLF can provide machine learning models for the analysis tasks corresponding to each of the one or more analysis IDs. For example, MTLF1 is related to analysis ID 1 and analysis ID 2, that is, MTLF1 can provide a machine learning model for the analysis task corresponding to analysis ID 1 and a machine learning model for the service corresponding to analysis ID 2.

[0092] Model Subscription:

[0093] NWDAF (MTLF) obtains a machine learning model by training based on relevant data of the machine learning model. NWDAF (AnLF) can request the machine learning model from NWDAF (MTLF) through a model subscription message. NWDAF (AnLF) can input input data into the machine learning model obtained from NWDAF (MTLF) to obtain the analysis result output by the machine learning model.

[0094] For example, as Figure 2 shown, it is a schematic diagram of a model subscription process provided by an embodiment of the present application.

[0095] Step 201: NWDAF (AnLF) sends a model subscription request message to NWDAF (MTLF).

[0096] The model subscription request message includes information such as an analysis identifier.

[0097] The model subscription request message may further include information such as an accuracy level requirement (Accuracy level(s) of Interest) information and an ML model filtering information (ML Model Filter Information).

[0098] Step 202: NWDAF (MTLF) sends a model subscription response message to NWDAF (AnLF).

[0099] The model subscription response message includes model information of the machine learning model for implementing the analysis task corresponding to the analysis identifier.

[0100] If the model subscription message includes accuracy level requirement information, then the accuracy of the machine learning model indicated by the model subscription response message also meets the accuracy indicated by the accuracy level requirement information.

[0101] If the model subscription message includes ML model filtering information, then the machine learning model indicated by the model subscription response message is the model filtered according to the ML model filtering information.

[0102] If NWDAF (AnLF) needs to determine the analysis result through the machine learning model, when the energy consumption generated during the operation of the model provided by NWDAF (MTLF) is relatively high, it will greatly increase the energy consumption of the network, which is not conducive to the energy saving of the network.

[0103] Therefore, the present application provides a method that can enable the model provided by NWDAF (MTLF) to meet the energy consumption requirements of NWDAF (AnLF), reduce energy consumption, and save the energy consumption of the network, which will be described in detail below.

[0104] In this application, the names of various messages and various information are only examples. With the evolution of the network architecture and the emergence of new service scenarios, the names of messages or information may change accordingly. However, the technical solutions provided by the embodiments of this application are equally applicable to similar technical problems.

[0105] As Figure 3 shown, it is a schematic diagram of the process of a communication method provided by an embodiment of this application.

[0106] When this method is applied to Figure 1 the system shown, the first network element can be network elements such as NWDAF (MTLF), that is, NWDAF that supports the model training function; the second network element can be network elements such as NWDAF (AnLF) or UE; the third network element can be used to run the machine learning model, for example, it can be network elements such as NWDAF (AnLF) or UE; the fourth network element can be network elements such as OAM; the fifth network element can be network elements such as NRF; the sixth network element can be network elements such as AF or AMF or PCF or SMF or UE.

[0107] In this application, the first network element has the ability to determine the energy consumption for running the machine learning model. For example, a model energy consumption prediction model has been pre-configured in the first network element, and the first network element can determine the energy consumption for running each machine learning model according to the model energy consumption prediction model. Optionally, the first network element also has the model training function. For example, the first network element can train the machine learning model according to the training data to obtain the trained machine learning model.

[0108] Step 301: The second network element sends a first message to the first network element.

[0109] Correspondingly, the first network element receives the first message from the second network element.

[0110] Among them, the first message is used to request the machine learning model. The name of the first message in this application is not limited. For example, the first message can also be called the NnwdafML model subscription (Nnwdaf_MLModelProvison_Subscribe) message.

[0111] This application does not limit under what circumstances the second network element sends the first message. For example, the second network element receives a request message from the sixth network element. The request message is used to request the analysis result of an analysis task. The second network element sends the first message to the first network element to request the machine learning model corresponding to the analysis task. The second network element combines the collected data as the input data of the model based on the machine learning model received from the first network element, obtains the analysis result by running the machine learning model, and finally sends the analysis result to the sixth network element. For another example, the second network element receives a request message from the sixth network element. The request message is used to request a machine learning model. Thus, the second network element can request the machine learning model from the first network element that stores the machine learning model.

[0112] The first message may include an analysis identifier. The analysis identifier is used to identify the analysis task. At this time, the machine learning model requested by the first message is used to implement the analysis task corresponding to the analysis identifier. It can be understood that the machine learning model requested by the first message is used to determine the analysis result of the analysis task corresponding to the analysis identifier. The specific type of the analysis task is not limited. For example, the analysis task includes, but is not limited to, any one of the following: NF load analytics, Network Performance Analytics, UE mobility analytics, UE communication analytics, or User Data Congestion Analytics.

[0113] The first message includes energy consumption indication information. The energy consumption indication information can be used to indicate the energy consumption conditions that the machine learning model needs to meet. For example, in implementation method one, the energy consumption indication information includes an energy consumption threshold or an energy consumption level. It can be understood that the energy consumption conditions include: the energy consumption for running (or inferring) the machine learning model is less than or equal to the energy consumption threshold, or the energy consumption for running the machine learning model conforms to the energy consumption level. For example, the energy consumption level includes three levels: high, medium, and low. Among them, high, medium, and low respectively correspond to an energy consumption range. The energy consumption range is preset, or the energy consumption range is a range agreed upon by each network element when calculating the energy consumption.

[0114] In implementation method two, the energy consumption indication information indicates that the second network element is in an energy-saving state. At this time, the energy consumption indication information implicitly indicates the machine learning model with the minimum requested energy consumption. It can be understood that the energy consumption conditions include: among the machine learning models used to implement the analysis task, at least one machine learning model with the minimum energy consumption for running.

[0115] Implementation method three: The energy consumption indication information directly indicates at least one machine learning model with the lowest energy consumption for running in the machine learning model used to implement the analysis task.

[0116] The above are just examples. The specific implementation methods of the energy consumption indication information are not limited in this application and will not be exemplified one by one here.

[0117] Optionally, the first message may further include at least one of the number of models information, the accuracy level requirement (Accuracy level(s) of Interest) information, or the ML model filter information (ML Model Filter Information). Among them, the number of models information indicates the number N of the requested machine learning models, where N is an integer greater than 0; the accuracy level requirement information indicates the accuracy requirement of the analysis result output by the machine learning model; the ML model filter information includes at least one filter parameter, and the ML model filter information indicates that the machine learning model meets the filter parameters included in the ML model filter information. For example, the filter parameters include, but are not limited to, the area of interest (Area of Interest), QoS requirement (QoS requirement), etc.

[0118] Optionally, the first message may further include at least one of the configuration information of the third network element, the identifier of the third network element, or the platform type information. The configuration information indicates the hardware configuration and / or software configuration of the third network element. For example, the hardware configuration indicated by the configuration information includes the type of the central processing unit (CPU) of the third network element, and / or the type of the graphic processing unit (GPU), etc. The software configuration indicated by the configuration information includes information such as the type of the operating system and the version of the operating system; the platform type information indicates the type of the platform of the third network element, and the type of the platform includes general hardware and virtual network elements after cloudification.

[0119] Among them, the third network element is used to run the machine learning model. The third network element and the second network element may be the same network element. For example, the second network element is NWDAF (AnLF), and the third network element is NWDAF (AnLF). In this case, the second network element itself runs the machine learning model requested from the first network element. Or, the third network element and the second network element are not the same network element. The second network element is a network element such as NWDAF (AnLF), AMF, or LMF, and the third network element is a UE. In this case, the second network element forwards the model information of the machine learning model returned by the first network element to the third network element, and the third network element runs the machine learning model.

[0120] In one implementation, before sending the first message, the second network element may send a third message to the fourth network element. The third message includes the identifier of the third network element, and the third message is used to request the configuration information of the third network element. The fourth network element can thus send the configuration information of the third network element to the second network element. The third network element may be different from the second network element or the same as the second network element. When the third network element is the same as the second network element, the identifier carried in the third message request is the identifier of the second network element, and the configuration information returned by the fourth network element is the configuration information of the second network element.

[0121] The first message may further include other information, which is not limited in this application and will not be exemplified one by one here.

[0122] Step 302: The first network element sends the model information of at least one machine learning model to the second network element.

[0123] Correspondingly, the second network element receives the model information of at least one machine learning model from the first network element. The model information may indicate each machine learning model in the at least one machine learning model. For example, the model information may indicate at least one of the model size, the algorithm of the model, the depth of the model, the architecture of the model, or the number of parameters of the model, the parameter values of the model in each machine learning model in the at least one machine learning model. Among them, the at least one machine learning model is determined according to the energy consumption indication information and the energy consumption for running the at least one machine learning model.

[0124] The first network element may determine all the machine learning models for implementing the analysis task corresponding to the analysis identifier according to the analysis identifier in the first message. If the first message further includes ML model filtering information, then the first network element may also select the machine learning models that meet the ML model filtering information from all the machine learning models of the analysis task. Similarly, if the first message further includes accuracy level requirement information, then the first network element may also select the machine learning models that meet the accuracy level requirement information from all the machine learning models of the analysis task.

[0125] Furthermore, the first network element may determine, according to the configuration information of the third network element, the energy consumption for running each machine learning model that meets the accuracy level requirement information and / or ML model filtering information among all the machine learning models for implementing the analysis task. Among them, if the configuration information is not included in the first message, the first network element needs to obtain the configuration information from the fourth network element. If the identifier of the third network element is further included in the first message, it indicates that the third network element and the second network element are different network elements. The configuration information obtained by the first network element from the fourth network element is the configuration information of the third network element. For example, the first network element sends the identifier of the third network element to the fourth network element to request the configuration information of the third network element. If the identifier of the third network element is not included in the first message, it indicates that the third network element and the second network element are the same network element. The configuration information obtained by the first network element from the fourth network element is the configuration information of the second (third) network element.

[0126] How the first network element specifically determines the energy consumption for running each machine learning model based on the configuration information of the third network element is not limited in this application. For example, in a first implementation manner, the first network element may obtain an energy consumption information table, which indicates the energy consumption required to run a machine learning model to process unit data per unit time under different hardware configurations, different software configurations, and different model frameworks. The first network element may query the energy consumption of each machine learning model from the energy consumption information table according to the configuration information. Among them, how the first network element obtains the energy consumption information table is not limited in this application. For example, the first network element obtains the energy consumption information table from the OAM network element, or may also obtain the energy consumption information table from a newly defined network element, and the newly defined network element may be called a name such as an energy consumption information table storage network element.

[0127] For example, the energy consumption information table may be as shown in Table 1.

[0128] Table 1

[0129]

[0130]

[0131] The above is only an example, and the energy consumption information table may also include other parameters, such as information including the depth of the model, the algorithm used for training the model, etc.

[0132] Assume that the configuration information indicates that the hardware configuration of the third network element is that the CPU type is type a1 and the GPU type is type b1; the software configuration is that the operating system is the Android system and the operating system version is V3.5. The first network element determines that the analysis task corresponds to 2 machine learning models, namely model 1 and model 2. The model framework of model 1 is TensorFlow, and the model framework of model 2 is pyTorch. Assume that the data to be processed is 20 unit data. Combining with the energy consumption information table shown in Table 1, it can be determined that the energy consumption for running model 1 is 20 * 13 = 260 joules, and the energy consumption for running model 2 is 20 * 15 = 300 joules. Or, assume that the energy consumption level corresponding to 260 joules is low, and the energy consumption level corresponding to 300 joules is medium. Then, according to the configuration information, it is determined that the energy consumption level for running model 1 is low, and the energy consumption level for running model 2 is medium.

[0133] For another example, in the second implementation manner, the first network element includes a model energy consumption prediction model, which is a trained machine learning model and is used to predict the energy consumption for running the machine learning model. For each machine learning model among all the machine learning models used to implement the analysis task, the first network element inputs information such as the configuration information of the third network element for running the machine learning model and the model information of the machine learning model (including at least one of the size of the model, the algorithm of the model, the depth of the model, the number of parameters of the model, and the running duration of the model in the training function) into the model energy consumption prediction model, and the model energy consumption prediction model can output the specific energy consumption or energy consumption level for running the machine learning model.

[0134] The above are just examples. There may be other implementation manners for how the first network element specifically determines the energy consumption for running the machine learning model, and no further examples will be given here one by one.

[0135] In this application, if the first message further includes platform type information, the first network element can also determine whether to correct the energy consumption for running the machine learning model according to the platform type information. For example, if the type of the platform indicates that the type of the third network element is general hardware, then the energy consumption for running the machine learning model may not be corrected. If the type of the platform indicates that the type of the third network element is a virtual network element after cloudification, then the energy consumption for running the machine learning model is corrected. For example, the energy consumption for running each machine learning model is multiplied by a correction factor, which is a number greater than 1, and the correction factor for each machine learning model can be the same, and the correction factor can be preset.

[0136] Furthermore, the first network element can determine at least one machine learning model according to the energy consumption indication information and the energy consumption for running each machine learning model.

[0137] For example, in the first implementation manner, the energy consumption indication information includes an energy consumption threshold, then the energy consumption for running each machine learning model determined by the first network element is less than or equal to the energy consumption threshold.

[0138] Optionally, if the first message further includes model quantity information, and the model quantity information indicates the model quantity N. When the number of machine learning models with energy consumption less than or equal to the energy consumption threshold among all the machine learning models used to implement the analysis task is greater than N, the first network element can select N machine learning models from the multiple machine learning models with energy consumption less than or equal to the energy consumption threshold as at least one machine learning model. For example, from the multiple machine learning models with energy consumption less than or equal to the energy consumption threshold, select the N machine learning models with the smallest energy consumption for running the machine learning model.

[0139] Wherein, if the first message further includes accuracy level requirement information and / or ML model filtering information, then at least one machine learning model determined by the first network element meets the accuracy level requirement information and / or the ML model filtering information.

[0140] In Implementation Manner 2, the energy consumption indication information includes an energy consumption level. Then, for each machine learning model to be run in at least one machine learning model determined by the first network element, the energy consumption conforms to the energy consumption level. For example, the energy consumption levels are high, medium, and low. If the first message further includes model quantity information, and the model quantity information indicates the model quantity N. Then the first network element selects one or more models that conform to the energy consumption level from all the machine learning models used to implement the analysis task. Then, the at least one machine learning model determined by the first network element is N machine learning models that conform to the energy consumption level among all the machine learning models used to implement the analysis task.

[0141] In Implementation Manner 3, the energy consumption indication information indicates that the second network element is in an energy-saving state or the network is in an energy-saving state. Then, the first network element selects a machine learning model with the minimum energy consumption from all the machine learning models used to implement the analysis task.

[0142] Optionally, if the first message further includes model quantity information, and the model quantity information indicates the model quantity N. Then, the at least one machine learning model determined by the first network element is N machine learning models with the minimum energy consumption among all the machine learning models used to implement the analysis task.

[0143] Similarly, if the first message further includes accuracy level requirement information and / or ML model filtering information, then at least one machine learning model determined by the first network element meets the accuracy level requirement information and / or the ML model filtering information.

[0144] The above are just examples. The first network element may also determine at least one machine learning model in other ways, and the present application does not limit this.

[0145] In this application, the model information may further include first energy consumption information, which indicates the energy consumption for running at least one machine learning model. Specifically, the first energy consumption information may indicate the energy consumption for running each machine learning model among at least one machine learning model. For example, the first energy consumption information includes the energy consumption or energy consumption range for running each machine learning model among at least one machine learning model. Alternatively, the first energy consumption information includes the energy consumption level for running each machine learning model among at least one machine learning model (for example, the energy consumption level can be identified as high, medium, low, or level 1, level 2, level 3), and each energy consumption level corresponds to an energy consumption or energy consumption range; the correspondence between the energy consumption level and the energy consumption or energy consumption range is preset or pre-configured. Among them, the first energy consumption information may also be outside the model information and is two independent pieces of information from the model information.

[0146] After the second network element obtains the model information and the first energy consumption information of at least one machine learning model, it can select a machine learning model from at least one machine learning model according to the first energy consumption information, and determine the analysis result of the analysis task according to the selected machine learning model. For example, the second network element selects the machine learning model with the smallest energy consumption among at least one machine learning model, inputs the data of the analysis task into this machine learning model, runs this machine learning model, and obtains the analysis result of the analysis task.

[0147] Optionally, before step 301, the first network element may also register in the fifth network element. When the second network element needs a machine learning model, it can request the address information of the first network element from the fifth network element. Specifically, the following process can be referred to:

[0148] When the first network element registers, the first network element may send a registration request message to the fifth network element.

[0149] This registration request message includes capability information, which indicates that the first network element has the capability to determine the energy consumption for running a machine learning model.

[0150] This registration request message may also include an analysis identifier, indicating that the first network element has the capability to determine the energy consumption of the machine learning model for running the analysis task corresponding to this analysis identifier. The number of analysis identifiers included in the registration request message is not limited, and it may include 1 analysis identifier or multiple analysis identifiers.

[0151] This application does not limit the name of the registration request message. For example, the registration request message may also be called a name such as Nnrf_NF management NF register request message, etc.

[0152] When the second network element needs a machine learning model, the second network element can send a discovery request message to the fifth network element. The discovery request message is used to request a network element with the ability to determine the energy consumption for running the machine learning model.

[0153] The discovery request message may include an analysis identifier, indicating a network element for requesting the ability to determine the energy consumption of a machine learning model corresponding to an analysis task associated with the analysis identifier.

[0154] Correspondingly, the fifth network element sends a discovery response message to the second network element.

[0155] The discovery response message includes the address information of the first network element. The address information of the first network element includes information such as the Internet Protocol (IP) address or the Fully Qualified Domain Name (FQDN) of the first network element.

[0156] After obtaining the address information of the first network element through the above process, when the second network element needs a machine learning model, it can request the machine learning model from the first network element according to the address information of the first network element.

[0157] Through the above method, when the second network element requests a machine learning model from the first network element, it indicates the energy consumption indication information required by the machine learning model, so that the first network element determines at least one machine learning model according to the energy consumption indication information. In this way, when the second network element runs the machine learning model, it can consider the energy consumption of each machine learning model, avoiding high energy consumption during the operation of the machine learning model and achieving network energy saving.

[0158] Combined with the previous description, the following takes the first network element as NWDAF(MTLF), the second and third network elements as the same network element, the second network element as NWDAF(AnLF), the fourth network element as OAM, the fifth network element as NRF, and the sixth network element as AF as an example for illustration. The above-mentioned various network elements can also be replaced with other network elements, and the present application is not limited thereto. In this process, AF requests an analysis result from NWDAF(AnLF), NWDAF(AnLF) requests a machine learning model from NWDAF(MTLF), runs the machine learning model, obtains the analysis result, and sends the analysis result to AF.

[0159] As Figure 4 shown, it is a schematic diagram of a communication method flow provided by an embodiment of the present application.

[0160] Step 401: NWDAF(MTLF) sends a registration request message to NRF.

[0161] The registration request message includes capability information, which indicates that the NWDAF (MTLF) has the capability to determine the energy consumption for running a machine learning model.

[0162] The registration request message may also include an analysis identifier, indicating that the NWDAF (MTLF) has the capability to determine the energy consumption of the machine learning model for the analysis task corresponding to the analysis identifier. The number of analysis identifiers included in the registration request message is not limited, and it may include one analysis identifier or multiple analysis identifiers.

[0163] This application does not limit the name of the registration request message. For example, the registration request message may also be referred to as the Nnrf_NF management NF registration request (Nnrf_NFmanagement_NFregister request) message or other names.

[0164] Step 402: The AF sends an analysis request message to the NWDAF (AnLF).

[0165] The analysis request message includes an analysis identifier and is used to request the analysis result of the analysis task corresponding to the analysis identifier.

[0166] The analysis request message may also include energy consumption request information, which is used to request the determination of the energy consumption of the analysis result or to indicate the expected energy consumption for requesting the analysis result. For example, it can be expressed as an energy consumption range or energy consumption level, indicating that the AF expects to obtain the analysis result using the energy consumption information indicated in the energy consumption request.

[0167] This application does not limit the name of the analysis request message. For example, the analysis subscription message may also be referred to as the analysis subscription message or the Nnwdaf analytics subscription (Nnwdaf_analyticsSubscription_Subscribe) message or other names. The analysis request message may also include other information, which will not be exemplified one by one here.

[0168] Optionally, step 403: The NWDAF (AnLF) sends a configuration request message to the OAM.

[0169] The configuration request message includes a second identifier of the NWDAF (AnLF) and is used to request the configuration information of the NWDAF (AnLF).

[0170] Step 404: The OAM sends a configuration response message of the NWDAF (AnLF) to the NWDAF (AnLF).

[0171] The configuration response message includes the configuration information of the NWDAF (AnLF).

[0172] Among them, if NWDAF(AnLF) can determine its own configuration information, steps 403 and 404 may not be executed.

[0173] Optionally, if NWDAF(AnLF) determines that it is necessary to generate the analysis result through a machine learning model, it may request at least one machine learning model from NWDAF(MTLF), and then step 405 may be executed.

[0174] Step 405: NWDAF(AnLF) sends a discovery request message to the NRF. The discovery request message is used to request a network element with the ability to determine the energy consumption for running a machine learning model.

[0175] The discovery request message may include an analysis identifier, indicating a network element that requests the ability to determine the energy consumption of a machine learning model capable of running the analysis task corresponding to the analysis identifier.

[0176] Step 406: The NRF sends a discovery response message to NWDAF(AnLF).

[0177] The discovery response message includes address information of at least one NWDAF(MTLF), for example, including the Internet Protocol (IP) address or Fully Qualified Domain Name (FQDN) of each NWDAF(MTLF) in at least one NWDAF(MTLF), etc.

[0178] NWDAF(AnLF) selects one NWDAF(MTLF) from at least one NWDAF(MTLF) and executes step 407. The application does not limit how NWDAF(AnLF) selects NWDAF(MTLF).

[0179] Step 407: NWDAF(AnLF) sends a model subscription message to NWDAF(MTLF).

[0180] The model subscription message is used to request a machine learning model.

[0181] The model subscription message includes an analysis identifier and energy consumption indication information. Optionally, the energy consumption indication information is determined according to the energy consumption request information. It can be understood that when NWDAF(AnLF) obtains the energy consumption request information, the energy consumption indication information is carried in the model subscription message for requesting the machine learning model.

[0182] Optionally, the model subscription message may further include at least one of the following:

[0183] Model quantity information, precision level requirements, ML model filtering information, configuration information of NWDAF (AnLF), or platform type information.

[0184] Optionally, step 408: If the configuration information of NWDAF (AnLF) is not included in the model subscription message, NWDAF (MTLF) sends a subscribe input message to OAM to subscribe to the configuration information of NWDAF (AnLF), and the subscription message includes the identification information of NWDAF (AnLF).

[0185] Step 409: OAM sends a subscribe output message to NWDAF (MTLF).

[0186] The subscribe output message includes the configuration information of NWDAF (AnLF).

[0187] Optionally, the subscribe output message further includes information such as an energy consumption information table.

[0188] Optionally, if the subscribe output message does not include the energy consumption information table, NWDAF (MTLF) can obtain the energy consumption information table from other network elements, and this application does not limit this.

[0189] Step 410: NWDAF (MTLF) determines at least one machine learning model according to the energy consumption indication information.

[0190] Among them, NWDAF (MTLF) can determine the energy consumption of each machine learning model among all the machine learning models used to run the analysis tasks corresponding to the analysis identifiers according to the obtained energy consumption information table and the configuration information of NWDAF (AnLF). How NWDAF (MTLF) specifically determines the energy consumption for running each machine learning model is not limited in this application and can refer to the description in step 302 and will not be elaborated here.

[0191] If NWDAF (MTLF) obtains the platform type information, it can also correct the energy consumption for running each machine learning model. The specific process can refer to the description in step 302 and will not be elaborated here.

[0192] Furthermore, NWDAF (MTLF) determines at least one machine learning model according to the energy consumption indication information and the energy consumption for running each machine learning model. The specific process can refer to the description in step 302 and will not be elaborated here.

[0193] Wherein, if the model subscription message includes a precision level requirement and / or ML model filtering information, the at least one machine learning model meets the precision level requirement and / or ML model filtering information.

[0194] Step 411: NWDAF (MTLF) sends a model provision notification message to NWDAF (AnLF).

[0195] The model provision notification message includes model information of at least one machine learning model and first energy consumption information, where the first energy consumption information indicates the energy consumption for running each machine learning model in the at least one machine learning model.

[0196] Step 412: NWDAF (AnLF) determines a first machine learning model from the at least one machine learning model according to the first energy consumption information, and runs the first machine learning model to obtain an analysis result of the analysis task.

[0197] This application does not limit how NWDAF (AnLF) determines the first machine learning model from the at least one machine learning model. For example, the machine learning model with the minimum energy consumption can be used as the first machine learning model.

[0198] This application does not limit how NWDAF (AnLF) obtains the analysis result according to the first machine learning model. For example, NWDAF (AnLF) can input the data corresponding to the analysis task into the first machine learning model to obtain the analysis result.

[0199] Step 413: NWDAF (AnLF) sends a subscription notification message to the AF.

[0200] The subscription notification message includes the analysis result and second energy consumption information, where the second energy consumption information indicates the energy consumption for determining the analysis result, that is, the energy consumption of NWDAF (AnLF) for obtaining the analysis result.

[0201] In one implementation, the second energy consumption information is determined according to the first energy consumption consumed for running the first machine learning model to obtain the analysis result. At this time, the energy consumption indicated by the second energy consumption information can be the energy consumption actually consumed by NWDAF (AnLF) when running the first machine learning model to obtain the analysis result. Optionally, in this implementation, the second energy consumption information is the specific value of the first energy consumption, or the second energy consumption information is the energy consumption level corresponding to the first energy consumption.

[0202] In another implementation, the second energy consumption information is determined according to the second energy consumption, where the second energy consumption is the energy consumption for running the first machine learning model indicated by the first energy consumption information. At this time, the energy consumption indicated by the second energy consumption information can be the energy consumption for running the first machine learning model to obtain the analysis result determined according to the first energy consumption information (i.e., the energy consumption inferred or estimated by NWDAF(MTLF)). Optionally, in this implementation, the second energy consumption information is the specific value of the second energy consumption, or the second energy consumption information is the energy consumption level corresponding to the second energy consumption.

[0203] The second energy consumption information may include a specific energy consumption value or range, or may include an energy consumption level. For example, the energy consumption level includes one of high, medium, and low, or the energy consumption level includes one of level1, level2, and level3.

[0204] Among them, if NWDAF(AnLF) does not need to request the machine learning model for the analysis task corresponding to the analysis identifier from NWDAF(MTLF), steps 403-411 can be omitted. NWDAF(AnLF) can directly generate the analysis result, and NWDAF(AnLF) collects the energy consumption information when generating the analysis result. For example, NWDAF(ANLF) collects the energy consumption before running the analysis result, then runs the analysis, then collects the energy consumption after running the analysis result, and then calculates the difference between the two energy consumptions to obtain the energy consumption of NWDAF(AnLF) for generating this analysis result. NWDAF(AnLF) uses the energy consumption for generating this analysis result as the second energy consumption information, or converts this energy consumption into the corresponding energy consumption level and sends it to AF as the second energy consumption information.

[0205] If NWDAF(AnLF) needs to request the machine learning model for the analysis task corresponding to the analysis identifier from NWDAF(MTLF), but does not need to request the inference energy consumption information corresponding to the machine learning model. The energy consumption indication information may not be included in the network element discovery and model subscription message for requesting the machine learning model in steps 403-411, and the first energy consumption information may not be included in the model information provided in step 411. NWDAF(AnLF) selects a machine learning model from at least one machine learning model returned by NWDAF(MTLF), and generates an analysis result according to this machine learning model. When generating the analysis result, NWDAF(AnLF) collects the energy consumption for running this machine learning model to generate the analysis result. The specific energy consumption or the energy consumption level corresponding to the energy consumption is returned to AF as the second energy consumption information.

[0206] The above three methods for generating the second energy consumption information are all methods for NWDAF(AnLF) to obtain the real-time energy consumption of the analysis result.

[0207] Another situation is that the NWDAF (ANLF) forms the energy consumption baseline corresponding to each analysis identifier through mathematical calculations based on the historical energy consumption information corresponding to the generated analysis identifier. When the NWDAF (AnLF) returns the analysis result, it includes the information of the energy consumption baseline corresponding to each analysis result. That is, the specific energy consumption value or energy consumption range corresponding to the energy consumption baseline or the energy consumption level corresponding to the energy consumption is returned to the AF as the second energy consumption information.

[0208] From the above process, it can be seen that when the NWDAF (MTLF) determines the machine learning model, in addition to considering information such as the accuracy level requirement and the ML model filtering information, it also considers the energy consumption for running the machine learning model. This can determine the machine learning model with the minimum energy consumption or the machine learning model with energy consumption less than or equal to the energy consumption threshold for the NWDAF (AnLF). In this way, when the NWDAF (AnLF) runs the machine learning model, the energy consumption is less, which can save energy and avoid energy waste.

[0209] Combined with the previous description, the following takes the first network element as the NWDAF (MTLF), the second network element as the AMF (the AMF can also be replaced by network elements such as the AF), the third network element as the UE (the UE can also be replaced by other network elements that can run the machine learning model), the fourth network element as the OAM, and the fifth network element as the NRF as an example for illustration. In this process, the UE requests the machine learning model from the NWDAF (MTLF) through the AMF and runs the obtained machine learning model.

[0210] As Figure 5 shown, it is a schematic diagram of the communication method flow provided by the embodiment of the present application.

[0211] Step 501: The NWDAF (MTLF) sends a registration request message to the NRF.

[0212] The registration request message includes capability information, and the capability information indicates that the NWDAF (MTLF) has the capability to determine the energy consumption for running the machine learning model.

[0213] The registration request message may also include an analysis identifier, indicating that the NWDAF (MTLF) has the capability to determine the energy consumption of the machine learning model for running the analysis task corresponding to the analysis identifier. The number of analysis identifiers included in the registration request message is not limited, and it may include 1 analysis identifier or multiple analysis identifiers.

[0214] Step 502: The UE sends a request message to the AMF.

[0215] The subscription message includes an analysis identifier, and the subscription message is used to request the machine learning model corresponding to the analysis identifier.

[0216] The subscribed message may also include information such as the configuration information of the UE, the energy consumption indication information, and the identifier of the UE.

[0217] Step 503: The AMF sends a discovery request message to the NRF. The discovery request message is used to request a network element with the ability to determine the energy consumption for running a machine learning model.

[0218] The discovery request message may include an analysis identifier, indicating a network element for requesting the ability to determine the energy consumption of a machine learning model capable of running the analysis task corresponding to the analysis identifier.

[0219] Step 504: The NRF sends a discovery response message to the AMF.

[0220] The discovery response message includes information of at least one NWDAF (MTLF), for example, including the Internet Protocol (IP) address or the fully qualified domain name (FQDN) of each NWDAF (MTLF) in at least one NWDAF (MTLF), etc.

[0221] The AMF selects one NWDAF (MTLF) from at least one NWDAF (MTLF) and executes Step 505. The application does not limit how the AMF selects the NWDAF (MTLF).

[0222] Step 505: The AMF sends a model subscription message to the NWDAF (MTLF).

[0223] The model subscription message is used to request a machine learning model.

[0224] The model subscription message includes an analysis identifier and energy consumption indication information.

[0225] Optionally, the model subscription message may further include at least one of the following:

[0226] Model quantity information, accuracy level requirement, ML model filtering information, UE configuration information, or platform type information. Among them, the UE configuration information comes from the request message of the UE.

[0227] Optionally, if the NWDAF (MTLF) does not include an energy consumption information table, it may also request an energy consumption information table from the OAM.

[0228] Step 506: The NWDAF (MTLF) sends a subscription input message to the OAM to subscribe to an energy consumption information table.

[0229] Step 507: The OAM sends a subscription output message to the NWDAF (MTLF).

[0230] The subscribed output message includes information such as an energy consumption information table.

[0231] Among them, steps 506 and 507 are optional steps. If NWDAF (MTLF) includes a model energy consumption prediction model, NWDAF (MTLF) can determine the energy consumption for running the machine learning model according to the model energy consumption prediction model, and there is no need to obtain the energy consumption information table from the OAM.

[0232] Step 508: NWDAF (MTLF) determines at least one machine learning model according to the energy consumption indication information.

[0233] Among them, the application does not limit how NWDAF (MTLF) specifically determines the energy consumption for running each machine learning model. Reference can be made to the description in step 302 and will not be elaborated here.

[0234] Step 509: NWDAF (MTLF) sends a model provision notification message to the AMF.

[0235] The model provision notification message includes the model information of at least one machine learning model and first energy consumption information, and the first energy consumption information indicates the energy consumption for running each machine learning model in at least one machine learning model.

[0236] Step 510: The AMF sends a response message to the UE.

[0237] The response message includes the model information of at least one machine learning model and first energy consumption information.

[0238] Step 511: The UE determines a first machine learning model from at least one machine learning model according to the first energy consumption information, and runs the first machine learning model to obtain an analysis result of the analysis task.

[0239] The application does not limit how the UE determines the first machine learning model from at least one machine learning model. For example, the machine learning model with the lowest energy consumption can be used as the first machine learning model.

[0240] The application does not limit how the UE obtains the analysis result according to the first machine learning model. For example, the UE can input the data corresponding to the analysis task into the first machine learning model to obtain the analysis result.

[0241] It can be understood that, in order to implement the functions in the above embodiments, the first network element or the second network element includes the corresponding hardware structures and / or software modules for executing various functions. Those skilled in the art should easily realize that, in combination with the units and method steps of the examples described in the embodiments disclosed in this application, this application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a certain function is executed in the form of hardware or computer software driving hardware depends on the specific application scenarios and design constraints of the technical solution.

[0242] The following are schematic structural diagrams of possible communication devices provided by the embodiments of this application. These communication devices can be used to implement the functions of the first network element or the second network element in the above method embodiments, and thus can also achieve the beneficial effects possessed by the above method embodiments.

[0243] As Figure 6 shown, the communication device 600 includes a processing unit 610 and a communication unit 620. The communication device 600 is used to implement the functions of the first network element or the second network element in the above various method embodiments.

[0244] When the communication device 600 is used to implement the function of the first network element:

[0245] The processing unit is configured to receive, through the communication unit, a first message from the second network element; the first message is used to request a machine learning model; the first message includes energy consumption indication information;

[0246] The processing unit is configured to send, through the communication unit, model information of at least one machine learning model to the second network element, where the at least one machine learning model is determined according to the energy consumption indication information and the energy consumption for running the at least one machine learning model.

[0247] When the communication device 600 is used to implement the function of the second network element:

[0248] The processing unit is configured to send, through the communication unit, a first message to the first network element; the first message is used to request a machine learning model; the first message includes energy consumption indication information;

[0249] The processing unit is configured to receive, through the communication unit, model information of at least one machine learning model from the first network element, where the at least one machine learning model is determined according to the energy consumption indication information and the energy consumption for running the at least one machine learning model.

[0250] For a more detailed description of the above processing unit 610 and communication unit 620, reference can be directly made to the relevant descriptions in the above various method embodiments, and details are not repeated here.

[0251] It should be understood that the division of units in the above device is only a division of logical functions. In actual implementation, they can be fully or partially integrated into a physical entity, or physically separated. And the units in the device can all be implemented in the form of software called by processing elements; they can also all be implemented in the form of hardware; or some units can be implemented in the form of software called by processing elements, and some units can be implemented in the form of hardware. For example, each unit can be a separately established processing element, or can be integrated in a certain chip of the device. In addition, it can also be stored in the memory in the form of a program, and the function of the unit is called and executed by a certain processing element of the device. In addition, all or part of these units can be integrated together or can be independently implemented. Here, the processing element can also be a processor, which can be an integrated circuit with signal processing capabilities. In the implementation process, each operation of the above method or each of the above units can be implemented through the integrated logic circuit of the hardware in the processor element or in the form of software called by the processing element.

[0252] In one example, the units in any of the above devices can be one or more integrated circuits configured to implement the above method. For example: one or more application specific integrated circuits (ASICs), or one or more digital signal processors (DSPs), or one or more field programmable gate arrays (FPGAs), or a combination of at least two of these integrated circuit forms. Again, when the units in the device can be implemented in the form of a processing element scheduler, the processing element can be a processor, such as a general central processing unit (CPU), or other processors that can call programs. Again, these units can be integrated together and implemented in the form of a system-on-a-chip (SOC).

[0253] The above unit for receiving is an interface circuit of the device, used to receive signals from other devices. For example, when the device is implemented in the form of a chip, the receiving unit is the interface circuit of the chip for receiving signals from other chips or devices. The above unit for sending is an interface circuit of the device, used to send signals to other devices. For example, when the device is implemented in the form of a chip, the sending unit is the interface circuit of the chip for sending signals to other chips or devices.

[0254] As another possible product form, the first network element or the second network element of the embodiments of the present application can be implemented by a general bus architecture. For the convenience of description, seeFigure 7 , Figure 7 is a schematic structural diagram of a communication device 700 provided by an embodiment of the present application. The communication device 700 includes a processor 701 and a transceiver 702. The communication device 700 can be a terminal device, or a chip or a chip system therein; or, the communication device 700 can be a network device, or a chip or a module therein. Figure 7 Only the main components of the communication device 700 are shown. In addition to the processor 701 and the transceiver 702, the communication device 700 may further include a memory 703 and an input / output device (not shown in the figure).

[0255] Optionally, the processor 701 is mainly used to process communication protocols and communication data, control the entire communication device, execute software programs, and process data of the software programs. The memory 703 is mainly used to store software programs and data. The transceiver 702 may include a radio frequency circuit and an antenna. The radio frequency circuit is mainly used for the conversion between baseband signals and radio frequency signals and the processing of radio frequency signals. The antenna is mainly used to transmit and receive radio frequency signals in the form of electromagnetic waves. The input / output device, such as a touch screen, a display screen, a keyboard, etc., is mainly used to receive data input by the user and output data to the user.

[0256] Optionally, the processor 701, the transceiver 702, and the memory 703 can be connected through a communication bus.

[0257] After the communication device is powered on, the processor 701 can read the software program in the memory 703, interpret and execute the instructions of the software program, and process the data of the software program. When data needs to be wirelessly transmitted, the processor 701 performs baseband processing on the data to be transmitted and then outputs a baseband signal to the radio frequency circuit. The radio frequency circuit performs radio frequency processing on the baseband signal and then transmits the radio frequency signal outward in the form of electromagnetic waves through the antenna. When data is sent to the communication device, the radio frequency circuit receives the radio frequency signal through the antenna, converts the radio frequency signal into a baseband signal, and outputs the baseband signal to the processor 701. The processor 701 converts the baseband signal into data and processes the data.

[0258] In another implementation, the radio frequency circuit and the antenna can be set independently of the processor performing baseband processing. For example, in a distributed scenario, the radio frequency circuit and the antenna can be independent of the communication device and are arranged in a remote manner.

[0259] In some embodiments, in terms of hardware implementation, those skilled in the art can think that the above communication device 600 can adopt Figure 7 the form of the communication device 700 shown.

[0260] As an example, Figure 6 the function / implementation process of the processing unit 610 inFigure 7 The processor 701 in the communication device 700 shown implements by invoking computer-executable instructions stored in the memory 703. Figure 6 The function / implementation process of the communication unit 620 in can be implemented by Figure 7 the transceiver 702 in the communication device 700 shown.

[0261] As another possible product form, the first network element or the second network element in this application may adopt Figure 8 the composition structure shown, or include Figure 8 the components shown. Figure 8 FIG. is a schematic diagram of the composition of a communication device 800 provided by this application.

[0262] As shown in Figure 8 the communication device 800 includes at least one processor 801. Optionally, the communication device further includes a communication interface 802.

[0263] When the program instructions involved are executed in the at least one processor 801, the communication device 800 can implement the method provided in any of the foregoing embodiments and any possible design therein. Alternatively, the processor 801 is used to implement the method provided in any of the foregoing embodiments and any possible design therein through logic circuits or by executing code instructions.

[0264] The communication interface 802 can be used to receive program instructions and transmit them to the processor. Alternatively, the communication interface 802 can be used for the communication device 800 to communicate and interact with other communication devices, such as interacting control signaling and / or service data, etc. Exemplarily, the communication interface 802 can be used to receive signals from other devices outside the communication device 800 and transmit them to the processor 801 or send signals from the processor 801 to other communication devices outside the communication device 800.

[0265] Optionally, the communication interface 802 can be a code and / or data read / write interface circuit, or the communication interface 802 can be a signal transmission interface circuit between a communication processor and a transceiver, or a pin of a chip.

[0266] Optionally, the communication device 800 may further include at least one memory 803, and the memory 803 can be used to store the program instructions and / or data involved as required. It should be noted that the memory 803 can exist independently of the processor 801 or be integrated with the processor 801. The memory 803 can be located inside the communication device 800 or outside the communication device 800, without limitation.

[0267] Optionally, the communication device 800 may further include a power supply circuit 804, which can be used to supply power to the processor 801. The power supply circuit 804 may be located within the same chip as the processor 801, or within another chip outside the chip where the processor 801 is located.

[0268] Optionally, the communication device 800 may further include a bus, and various parts in the communication device 800 may be interconnected through the bus.

[0269] In some embodiments, in terms of hardware implementation, those skilled in the art can conceive of the above Figure 6 The illustrated communication device 600 may adopt Figure 8 the form of the illustrated communication device 800.

[0270] As an example, Figure 6 the function / implementation process of the processing unit 610 in Figure 8 can be implemented by the processor 801 in the illustrated communication device 800 calling computer-executable instructions stored in the memory 803. Figure 6 the function / implementation process of the communication unit 620 in Figure 8 can be implemented by the communication interface 802 in the illustrated communication device 800.

[0271] It should be noted that Figure 8 the illustrated structure does not constitute a specific limitation on the first network element or the second network element. For example, in other embodiments of the present application, the first network element or the second network element may include more or fewer components than those illustrated, or combine certain components, or split certain components, or have different component arrangements. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.

[0272] It can be understood that the processor in the embodiments of the present application may be a central processing unit (CPU), and may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. The general-purpose processor may be a microprocessor or any conventional processor.

[0273] The method steps in the embodiments of the present application can be implemented in a hardware manner or by a processor executing software instructions. The software instructions can be composed of corresponding software modules, and the software modules can be stored in a random access memory, a flash memory, a read-only memory, a programmable read-only memory, an erasable programmable read-only memory, an electrically erasable programmable read-only memory, a register, a hard disk, a removable hard disk, a CD-ROM, or any other form of storage medium well known in the art. An exemplary storage medium is coupled to the processor, enabling the processor to read information from the storage medium and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and the storage medium can be located in an ASIC. Additionally, the ASIC can be located in a base station or a terminal. Of course, the processor and the storage medium can also exist as discrete components in a base station or a terminal.

[0274] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer programs or instructions. When the computer program or instructions are loaded and executed on a computer, the processes or functions described in the embodiments of the present application are executed in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, a network device, a user device, or other programmable devices. The computer program or instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer program or instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center in a wired or wireless manner. The computer-readable storage medium can be any available medium that the computer can access or a data storage device such as a server or a data center integrating one or more available media. The available medium can be a magnetic medium, such as a floppy disk, a hard disk, or a magnetic tape; it can also be an optical medium, such as a digital video disc; or it can be a semiconductor medium, such as a solid-state drive. The computer-readable storage medium can be a volatile or non-volatile storage medium, or can include both volatile and non-volatile types of storage media.

[0275] In the various embodiments of the present application, if there is no special explanation and logical conflict, the terms and / or descriptions between different embodiments are consistent and can be referenced to each other. The technical features in different embodiments can be combined to form new embodiments according to their internal logical relationships.

[0276] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, optical storage, etc.) that contain computer-usable program code.

[0277] The present application is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, as well as the combination of flows and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices generate means for implementing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0278] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including instruction means that implement the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0279] Obviously, those skilled in the art can make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalent technologies, the present application is also intended to include these modifications and variations.

Claims

1. A communication method, characterized in that, including: A first network element receives a first message from a second network element; The first message is used to request a machine learning model; The first message includes energy consumption indication information; The first network element sends model information of at least one machine learning model to the second network element, and the at least one machine learning model is determined according to the energy consumption indication information and the energy consumption for running the at least one machine learning model.

2. The method according to claim 1, wherein The method further includes: The first network element determines the at least one machine learning model according to the energy consumption indication information and the energy consumption for running each machine learning model in the at least one machine learning model.

3. The method according to claim 1 or 2, characterized in that, The energy consumption indication information indicates that the second network element is in an energy-saving state; The first message further includes an analysis identifier, and the analysis identifier is used to identify an analysis task; Among the machine learning models for implementing the analysis task, the energy consumption for running the at least one machine learning model is the smallest.

4. The method according to claim 1 or 2, characterized in that, The energy consumption indication information includes an energy consumption threshold; The energy consumption for running each machine learning model in the at least one machine learning model is less than or equal to the energy consumption threshold.

5. The method according to any one of claims 1 to 4, characterized in that The method further includes: The first network element determines the energy consumption for running the at least one machine learning model according to the configuration information of a third network element; Wherein, the third network element is used to run the machine learning model in the at least one machine learning model.

6. The method according to claim 5, characterized in that The first message further includes the configuration information of the third network element.

7. The method according to claim 5, wherein The first message further includes an identifier of the third network element; the method further includes: The first network element sends the identifier of the third network element to a fourth network element; The first network element receives the configuration information of the third network element from the fourth network element.

8. The method according to any one of claims 1 to 7, characterized in that The model information contains first energy consumption information, and the first energy consumption information indicates the energy consumption for running the at least one machine learning model.

9. The method according to any one of claims 1 to 8, characterized in that, The method further includes: The first network element sends a registration request message to a fifth network element, and the registration request message includes capability information, and the capability information indicates that the first network element has the capability to determine the energy consumption for running a machine learning model.

10. A communication method, characterized in that, including: A second network element sends a first message to a first network element; The first message is used to request a machine learning model; The first message includes energy consumption indication information; The second network element receives model information of at least one machine learning model from the first network element, and the at least one machine learning model is determined according to the energy consumption indication information and the energy consumption for running the at least one machine learning model.

11. The method according to claim 10, characterized in that, Before sending the first message, the method further includes: The second network element receives an analysis request message from a sixth network element, and the analysis request message contains energy consumption request information, and the energy consumption request information is used to indicate the energy consumption for requesting to determine an analysis result.

12. The method according to claim 11, wherein The energy consumption indication information is determined according to the energy consumption request information.

13. The method according to any one of claims 10 to 12, characterized in that, The model information contains first energy consumption information, and the first energy consumption information indicates the energy consumption for running the at least one machine learning model.

14. The method according to claim 13, wherein The method further includes: The second network element determines a first machine learning model from the at least one machine learning model according to the first energy consumption information; The second network element determines the analysis result according to the first machine learning model; The second network element sends the analysis result and second energy consumption information to a sixth network element, where the second energy consumption information indicates the energy consumption for determining the analysis result.

15. The method according to claim 14, wherein The second energy consumption information is determined according to the first energy consumption consumed for obtaining the analysis result by running the first machine learning model; Alternatively, the second energy consumption information is determined according to a second energy consumption, where the second energy consumption is the energy consumption indicated by the first energy consumption information for running the first machine learning model.

16. The method according to any one of claims 10 to 15, characterized in that The energy consumption indication information indicates that the second network element is in an energy-saving state; The first message further includes an analysis identifier for identifying an analysis task; Among the machine learning models for implementing the analysis task, the energy consumption for running the at least one machine learning model is the smallest.

17. The method according to any one of claims 10 to 15, characterized in that, The energy consumption indication information includes an energy consumption threshold; The energy consumption for running each machine learning model in the at least one machine learning model is less than or equal to the energy consumption threshold.

18. The method according to any one of claims 10 to 17, characterized in that, The first message further includes at least one of the following: Configuration information of a third network element or an identifier of the third network element; the third network element is used to run the machine learning model in the at least one machine learning model.

19. The method according to any one of claims 10 to 18, characterized in that, The method further includes: The second network element sends a second message to a fifth network element, where the second message is used to request a network element with the ability to determine the energy consumption for running a machine learning model; The second network element receives address information of the first network element from the fifth network element; The second network element sends the first message to the first network element according to the address information of the first network element.

20. A communication method, characterized in that, Including: The second network element sends a first message to the first network element; The first message is used to request a machine learning model; The first message includes energy consumption indication information; The first network element receives the first message from the second network element; The first network element sends model information of at least one machine learning model to the second network element, where the at least one machine learning model is determined according to the energy consumption indication information and the energy consumption for running the at least one machine learning model; The second network element receives the model information of at least one machine learning model from the first network element.

21. The method according to claim 20, wherein The energy consumption indication information indicates that the second network element is in an energy-saving state; The first message further includes an analysis identifier for identifying an analysis task; Among the machine learning models for implementing the analysis task, the energy consumption for running the at least one machine learning model is the smallest.

22. The method according to claim 20, wherein The energy consumption indication information includes an energy consumption threshold; The energy consumption for running each machine learning model in the at least one machine learning model is less than or equal to the energy consumption threshold.

23. The method according to any one of claims 20 to 22, characterized in that, The method further includes: The first network element determines the energy consumption for running the at least one machine learning model according to the configuration information of a third network element; Wherein, the third network element is used to run the machine learning model in the at least one machine learning model.

24. The method according to claim 23, wherein The first message further includes the configuration information of the third network element.

25. The method according to any one of claims 20 to 24, characterized in that, The model information includes first energy consumption information, and the first energy consumption information indicates the energy consumption for running the at least one machine learning model.

26. A communication system, characterized in that, Comprising: A first network element and a second network element; The first network element is configured to execute the method according to any one of claims 1 to 9, and the second network element is configured to execute the method according to any one of claims 10 to 15.

27. A communication device, characterized in that, Comprising: A processing unit and a communication unit; The processing unit is configured to receive, via the communication unit, a first message from the second network element; The first message is used to request a machine learning model; the first message includes energy consumption indication information; The processing unit is configured to send, via the communication unit, model information of at least one machine learning model to the second network element, and the at least one machine learning model is determined according to the energy consumption indication information and the energy consumption for running the at least one machine learning model.

28. A communication device, characterized in that, Comprising: A processing unit and a communication unit; The processing unit is configured to send, via the communication unit, a first message to the first network element; The first message is used to request a machine learning model; the first message includes energy consumption indication information; The processing unit is configured to receive, via the communication unit, model information of at least one machine learning model from the first network element, and the at least one machine learning model is determined according to the energy consumption indication information and the energy consumption for running the at least one machine learning model.

29. A communication device, characterized in that, Comprising a processor; The processor is configured to execute a computer program or instruction stored in a memory, so that the communication device implements the method according to any one of claims 1 to 19.

30. A computer-readable storage medium, characterized in that, A computer program or instruction is stored, and when the computer program or instruction runs on a computer, the computer implements the method according to any one of claims 1 to 19.

Images