Mechanism for determining energy-related performance indicators for data processing entities

Abstract

The embodiment of the invention relates to equipment, a method, a device and a computer readable storage medium for determining an energy-related performance indicator for a data processing entity. In accordance with an example embodiment of the present disclosure, a first device determines first information for a data processing entity, the first information including at least an identification of the data processing entity and a list of energy-related performance indicators for the data processing entity, and the list of energy-related performance indicators including at least data processing entity performance. The first information is transmitted to the second device or the third device. In this manner, the energy consumption related information may be stored and updated in a consistent manner so that queries about the energy consumption related information of the AIML entity may be completed by the authorized consumer.

Description

Technical Field

[0001] Various example embodiments of the present disclosure relate generally to the field of telecommunications, and in particular, to methods, devices, apparatuses, and computer-readable storage media for determining energy-related performance indicators for a data processing entity. Background Art

[0002] Artificial intelligence (AI) and machine learning (ML) technologies are increasingly used in 5G systems (5GS) and are considered key enablers for the generation of 5G-Advanced and 6G mobile networks. In some scenarios, AI / ML management-related capabilities and services are proposed, mainly focusing on AI / ML training. Current research on AI / ML management aims to discuss use cases, potential requirements and possible scenarios for AI / ML capabilities to manage another AI / ML capability, such as AI / ML verification, testing, deployment, configuration and performance evaluation. In addition, energy consumption / efficiency metrics are studied. Therefore, the energy consumption of AI / ML entities deserves study. Summary of the Invention

[0003] In a first aspect of the present disclosure, a first apparatus is provided. The apparatus includes: at least one processor; and at least one memory, the at least one memory storing instructions that, when executed by the at least one processor, cause the first apparatus to at least: determine first information for a data processing entity, the first information including at least an identifier of the data processing entity and a list of energy-related performance indicators for the data processing entity, wherein the list of energy-related performance indicators includes at least data processing entity performance; and transmit the first information to a second apparatus or a third apparatus.

[0004] In a second aspect of the present disclosure, a second device is provided. The second device includes: at least one processor; and at least one memory, the at least one memory storing instructions that, when executed by the at least one processor, cause the second device to at least: transmit a request for a data processing entity and first information for the data processing entity to a first device, the first information including at least an identifier of the data processing entity and a list of energy-related performance indicators for the data processing entity, wherein the list of energy-related performance indicators includes at least data processing entity performance; and receive second information including the data processing entity and the first information from the first device.

[0005] In a third aspect of the present disclosure, a third apparatus is provided. The third apparatus includes: at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the third apparatus to at least: receive first information for a data processing entity from a first apparatus, the first information including at least an identifier of the data processing entity and a list of energy-related performance indicators for the data processing entity, wherein the list of energy-related performance indicators includes at least data processing entity performance; receive a request for the data processing entity and the first information for the data processing entity from a second apparatus; and transmit second information including the data processing entity and the first information to the second apparatus.

[0006] In a fourth aspect of the present disclosure, a method is provided. The method includes: determining, at a first device, first information for a data processing entity, the first information including at least an identifier of the data processing entity and a list of energy-related performance indicators for the data processing entity, wherein the list of energy-related performance indicators includes at least data processing entity performance; and transmitting the first information to a second device or a third device.

[0007] In a fifth aspect of the present disclosure, a method is provided. The method includes: transmitting, at a second device, a request for a data processing entity and first information for the data processing entity to a first device, the first information including at least an identifier of the data processing entity and a list of energy-related performance indicators for the data processing entity, wherein the list of energy-related performance indicators includes at least data processing entity performance; and receiving, from the first device, second information including the data processing entity and the first information.

[0008] In a sixth aspect of the present disclosure, a method is provided. The method includes: receiving, at a third device, first information for a data processing entity from a first device, the first information including at least an identifier of the data processing entity and a list of energy-related performance indicators for the data processing entity, wherein the list of energy-related performance indicators includes at least data processing entity performance; receiving, from a second device, a request for the data processing entity and the first information for the data processing entity; and transmitting, to the second device, second information including the data processing entity and the first information.

[0009] In a seventh aspect of the present disclosure, a first apparatus is provided. The first apparatus includes: means for determining, at the first apparatus, first information for a data processing entity, the first information including at least an identifier of the data processing entity and a list of energy-related performance indicators for the data processing entity, wherein the list of energy-related performance indicators includes at least data processing entity performance; and means for transmitting the first information to a second apparatus or a third apparatus.

[0010] In an eighth aspect of the present disclosure, a second device is provided. The second device includes: a component for transmitting, at the second device, a request for a data processing entity and first information for the data processing entity to a first device, the first information including at least an identifier of the data processing entity and a list of energy-related performance indicators for the data processing entity, wherein the list of energy-related performance indicators includes at least data processing entity performance; and a component for receiving, from the first device, second information including the data processing entity and the first information.

[0011] In a ninth aspect of the present disclosure, a third device is provided. The third device includes: a component for receiving, at the third device, first information for a data processing entity from a first device, the first information including at least an identifier of the data processing entity and a list of energy-related performance indicators for the data processing entity, wherein the list of energy-related performance indicators includes at least data processing entity performance; a component for receiving, from a second device, a request for the data processing entity and the first information for the data processing entity; and a component for transmitting, to the second device, second information including the data processing entity and the first information.

[0012] In a tenth aspect of the present disclosure, a computer-readable medium is provided, wherein the computer-readable medium includes instructions stored thereon, the instructions being used to cause a device to at least execute the method according to any one of the fourth aspect, the fifth aspect, or the sixth aspect.

[0013] It should be understood that the present invention summary is not intended to identify the key features or essential features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Some example embodiments will now be described with reference to the accompanying drawings, in which:

[0015] Figure 1 An example communication environment is shown in which example embodiments of the present disclosure may be implemented;

[0016] Figure 2A shows an example signaling diagram for managing energy consumption descriptors according to some example embodiments of the present disclosure;

[0017] Figure 2B shows another example signaling diagram for managing energy consumption descriptors according to some example embodiments of the present disclosure;

[0018] Figure 3 shows yet another example signaling diagram for managing energy consumption descriptors according to some example embodiments of the present disclosure;

[0019] Figure 4shows yet another example signaling diagram for managing energy consumption descriptors according to some example embodiments of the present disclosure;

[0020] Figure 5 A flowchart illustrating a method implemented at a first device according to some example embodiments of the present disclosure is shown;

[0021] Figure 6 A flowchart illustrating a method implemented at a second device according to some example embodiments of the present disclosure is shown;

[0022] Figure 7 A flowchart illustrating a method implemented at a third device according to some example embodiments of the present disclosure is shown;

[0023] Figure 8 shows a simplified block diagram of a device suitable for implementing an example embodiment of the present disclosure; and

[0024] Figure 9 A block diagram of an example computer-readable medium is shown, according to some example embodiments of the present disclosure.

[0025] Throughout the drawings, the same or similar reference numerals refer to the same or similar elements. DETAILED DESCRIPTION

[0026] The principles of the present disclosure will now be described with reference to some exemplary embodiments. It should be understood that these embodiments are described for illustrative purposes only and to help those skilled in the art understand and implement the present disclosure without implying any limitation on the scope of the present disclosure. The embodiments described herein can be implemented in various ways except as described below.

[0027] In the following description and claims, unless defined otherwise, all technical and scientific terms used herein may have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure belongs.

[0028] References in this disclosure to "one embodiment," "an embodiment," "an example embodiment," etc., indicate that the described embodiment may include a particular feature, structure, or characteristic, but not every embodiment must include the particular feature, structure, or characteristic. Furthermore, such phrases do not necessarily refer to the same embodiment. Furthermore, when a particular feature, structure, or characteristic is described in conjunction with an embodiment, it is intended that those skilled in the art would recognize and incorporate such feature, structure, or characteristic into other embodiments, whether or not explicitly described.

[0029] It should be understood that although the terms "first", "second", etc. can be used to describe various elements in this article, these elements should not be limited by these terms. These terms are only used to distinguish one element from another element. For example, without departing from the scope of the exemplary embodiments, the first element can be referred to as the second element, and similarly, the second element can be referred to as the first element. As used herein, the term "and / or" includes any and all combinations of one or more of the listed terms.

[0030] As used herein, “at least one of: ” and “at least one of ” and similar expressions, where a list of two or more elements is linked by “and” or “or”, mean at least any one of the elements, or at least any two or more of the elements, or at least all of the elements.

[0031] As used herein, unless explicitly stated otherwise, performing a step “in response to A” does not mean that the step is performed immediately after “A” occurs, but may include one or more intermediate steps.

[0032] The terms used herein are for the purpose of describing specific embodiments only and are not intended to limit the example embodiments. As used herein, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should be further understood that the terms "comprise," "including," "having," "containing," "include," and / or "comprising" when used herein specify the presence of stated features, elements, and / or components, etc., but do not exclude the presence or addition of one or more other features, elements, components, and / or combinations thereof.

[0033] As used in this application, the term "circuitry" may refer to one or more or all of the following: (a) hardware circuit implementation only (such as implementation only in analog and / or digital circuitry) and (b) A combination of hardware circuitry and software such as (if applicable): (i) a combination of analog and / or digital hardware circuit(s) with software / firmware and (ii) any portion of a hardware processor(s) with software (including digital signal processor(s), software, memory(s) that work together to enable a device such as a mobile phone or server to perform various functions) and (c) Hardware circuit(s) and / or processor(s), such as microprocessor(s) or portions of microprocessor(s) that require software (e.g., firmware) for operation (but where software is not required for operation, the software may not be present).

[0034] This definition of circuitry applies to all uses of the term in this application, including any claims. As another example, as used in this application, the term circuitry also encompasses implementations of merely a hardware circuit or processor (or multiple processors), or a portion of a hardware circuit or processor, and its (or their) accompanying software and / or firmware. The term circuitry also encompasses, for example, and as applicable to a particular claim element, a baseband integrated circuit or processor integrated circuit for a mobile device, or a similar integrated circuit in a server, cellular network device, or other computing or networking device.

[0035] As used herein, the term "communication network" refers to a network that complies with any suitable communication standard, such as New Radio (NR), Long Term Evolution (LTE), Advanced LTE (LTE-A), Wideband Code Division Multiple Access (WCDMA), High Speed Packet Access (HSPA), Narrowband Internet of Things (NB-IoT), etc. In addition, the communication between the terminal equipment and the network equipment in the communication network can be performed according to any suitable generation communication protocol, including but not limited to first generation (1G), second generation (2G), 2.5G, 2.75G, third generation (3G), fourth generation (4G), 4.5G, fifth generation (5G) communication protocols and / or any other protocol currently known or developed in the future. The embodiments of the present disclosure can be applied to various communication systems. In view of the rapid development of communications, there will certainly be future types of communication technologies and systems that can embody the present disclosure. It should not be considered that the scope of the present disclosure is limited to the aforementioned systems.

[0036] It should be noted that any section / subsection headings provided herein are not intended to be limiting. Embodiments are described throughout this document, and any type of embodiment may be included under any section / subsection. Furthermore, an embodiment disclosed in any section / subsection may be combined in any manner with any other embodiment described in the same section / subsection and / or in different sections / subsections.

[0037] The term "data processing model" as used herein may refer to an algorithm for processing data. The term "AI / ML model" as used herein may refer to a data-driven algorithm that applies AI / ML techniques to generate a set of outputs based on a set of inputs. The term "AI / ML model" may be interchangeable with the term "data processing model" or "model". The term "AI / ML entity" as used herein may refer to an independent machine learning model, characterized by the model architecture and supporting hyperparameters, an executable software component (.exe format), or an image-based software version used by compatible applications. An AI / ML entity may also be an application that utilizes an ML model to perform a specific function, a network management function, or a network management function. The terms "data processing entity," "AI / ML entity," and "ML entity" may be used interchangeably. The terms "performance indicator" or "key performance indicator" as used herein may refer to a quantifiable measurement used to evaluate the performance of an entity.

[0038] As mentioned above, the energy consumption of AI / ML entities is worthy of investigation. The energy consumption of AI / ML entities depends on a large number of factors. These factors may be related to the execution environment of the AI / ML entity, the requirements for AI / ML performance, and so on. On the other hand, there are many ways to reduce the energy requirements of AI / ML entities. In most cases, this means changing the AI / ML performance or execution environment. A component for identifying, collecting, and exposing these dependencies is a prerequisite for any energy-related optimization of executing AI / ML entities.

[0039] However, there is no indication of the relationship between the energy consumption of AI / ML entities and other fundamental aspects of AI / ML functionality that consumers are primarily interested in, such as achievable ML performance, processing speed, etc. Such a description of energy consumption with respect to other ML aspects is needed to provide consumers (e.g., network operators) with a comprehensive view of ML entities, which is required to make well-informed trade-off decisions. For example, from an operator's perspective, the ultimate goal may be to estimate the most energy-efficient settings for running a certain ML model while achieving minimum acceptable ML performance and / or obtaining results with a desired latency. Furthermore, the following issues remain unresolved: (1) there is no mechanism or means for storing and updating energy consumption-related information in a consistent manner so that discovery and querying of energy consumption-related information about AIML entities can be accomplished by authorized consumers; and (2) there is no method for requesting redetermination of energy-related KPIs under different conditions (e.g., different performance KPIs, processing speeds, hardware and system specifications, applied energy-saving strategies, etc.).

[0040] In one solution, a metric is proposed to measure AIML-related energy consumption during data preprocessing, training, and inference on the AI / ML producer side, and to provide an indication of the expected energy consumption of the AI / ML entity based on the complexity of the AI / ML entity, the data required, and the retraining requirements. Such energy consumption metrics are providing insights into the energy consumption of a specific instance of an AI / ML entity measured per sample, training round, the entire training process, etc. In addition, the solution also provides the definition of an AI / ML energy consumption profile as an indication of the expected energy consumption during the actual data collection, training, or inference phase as measured by the AIML producer. The AI / ML energy consumption profile contains information about AI / ML or about AI / ML-related processes that contributes most to energy consumption and may include indications such as the complexity of the model (e.g., FLOPs per data sample used for inference) or, if available, an indication of the energy consumption of the model when executed at a specific, well-defined reference architecture (along with information / description of the reference architecture).

[0041] However, while this solution supports an indication of different energy consumption for different hardware implementations, it does not provide additional details about energy-related AI / ML aspects (such as AI / ML processing speed) to enable informative trade-offs between energy consumption and ML performance. Furthermore, it does not provide any mechanism to store, retrieve / query, and update information about AI / ML energy consumption related to different aspects of AI / ML (such as performance, processing speed, hardware platform used). Finally, it does not provide any means for requesting training / testing / inference processes based on energy consumption requirements or under different conditions (e.g., different performance KPIs, processing speed, hardware and system specifications, applied energy-saving policies, etc.).

[0042] In order to solve the above and other potential problems, the example embodiments of the present disclosure propose a scheme for determining energy-related performance indicators for AI / ML entities. According to the example embodiments of the present disclosure, a first device determines first information for a data processing entity, the first information including at least: an identifier of the data processing entity and a list of energy-related performance indicators for the data processing entity, and the list of energy-related performance indicators includes at least data processing entity performance. The first information is transmitted to a second device or a third device. In this way, energy consumption-related information can be stored and updated in a consistent manner, so that queries on energy consumption-related information of AIML entities can be completed by authorized consumers.

[0043] Hereinafter, exemplary embodiments of the present disclosure will be described in detail with reference to the accompanying drawings. Example environment and working principle

[0044] Figure 1An example communication environment 100 is shown in which example embodiments of the present disclosure may be implemented. In the communication environment 100, there is a first device 110 and a second device 120. The communication environment 100 may also include a third device 130.

[0045] The first device 110 may be an MnS producer, such as an AI / ML MnS producer. In some example embodiments, the AI / ML MnS producer may be a gNB / CU, another NF different from the first device 110, or an OAM function, in which an ML entity (e.g., an MLApp) executes. One or more AI / ML entities may be associated with the first device 110. The AI / ML entity may be an ML model, or may include an ML model and metadata related to the ML model. The AI / ML entity may be managed as a single composite entity. In some example embodiments, the AI / ML entity may be implemented as an MLApp. It should be understood that this is for illustrative purposes only and does not imply any limitation on the embodiments of the present disclosure. The first device 110 may be one of the following: an AI / ML management service training producer, an AI / ML management service test producer, an AI / ML management service inference producer, a network data analysis function model training logic function, a network data analysis function analysis logic function, a management data analysis function, a cross-domain management data analysis function, a network device, or a terminal device.

[0046] The second device 120 may be a management service (MnS) consumer, such as an AI / ML MnS consumer. In some example embodiments, the AI / ML MnS consumer may be an operations, administration, and maintenance (OAM) or network function (NF) function. The second device may be one of the following: an AI / ML management service training consumer, an AI / ML management service testing consumer, an AI / ML management service inference consumer, a network data analysis function model training logic function, a network data analysis function analysis logic function, a management data analysis function, a cross-domain management data analysis function, a network device, or a terminal device.

[0047] In some example embodiments, the second device 120 may be an operator or a management function (MnF) of the operator and may be implemented as, for example, an AI / ML MnS consumer. The first device 110 may provide management services based on an AI / ML entity as a producer of management services, which is referred to herein as an AI / ML management service producer or an AI / ML MnS producer.

[0048] In some embodiments, the third device 130 may be an analytical data repository function. Alternatively, the third device 130 may be an AI / ML model repository function.

[0049] Hereinafter, for illustrative purposes, some example embodiments are described in which the second device 120 operates as an MnS consumer and the first device 110 operates as an MnS producer. However, in some example embodiments, the operations described in conjunction with the second device 120 may be implemented at a device other than an MnS consumer, and the operations described in conjunction with the first device 110 may be implemented at a device other than an MnS producer.

[0050] Communications in the communication environment 100 may be implemented according to any suitable communication protocol(s), including but not limited to first generation (1G), second generation (2G), third generation (3G), fourth generation (4G), fifth generation (5G), sixth generation (6G), etc. cellular communication protocols, wireless local area network communication protocols such as Institute of Electrical and Electronics Engineers (IEEE) 802.11, etc., and / or any other protocol currently known or developed in the future. Furthermore, communications may utilize any suitable wireless communication technology, including but not limited to: code division multiple access (CDMA), frequency division multiple access (FDMA), time division multiple access (TDMA), frequency division duplex (FDD), time division duplex (TDD), multiple input multiple output (MIMO), orthogonal frequency division multiple access (OFDM), discrete Fourier transform spread OFDM (DFT-s-OFDM), and / or any other technology currently known or developed in the future. Example general process for energy descriptor management

[0051] Figure 2A and Figure 2B An example signaling diagram of a process for managing energy consumption descriptors according to some example embodiments of the present disclosure is shown. For the purpose of discussion, reference will be made to Figure 1 For example, by using the first device 110 and the second device 120 Figure 2A The process 200 shown in FIG. Figure 1 For example, by using the first device 110, the second device 120 and the third device 130 to describe Figure 2B The process shown in 205. Note that Figure 2A and Figure 2B The same reference numerals in the drawings refer to the same steps / operations.

[0052] like Figure 2A and Figure 2BAs shown, the first device 110 determines (2010) first information (also referred to as an "energy consumption descriptor") for a data processing entity. The first information includes an identification of the data processing entity and a list of energy-related performance indicators for the data processing entity. For example, the first device 110 may determine energy-related key performance indicators (KPIs) for ML services subject to other relevant factors. ML services may include one or more of the following: training, testing, or reasoning of AI / ML entities. Advantageously, energy consumption-related information can be stored and updated in a consistent manner, so that queries about energy consumption-related information of AIML entities can be completed by authorized consumers.

[0053] The list of energy-related performance indicators includes data processing entity performance. The list of energy-related performance indicators may also include one or more of the following: a data processing energy consumption performance indicator, a data processing speed performance indicator, or metadata related to the data processing entity. In other words, the first information for the AI / ML entity, identified by the AI / ML entity identifier and the version identity of the AI / ML entity, may include a list of KPIs (such as an ML energy consumption KPI, an ML performance KPI, an ML processing speed KPI, and other metadata related to the AI / ML entity). Such metadata may describe the hardware / system description of the KPIs measured by the AI / ML entity, the batch size used for training / inference, and energy-saving strategies such as pruning or quantization. The initial list provided by the AI / ML MnS producer may include the most common options for implementing certain KPIs for the AI / ML entity. For example, the initial list provided by the MnS producer for AI / ML entity 1 may include basic options: {energy consumption = 3 KWh, accuracy = 92%, processing speed = 13 ms, batch size = 1000, energy-saving strategy = NONE}. Table 1 below shows an example of attributes of the ML energy consumption descriptor (ie, the first information). Note that Table 1 is only an example and not a limitation. Table 1

[0054] The first device 110 may determine first information for a plurality of AI / ML entities. In other words, each AI / ML entity may have corresponding first information. For example, the first device 110 may determine an energy consumption descriptor for each of the plurality of AI / ML entities.

[0055] In some example embodiments, if the third device does not exist, there may be directional communication between the first device 110 and the second device 120, such as Figure 2A In some example embodiments, there may be a third device 130, such as Figure 2B First refer to Figure 2A A description of example embodiments follows.

[0056] The second device 120 transmits (2020) a request for the first information (hereinafter referred to as the "second request"). In some example embodiments, the second device 120 may request one or more AI / ML entities and their corresponding first information. Alternatively or additionally, the second device 120 may request a subset of the available AI / ML entities. In this case, the subset of available AI / ML entities may meet a certain performance indicator requirement / constraint. In some example embodiments, the performance indicator may be an energy consumption requirement. For example, certain energy consumption requirements are based on the maximum expected energy consumption of the AI / ML entity. Certain energy consumption requirements may be in joules or watt*s. Certain performance indicator requirements may include one or more of the following or any combination thereof: a performance KPI constraint, a processing speed constraint, or the above energy consumption requirements.

[0057] The first device 110 transmits (2030) the first information to the second device 120. For example, based on the second request, the first device 110 may transmit the first information to the second device 120. Alternatively, if the second device 120 requests one or more AI / ML entities and third corresponding first information, the first device 110 may transmit information (referred to as "second information") including the one or more AI / ML entities and the corresponding information to the second device 120. In some other example embodiments, if a subset of available AI / ML entities is requested, the second information including the subset of available AI / ML entities and the corresponding information of the subset of available AI / ML entities may be transmitted to the device 120.

[0058] In some example embodiments, the second device 120 may transmit (2040) a request to update the first information (referred to as a "first request") to the first device 110. The first request may include an energy consumption requirement. For example, the energy consumption requirement may include one or more of the following: system information different from the system information in the first information, a data processing performance metric, a decision confidence score, or a data processing speed, an energy saving strategy, or a delay in receiving updated feedback. The energy consumption requirement may also include a requirement to apply an energy saving strategy, such as quantization, pruning, etc. Table 2 shows example energy consumption requirements. Note that Table 2 is only an example and not a limitation. Table 2

[0059] The first device 110 may transmit (2050) feedback to the second device 120 regarding the feasibility of updating the first information based on the energy consumption requirement. For example, the first device 110 may determine whether it can perform the update based on the energy consumption requirement. If the first device 110 can perform the update, the feedback may indicate that the first device 110 can perform the update based on the energy consumption requirement. Alternatively, if the first device 110 cannot perform the update, the feedback may indicate that the first device 110 cannot perform the update based on the energy consumption requirement.

[0060] In some example embodiments, the first device 110 may update (2060) the first information based on the energy consumption requirement. For example, the energy consumption descriptor of the AI / ML entity may be recalculated based on specific requirements including one or more of the following: hardware / system specifications, performance metrics, decision confidence scores, processing speed, and application requirements of energy saving strategies. In some example embodiments, the first information corresponding to one or more data processing entities may be updated based on the energy consumption requirement.

[0061] In some example embodiments, first device 110 may transmit fourth information to second device 120. The fourth information may include updated first information for the data processing entity that has been updated based on the energy consumption requirements. Alternatively or additionally, the fourth information may include first information for another data processing entity, the first information for the other data processing entity including at least another identifier of the other data processing entity and another list of energy-related performance indicators for the other data processing entity. In other words, the fourth information may include an updated energy consumption descriptor for an existing AI / ML entity or a new energy consumption descriptor for a new AI / ML entity.

[0062] In some example embodiments, the first device may receive a request (hereinafter referred to as the "fifth request") from the second device 120 for one of the following: training, testing, or reasoning of a data processing entity based on energy consumption requirements. In this case, the first device may transmit actual energy consumption information including one of the requested items: training, testing, or reasoning of the data processing entity to the second device 120. The report may also include other information, such as an energy saving strategy. In this case, the energy consumption requirement may include at least one of the following: energy saving strategy, expected processing time, expected energy. The energy consumption requirement may also include other requirements / constraints shown in Table 1. For example, after receiving the energy consumption requirement, the first device 110 may change its function (i.e., training, testing, or reasoning) to comply with the first information. In other words, the first device 110 may use the first information as an input requirement for its service generation (i.e., training, testing, or reasoning).

[0063] As mentioned above, there may be a third device 130, such as Figure 2B Now refer to Figure 2B A description of example embodiments follows.

[0064] like Figure 2B As shown, the first device 110 transmits (2110) the first information to the third device 130. In some example embodiments, the first device 110 may transmit a request for registering the first information with the third device 130 (referred to as a "third request"). In this case, the third request may include the first information. As an example, the first device 110 may register the energy consumption descriptor of the AI / ML entity (i.e., the first information) with the third device 130. Thus, the third device 130 may receive the AI / ML entity registration request or update request (i.e., the third request) and may add the energy consumption descriptor to the metadata describing the given registered ML entity.

[0065] The second device 120 transmits (2115) a request for a data processing entity (hereinafter referred to as a "second request") to the third device 130 transmits (2120) second information including the data processing entity and the first information to the second device. For example, the second device 120 may request a list of registered / available AI / ML entities including energy consumption descriptors of the registered / available AI / ML entities. Thus, the third device 130 may provide the second device 120 with a report having registered / available AI / ML entities and corresponding energy consumption descriptors. In some example embodiments, the second request may be for a group of data processing entities and the first information of the group of data processing entities. In this case, the second information may include a group of data processing entities and the corresponding first information.

[0066] In some example embodiments, the set of data processing entities may satisfy performance indicator requirements. For example, the second device may request a list of registered / available AI / ML entities that satisfy a specific KPI requirement / constraint (e.g., energy consumption constraint, performance KPI constraint, processing speed constraint, etc., or a combination thereof). Thus, the third device 130 may provide a report with registered / available AI / ML entities that satisfy the given requirement / constraint and the corresponding energy consumption descriptors.

[0067] The second device 120 may transmit (2125) a request to update the first information (referred to as a "first request") to the third device 130. The first request may include an energy consumption requirement. The third device 130 may transmit (2130) a request to update the first information to the first device 110. For example, the second device 120 may request a recalculation of the energy consumption descriptor (i.e., the first information) of a certain AI / ML entity / list of AI / ML entities by providing specific requirements and / or specifications, such as: hardware / system specifications that are different from the hardware / system specifications defined in the registered energy consumption descriptor; requirements such as, but not limited to, performance metrics, decision confidence scores, processing speed, previous combinations, etc.; and requirements to apply certain energy saving strategies (e.g., quantization, pruning, etc.). Therefore, the third device 130 may transmit the first request to the first device 110 for re-determination of the energy consumption descriptor under the specifications and / or requirements given by the second device 120.

[0068] The first device 110 may transmit (2135) feedback to the third device 130 regarding the feasibility of determining the first information based on the energy consumption requirement provided by the second device 120. The third device 130 may transmit (2140) feedback to the second device 120. For example, the first device 110 may determine whether it can perform an update based on the energy consumption requirement. If the first device 110 can perform the update, the feedback may indicate that the first device 110 can perform the update based on the energy consumption requirement. Alternatively, if the first device 110 cannot perform the update, the feedback may indicate that the first device 110 cannot perform the update based on the energy consumption requirement.

[0069] In some example embodiments, the first device 110 may update (2145) the first information based on the energy consumption requirements. For example, the energy consumption descriptor of the AI / ML entity may be recalculated based on specific requirements including one or more of the following: hardware / system specifications, performance metrics, decision confidence scores, processing speed, application requirements of energy saving strategies. In some example embodiments, the first information corresponding to one or more data processing entities may be updated based on the energy consumption requirements. For example, the first device 110 may update the energy consumption descriptors of its stored / registered ML entities in the AI / ML entity repository based on the newly calculated energy consumption descriptors for specific hardware / system specifications or specific requirements.

[0070] The first device 110 may transmit (2150) a request (referred to as a "fourth request") including the updated first information to the third device 130. In some example embodiments, the first device 110 may store the updated first information. The third device 130 may transmit (2155) the updated first information to the second device 120. In some embodiments, the first device may receive a request (hereinafter referred to as a "fifth request") from the third device 130 for one of the following: training, testing, or inference of a data processing entity based on energy consumption requirements. The fifth request may be transmitted from the second device 120 and forwarded by the third device 130 to the first device 110. In this case, the first device may transmit a report to the third device 130 including energy consumption information for one of the requested items: training, testing, or inference of the data processing entity. The report may also include other information, such as an energy saving strategy. The third device 130 may forward the report including the actual energy consumption information to the second device 120. For example, after receiving the energy consumption requirement, the first device may use the first information as input requirements for its service generation (e.g., training, testing, or inference). In this case, the energy consumption requirement may include at least one of the following: an energy saving strategy, a desired processing time, and a desired energy. The energy consumption requirement may also include other requirements / constraints shown in Table 1 or another requirement / constraint. In some example embodiments, the second device 120 may request training / testing / inference of the AI / ML entity based on the energy consumption requirement / constraint indicated by the consumer. The first device 110 may provide the second device 120 with a descriptor of the actual energy consumption of the requested training / testing / inference of the AI / ML entity.

[0071] According to the reference Figure 2A and Figure 2B In the described embodiments, energy consumption related information can be stored and updated in a consistent manner, so that queries for energy consumption related information about AIML entities can be completed by authorized consumers. Example Procedure for Energy Descriptor Management

[0072] Figure 3 Another example signaling diagram of an energy consumption descriptor management process 300 according to some example embodiments of the present disclosure is shown. Process 300 may involve an AI / ML MnS producer 310, an AI / ML repository 320, and an AI / ML MnS consumer 330. In some example embodiments, AI / ML MnS producer 310 may be implemented at first device 110, AI / ML repository 320 may be implemented at third device 130, and AI / ML MnS consumer 330 may be implemented at second device 120. Process 300 may be applied in the context of 3GPP SA5.

[0073] The AI / ML MnS producer 310 may register (3001) an energy consumption descriptor of an ML entity identified by one or more of aIMLEntityId or mLEntityVersion with the AI / ML entity repository 320. The AI / ML entity repository 320 may contain relevant information about available ML entities and enable querying and retrieving ML entities upon request. Upon registration of the ML energy consumption descriptor, the AI / ML entity repository 320 may add an MLenegyDescriptor to the metadata describing the given registered AI / ML entity.

[0074] An authorized consumer 330 may request (3002) a list of registered / available AI / ML entities including their energy consumption descriptors. Accordingly, the AI / ML entity repository 320 may provide (3003) a report with registered / available AI / ML entities (identified by aIMLEntityId and, if applicable, mLEntityVersion) and their MLenegyDescriptors.

[0075] In addition or alternatively to the query in 3003, the authorized consumer 330 may request (3004) only a subset of registered / available AI / ML entities that meet certain energy consumption requirements / constraints. Such requirements may be based on the maximum desired energy consumption of the AI / ML entity and may be expressed in joules or watts*s.

[0076] Thus, the AI / ML entity repository 320 may provide (3005) a report of AI / ML entities and corresponding MLenegyDescriptors that meet a given energy consumption requirement. If, from the consumer's perspective, energy consumption information is missing, e.g., there is no information about the energy consumption for an AI / ML entity operating under certain conditions or achieving a specific performance desired by the consumer, then an authorized consumer 330 may request (3006) a recalculation of the energy consumption descriptor. Thus, the authorized consumer 330 may provide in the recalculation request specific requirements and / or specifications for which the energy consumption descriptor is to be recalculated. This may include, but is not limited to, requirements for: hardware / system specifications that are different from those defined in the available / registered energy consumption descriptors; ML performance metrics, such as decision confidence scores, ML processing speed; application of certain energy saving strategies, such as quantization, pruning, etc.; maximum latency for receiving recalculation feedback. Such a request may be communicated directly to the AI / MLMnS producer 310, such as Figure 3As depicted, or may be sent to the AI / ML repository 320. In this case, the AI / ML repository 320 may send a request to the AI / ML MnS producer 310 for recalculation of the energy consumption descriptor under the specifications and / or requirements given by the AI / ML MnS consumer 330.

[0077] The AI / ML MnS producer 310 may provide (3007) feedback on the feasibility of determining the energy consumption descriptor based on the conditions provided by the authorized consumer 330. Such feedback may be as follows: Figure 4 The depicted data is given directly to the AI / ML MnS consumer 330 or via the AI / ML repository 320 .

[0078] The AI / ML MnS producer 310 may perform (3008) a recalculation of the energy consumption descriptor based on the provided requirements / specifications. The AI / ML MnS producer 310 may update (3009) the ML energy consumption descriptor in the AI / ML repository 320 based on the newly calculated energy consumption for a specific hardware / system specification or specific requirements. This may result in an update of an existing AI / ML entity or the registration of a new AI / ML entity. The AI / ML repository 320 may provide (3010) an updated MLenegyDescriptor that matches the recalculation request. In other words, the AI / ML MnS consumer 330 may receive (3010) an updated MLenegyDescriptor that matches the recalculation request. Another example update process for energy descriptor management

[0079] Figure 4 Another example signaling diagram of an energy consumption descriptor management process 400 according to some example embodiments of the present disclosure is shown. The process 400 may involve a network data analysis function (NWDAF), a model training logic function (MTLF) 410, an analysis data repository function (ADRF) 420, an NWDAF analysis logic function (AnLF) 430, and an analysis consumer 440. In some example embodiments, the NWDAF 410 and the ADRF 420 may be implemented at the first device 110. Alternatively, the NWDAF 410 may be implemented at the first device 110, and the ADRF 420 may be implemented at the second device 120. The analysis consumer 440 and the AnLF 430 may be implemented at the second device 120. The process 400 may be applied in the context of 3GPP SA2.

[0080] The NWDAF MTLF 410 may store (4001) the energy consumption descriptor of the ML model in the ADRF. The ADRF 420 may contain relevant information about the available ML models and enable querying and retrieving the ML models according to specific requirements. Alternatively, the NWDAF MTLF 410 itself may store (4002) the energy consumption descriptor of the ML model, enabling querying and retrieving the ML model according to specific requirements.

[0081] The analysis consumer 440 may request (4003) a specific analysis and a preferred level of energy consumption requirements from the NWDAF AnLF 430. The NWDAF AnLF 430 may request (4004) a list of registered / available ML models including their energy consumption descriptors from the ADRF 420. Alternatively, the NWDAF AnLF 430 may request (4006) a list of registered / available ML models including their energy consumption descriptors from the NWDAF MTLF 410.

[0082] The ADRF 420 may provide (4005) a report with a list of registered / available ML models and their energy consumption descriptors to the NWDAF AnLF 430. Alternatively, the NWDAF MTLF 410 may provide (4007) a report with a list of registered / available ML models and their energy consumption descriptors to the NWDAF AnLF 430.

[0083] In addition to or as an alternative to the query at 4004, the NWDAF AnLF 430 may request (4008) only a subset of registered / available ML models that meet certain energy consumption requirements / constraints from the ADRF 420. Such requirements may be in terms of a maximum desired energy consumption of the ML models and may be expressed in Joules or Watts. In some example embodiments, in addition to or as an alternative to the query at 4006, the NWDAF AnLF 430 may request (4010) only a subset of registered / available ML models that meet certain energy consumption requirements / constraints from the NWDAF MTLF 410.

[0084] ADRF 420 may provide (4009) a report with an ML model and corresponding energy consumption descriptors that meet the given energy consumption requirements to NWDAF AnLF 430. Alternatively, NWDAF MTLF 410 may provide (4011) a report with an ML model and corresponding energy consumption descriptors that meet the given energy consumption requirements to NWDAF AnLF 430.

[0085] If energy consumption information is missing from the perspective of the NWDAF AnLF 430, e.g., there is no information about the energy consumption of the ML model operating under certain conditions or achieving certain performance desired by the NWDAF analytics consumer 440, the NWDAF AnLF 430 may request (4012) a recalculation of the energy consumption descriptor from the NWDAF MTLF 410. Thus, the NWDAF AnLF 430 may provide in the recalculation request specific requirements and / or specifications for which the energy consumption descriptor is to be recalculated. This may include, but is not limited to, requirements for hardware / system specifications that differ from those defined in the available / registered energy consumption descriptors, ML performance metrics such as decision confidence scores, ML processing speed, application of certain energy saving strategies (e.g., quantization, pruning, etc.), maximum latency for receiving recalculation feedback, etc.

[0086] The NWDAF MTLF 410 may perform ( 4013 ) recalculation of the energy consumption descriptor based on the requirements / specifications provided in 4012 .

[0087] The NWDAF MTLF 410 may update (4014) the updated energy consumption descriptor in the ADRF based on the newly calculated energy consumption for specific hardware / system specifications or specific requirements. Additionally, this may result in the update of an existing ML model or the registration of a new ML model that may be stored in the ADRF. Alternatively, the NWDAF MTLF 410 may store (4015) the updated energy consumption descriptor along with the updated ML model.

[0088] The NWDAF MTLF 410 may provide (4016) feedback on the result of recalculating the energy consumption descriptor based on the conditions provided by the NWDAF AnLF 430. Additionally, the NWDAF MTLF 410 may indicate the availability of an updated ML model (in the ADRF 420).

[0089] The NWDAF AnLF 430 may request (4017) the updated ML model and the updated energy consumption descriptor from the ADRF 430. Alternatively, the NWDAF AnLF 430 may request (4019) the updated ML model and the updated energy consumption descriptor from the NWDAF MTLF 410.

[0090] The ADRF 420 may provide the requested updated ML model along with the updated energy consumption descriptor to the NWDAF AnLF 430 (4018). Alternatively, the NWDAF MTLF 410 may directly provide (4020) the requested updated ML model and the updated energy consumption descriptor to the NWDAF AnLF 430. The NWDAF AnLF 430 may provide (4021) the requested analysis that meets the energy consumption requirements to the analysis consumer 440. Example information model definition for ML abstract behavior management

[0091] The following example embodiments of the present disclosure will discuss the information object classes (IOCs) and data types required to implement ML transfer learning and the relationship between these IOCs and data types. The following are example embodiments applicable to 3GPP TS28.105. The proposed extension enables requesting energy-aware training / testing / inference of AI / ML entities. Energy-related requirements are specified by AI / MLMnS consumers (training / testing / inference) in the corresponding requests. This section provides detailed examples in the context of the training process (MLTrainingRequest, MLTrainingReport). However, the same approach also applies to testing and inference. Use Cases Axe Use Cases Energy consumption of Axx ML entities

[0092] Energy consumption in ML services has become a key area of interest. From the perspective of network service sustainability, energy efficiency has become a crucial aspect. The energy consumption of ML entities depends on multiple factors, including the execution environment and performance requirements. To make ML entities and services energy-efficient, it is necessary to discover, query, store, and update the energy consumption of ML entities and services. Y Energy Consumption Aware ML Training Axy Energy-Aware ML Training

[0093] Optimizing energy consumption continues to grow in importance and has become a critical factor in network operations. ML training is a potentially energy-intensive process. Periodic retraining of AI / ML models is required to improve ML performance. Therefore, enabling energy-aware ML training is crucial. Furthermore, enabling authorized consumers to provide energy-related requirements for ML training based on the use case is crucial. Axz potential requirements

[0094] REQ-AIML_ENERGY-01 The 3GPP management system shall enable producers of ML services to provide authorized consumers of ML services with means to discover, query, store and update the energy consumption of ML entities and services.

[0095] REQ-AIML_ENERGY-02 The 3GPP management system shall enable authorized consumers of ML services to request producers to provide requirements for energy consumption for ML entities or services, and also provide updated models with required energy consumption characteristics.

[0096] REQ-AIML_ENERGY-03: AI / ML MnS Producers shall have the capability to allow authorized AI / ML MnS Consumers to provide energy consumption requirements for training of ML entities.

[0097] REQ-AIML_ENERGY-04: AI / ML MnS Producers shall have the ability to provide energy consumption reports on specific training instances to authorized AI / ML MnS Consumers. Axz1 possible solution

[0098] Extensions to existing data types and IOCs are needed to support the energy-aware training required by AI / ML MnS consumers and the reporting of energy consumption metrics by AI / ML MnS producers. Ax1 data type definition Ax1.1ML MLEnergyConsumptionRequirement< <datatype>> Ax1.1.1 Definition

[0099] This data type specifies the requirements from the consumer regarding energy consumption for any ML process including training and inference. Ax1.1.2 Properties Table 3 Ax1.1.3 Attribute Constraints

[0100] If isEnergyConsumptionNeeded is TRUE, expectedEnergyConsumption is provided. Ax1.1.4 Notice

[0101] Targeting the use of < <datatype>>Notifications specified for the IOC of the <<Data Type>> attribute(s) shall be applicable. Ax1.2MLEnergyConsumptionDescriptor< <datatype>> Ax1.2.1 Definition

[0102] This data type specifies descriptors of energy consumption aspects of an ML entity. Ax1.2.2 Properties Table 4 Ax1.2.3 Attribute Constraints

[0103] none Ax1.2.4 Notice

[0104] Targeting the use of < <datatype>>Notifications specified for the IOC of the <<Data Type>> attribute(s) shall be applicable. Ax1.3MLTrainingRequest Ax1.3.1 Definition

[0105] The IOC MLTrainingRequest represents an AI / ML model training request created by an ML training MnS consumer.

[0106] MLTrainingRequest MOI is contained under a MLTrainingFunction MOI. Each AIMLTrainingRequest is associated with at least one MLEntity.

[0107] The MLTrainingRequest can have a source that identifies where it comes from and can be used to prioritize training resources from different sources. The source can be, for example, a network function, an operator role, or other functional distinction.

[0108] Each MLTrainingRequest may indicate an expectedRunTimeContext that describes the specific conditions under which the MLEntity may be trained.

[0109] If the request is accepted, the ML Training MnS Producer decides when to start ML training. Once the MnS Producer decides to start training based on the request, the ML Training MnS Producer instantiates one or more MLTrainingProcess MOIs that are responsible for performing the following:

[0110] - if training data is not available or data is available but insufficient for training, collect (more) data for training;

[0111] - Prepare and select the required training data, taking into account the candidate training data (if any) provided by the consumer's request. The ML training MnS producer can examine the candidate training data provided by the consumer and select none, some, or all of them for training. In addition, the ML training MnS producer can select some other available training data in order to meet the consumer's requirements for MLentity training;

[0112] - Train MLEntity using the selected and prepared training data.

[0113] MLTrainingRequest can have a requestStatus field to indicate the status of a specific MLTrainingRequest:

[0114] - The property values are "NOT_STARTED", "TRAINING_IN_PROGRESS", "SUSPENDED", "FINISHED", and "CANCELLED".

[0115] - When the value becomes "TrainingInProcess", the ML Training MNS Producer instantiates one or more MLTrainingProcess(es) MOIs indicating that the(es) training process(es) are being executed for each request, and notifies the MLT MNS Consumer(s) subscribed to the notification.

[0116] When all training processes associated with this request are completed, the value becomes "Done". Ax1.3.2 Properties Table 5 Ax1.3.3 Attribute Constraints

[0117] none Ax1.3.4 Notice

[0118] The public notices defined in clause 7.6 apply to this IOC without exception or addition. Ax1.4MLTrainingReport Ax1.4.1 Definition

[0119] IOC MLTrainingReport represents the ML model training report provided by the training MnS producer.

[0120] The MLTrainingReport MOI is contained under an MLTrainingFunction MOI. Ax1.4.2 Properties Table 6 Ax1.4.3 Attribute Constraints Table 7 Ax1.4.4 Notice

[0121] The public notices defined in clause 7.6 apply to this IOC without exception or addition.

[0122] Note: As mentioned above, because the training process is currently specified in 3GPP SA5, MLTraingRequest and MLTraingReport are described in detail in this disclosure. However, the corresponding additions of mLEnergyConsumptionRequest and mLEnergyConsmptionDescriptor are applicable to other processes such as inference or testing, and once these processes are included in the 3GPP SA5 specification, the corresponding content will also be updated. Example Methods

[0123] Figure 5 FIG. 5 is a flow chart illustrating an example method 500 implemented at a first device according to some example embodiments of the present disclosure. For discussion purposes, Figure 1 The method 500 is described from the perspective of the first device 110.

[0124] At block 510, a first device determines first information for a data processing entity. The first information includes at least an identification of the data processing entity and a list of energy-related performance indicators for the data processing entity. The list of energy-related performance indicators includes at least data processing entity performance.

[0125] In block 520, the first device transmits the first information to the second device or the third device.In some example embodiments, upon receiving the first request for updating the first information, the first device may update the first information based on the energy consumption requirement included in the first request.

[0126] In some example embodiments, the list of energy-related performance indicators further includes at least one of the following: a data processing energy consumption performance indicator, a data processing speed performance indicator, or metadata related to the data processing entity. In some example embodiments, the energy consumption requirement includes at least one of the following: system information different from the system information in the first information, a data processing performance metric, a data processing speed, an energy saving strategy, or a delay in receiving updated feedback.

[0127] In some example embodiments, a first device may receive a first request to update first information from a second device. In some example embodiments, the first device may transmit feedback to the second device regarding the feasibility of updating the first information based on the energy consumption requirement. In some example embodiments, the first device may receive the first request to update the first information from a third device that received the first request from the second device. In some example embodiments, the first device may transmit feedback to the third device regarding the feasibility of updating the first information based on the energy consumption requirement.

[0128] In some example embodiments, a first device may receive, from a second device, a second request for a set of data processing entities and corresponding first information for the set of data processing entities. In some example embodiments, the first device may transmit, to the second device, second information including the set of data processing entities and the corresponding first information. In some example embodiments, the set of data processing entities meets performance indicator requirements.

[0129] In some example embodiments, the first device may transmit fourth information to the second device. The fourth information may include updated first information for the data processing entity that has been updated based on the energy consumption requirement. Alternatively, the fourth information may include first information for another data processing entity, the first information for the other data processing entity including at least another identifier of the other data processing entity and another list of energy-related performance indicators for the other data processing entity.

[0130] In some example embodiments, the first device may transmit a third request to the third device for registering the first information with the third device, the third request including the first information. In some example embodiments, the first device may transmit a fourth request to the third device including the updated first information. In some example embodiments, the first device may store the updated first information.

[0131] In some example embodiments, the first device may receive a fifth request from the second device or the third device for one of the following: training, testing, or inference of a data processing entity based on energy consumption requirements. In this case, the first device may transmit to the second device or the third device a report including actual energy consumption information of the requested one of the following: training, testing, or inference of the data processing entity. In this case, the energy consumption requirement includes at least one of the following: an energy saving strategy, an expected time for processing, or an expected energy.

[0132] Figure 6 FIG. 6 is a flow chart illustrating an example method 600 implemented at a second device according to some example embodiments of the present disclosure. Figure 1 The method 600 is described from the perspective of the second device 120.

[0133] At block 610, a second device transmits a request for a data processing entity and first information for the data processing entity. The first information includes at least an identifier of the data processing entity and a list of energy-related performance indicators for the data processing entity. The list of energy-related performance indicators includes at least performance of the data processing entity.

[0134] At block 620 , the second device receives second information including the data processing entity and the first information from the first device.

[0135] In some example embodiments, a first request for updating first information is transmitted to the first device, the first request including an energy consumption requirement. In some example embodiments, the second device may receive feedback from the first device regarding the feasibility of updating the first information based on the energy consumption requirement.

[0136] In some example embodiments, the list of energy-related performance indicators further includes at least one of the following: a data processing energy consumption performance indicator, a data processing speed performance indicator, or metadata related to the data processing entity. In some example embodiments, the energy consumption requirement includes at least one of the following: system information different from the system information in the first information, a data processing performance metric, a data processing speed, an energy saving strategy, or a delay in receiving updated feedback.

[0137] In some example embodiments, the second device may transmit a second request for a set of data processing entities and corresponding first information for the set of data processing entities to the first device. In some example embodiments, the second device may receive third information from the first device, the third information including the set of data processing entities and the corresponding first information. In some example embodiments, the set of data processing entities meets the performance indicator requirement.

[0138] In some example embodiments, the second device may receive fourth information from the first device. The fourth information may include updated first information for the data processing entity that has been updated based on the energy consumption requirement. Alternatively, the fourth information may include first information for another data processing entity, the first information for the other data processing entity including at least another identification of the other data processing entity and another list of energy-related performance indicators for the other data processing entity.

[0139] In some example embodiments, a fifth request is transmitted to the first device for one of the following: training, testing, or inference of a data processing entity based on energy consumption requirements. In this case, a report of actual energy consumption information for the requested one of the following: training, testing, or inference of the data processing entity is received from the first device. In this case, the energy consumption requirement may include at least one of the following: an energy saving strategy, a desired processing time, or a desired energy consumption.

[0140] Figure 7 FIG. 7 is a flow chart illustrating an example method 700 implemented at a third device according to some example embodiments of the present disclosure. Figure 1 Method 700 is described from the perspective of the third device 130.

[0141] At block 710, a third device receives first information for a data processing entity from a first device. The first information includes at least an identifier of the data processing entity and a list of energy-related performance indicators for the data processing entity. The list of energy-related performance indicators includes at least performance of the data processing entity.

[0142] At block 720 , the third device receives a request for a data processing entity and first information for the data processing entity from the second device.

[0143] At block 730 , the third device transmits second information including the data processing entity and the first information to the second device.

[0144] In some example embodiments, a third device may receive a first request from a second device to update first information, the first request including an energy consumption requirement. In some example embodiments, the third device may transmit the first request to the first device. In some example embodiments, the third device may receive feedback from the first device regarding the feasibility of updating the first information based on the energy consumption requirement. In some example embodiments, the third device may transmit the feedback to the second device.

[0145] In some example embodiments, the list of energy-related performance indicators further includes at least one of the following: a data processing energy consumption performance indicator, a data processing speed performance indicator, or metadata related to the data processing entity. In some example embodiments, the energy consumption requirement includes at least one of the following: system information different from the system information in the first information, a data processing performance metric, a data processing speed, an energy saving strategy, or a delay in receiving updated feedback.

[0146] In some example embodiments, a third device may receive, from a second first device, a second request for a group of data processing entities and corresponding information for the group of data processing entities. In some example embodiments, the third device may transmit third information to the second device, the third information including the group of data processing entities and the corresponding first information. In some example embodiments, the group of data processing entities meets the performance indicator requirement.

[0147] In some example embodiments, the third device may receive a third request from the first device to register the first information with the third device, the third request including the first information. In some example embodiments, the third device may receive a fourth request from the first device including the updated first information. Example devices, equipment, and media

[0148] In some example embodiments, a first device (eg, Figure 1 The first device 110 in the embodiment may include a component for performing the corresponding operation of the method 500. The component may be implemented in any suitable form. For example, the component may be implemented in a circuit system or a software module. The first device may be implemented as Figure 1 The first device 110 or is included in Figure 1 In the first device 110.

[0149] In some example embodiments, the first device includes: a component for determining first information for a data processing entity, the first information including at least: an identification of the data processing entity and a list of energy-related performance indicators for the data processing entity, and the list of energy-related performance indicators includes at least data processing entity performance; and a component for transmitting the first information to a second device or a third device.

[0150] In some example embodiments, the first apparatus comprises means for, when receiving the first request for updating the first information, updating the first information based on the energy consumption requirement included in the first request.

[0151] In some example embodiments, the list of energy-related performance indicators further includes at least one of the following: a data processing energy consumption performance indicator, a data processing speed performance indicator, or metadata related to a data processing entity.

[0152] In some example embodiments, the energy consumption requirement includes at least one of: system information different from the system information in the first information, a data processing performance metric, a data processing speed, a power saving strategy, or a delay in receiving updated feedback.

[0153] In some example embodiments, a first device includes: means for receiving a first request to update first information from a second device; and means for transmitting feedback to the second device regarding the feasibility of updating the first information based on energy consumption requirements. In some example embodiments, the first device includes: means for receiving the first request to update the first information from a third device that received the first request from the second device; and means for transmitting feedback to the third device regarding the feasibility of updating the first information based on energy consumption requirements.

[0154] In some example embodiments, the first device includes: a component for receiving a second request for a set of data processing entities and corresponding first information for the set of data processing entities from a second device; and a component for transmitting second information to the second device, the second information including the set of data processing entities and the corresponding first information.

[0155] In some example embodiments, the set of data processing entities meets performance indicator requirements.

[0156] In some example embodiments, the first device includes a component for transmitting fourth information to the second device, wherein the fourth information includes at least one of the following: updated first information for the data processing entity that has been updated based on the energy consumption requirement, or first information for another data processing entity, the first information for the other data processing entity including at least another identification of the other data processing entity and another list of energy-related performance indicators for the other data processing entity.

[0157] In some example embodiments, the first device includes means for transmitting, to a third device, a third request for registering the first information with the third device, the third request including the first information.

[0158] In some example embodiments, the first apparatus comprises means for transmitting a fourth request comprising the updated first information to the third apparatus.

[0159] In some example embodiments, the first device comprises means for storing the updated first information.

[0160] In some example embodiments, the first device includes: a component for receiving a fifth request from the second device or the third device for one of: training, testing, or reasoning of a data processing entity based on energy consumption requirements; and a component for transmitting to the second device or the third device a report including energy consumption information of the requested one of: training, testing, or reasoning of the data processing entity.

[0161] In some example embodiments, the energy consumption requirement includes at least one of: an energy saving strategy, an expected time for processing, or an expected energy.

[0162] In some example embodiments, the first device includes one of the following: an artificial intelligence machine learning (AI / ML) management service training producer, an AI / ML management service test producer, an AI / ML management service inference producer, a network data analysis function model training logic function, a network data analysis function analysis logic function, a management data analysis function, a cross-domain management data analysis function, a network device or a terminal device; and wherein the second device includes one of the following: an AI / ML management service training consumer, an AI / ML management service test consumer, an AI / ML management service inference consumer, a network data analysis function model training logic function, a network data analysis function analysis logic function, a management data analysis function, a cross-domain management data analysis function, a network device or a terminal device; and wherein the third device includes one of the following: an analysis data repository function or an AI / ML model repository function.

[0163] In some example embodiments, a second device (eg, Figure 1 The second device 120 in the embodiment may include a component for performing the corresponding operation of method 600. The component may be implemented in any suitable form. For example, the component may be implemented in a circuit system or a software module. The second device may be implemented as Figure 1 The second device 120 or included in Figure 1 In the second device 120.

[0164] In some example embodiments, the second device includes: a component for transmitting a request for a data processing entity and first information for the data processing entity to the first device, the first information including at least: an identification of the data processing entity and a list of energy-related performance indicators for the data processing entity, and the list of energy-related performance indicators includes at least data processing entity performance; and a component for receiving second information including the data processing entity and the first information from the first device.

[0165] In some example embodiments, the second device includes: means for transmitting a first request for updating first information to the first device, the first request including an energy consumption requirement; and means for receiving feedback from the first device regarding the feasibility of updating the first information based on the energy consumption requirement.

[0166] In some example embodiments, the list of energy-related performance indicators further includes at least one of the following: a data processing energy consumption performance indicator, a data processing speed performance indicator, or metadata related to a data processing entity.

[0167] In some example embodiments, the energy consumption requirement includes at least one of: system information different from the system information in the first information, a data processing performance metric, a data processing speed, a power saving strategy, or a delay in receiving updated feedback.

[0168] In some example embodiments, the second device includes: a component for transmitting a second request for a group of data processing entities and corresponding first information for the group of data processing entities to the first device; and a component for receiving third information from the first device, the third information including the group of data processing entities and the corresponding first information.

[0169] In some example embodiments, the set of data processing entities meets performance indicator requirements.

[0170] In some example embodiments, the second device includes: a component for receiving fourth information from the first device, wherein the fourth information includes at least one of the following: updated first information for the data processing entity that has been updated based on the energy consumption requirement, or first information for another data processing entity, the first information for another data processing entity including at least another identification of the another data processing entity and another list of energy-related performance indicators for the another data processing entity.

[0171] In some example embodiments, the second device includes: a component for transmitting to the first device a fifth request for one of the following items: training, testing, or reasoning of a data processing entity based on energy consumption requirements; and a component for receiving from the first device a report including actual energy consumption information of the requested one of the following items: training, testing, or reasoning of the data processing entity.

[0172] In some example embodiments, the second device includes one of the following: an AI / ML management service training consumer, an AI / ML management service testing consumer, an AI / ML management service inference consumer, a network data analysis function model training logic function, a network data analysis function analysis logic function, a management data analysis function, a cross-domain management data analysis function, a network device or a terminal device; and wherein the first device includes one of the following: an artificial intelligence machine learning (AI / ML) management service training producer, an AI / ML management service testing producer, an AI / ML management service inference function, a network data analysis function model training logic function, a network data analysis function analysis logic function, a management data analysis function, a cross-domain management data analysis function, a network device or a terminal device; or wherein the first device includes one of the following: an analysis data repository function or an AI / ML model repository function.

[0173] In some example embodiments, a third device (e.g., Figure 1 The third device 130 in the embodiment may include a component for performing the corresponding operation of method 700. The component may be implemented in any suitable form. For example, the component may be implemented in a circuit system or a software module. The third device may be implemented as Figure 1 The third device 130 or included in Figure 1 In the third device 130.

[0174] In some example embodiments, the third device includes: a component for receiving first information for a data processing entity from the first device, the first information including at least: an identification of the data processing entity and a list of energy-related performance indicators for the data processing entity, and the list of energy-related performance indicators includes at least data processing entity performance; a component for receiving a request for the data processing entity and the first information for the data processing entity from the second device; and a component for transmitting second information including the data processing entity and the first information to the second device.

[0175] In some example embodiments, the third device includes: a component for receiving a first request for updating the first information from the second device, the first request including an energy consumption requirement; a component for transmitting the first request to the first device; a component for receiving feedback from the first device regarding the feasibility of updating the first information based on the energy consumption requirement; and a component for transmitting the feedback to the second device.

[0176] In some example embodiments, the list of energy-related performance indicators further includes at least one of the following: a data processing energy consumption performance indicator, a data processing speed performance indicator, or metadata related to a data processing entity.

[0177] In some example embodiments, the energy consumption requirement includes at least one of: system information different from the system information in the first information, a data processing performance metric, a data processing speed, a power saving strategy, or a delay in receiving updated feedback.

[0178] In some example embodiments, the third device includes: a component for receiving a second request for a group of data processing entities and corresponding information for the group of data processing entities from a second first device; and a component for transmitting third information to the second device, the third information including the group of data processing entities and the corresponding first information.

[0179] In some example embodiments, the set of data processing entities meets performance indicator requirements.

[0180] In some example embodiments, the third apparatus includes means for receiving, from the first apparatus, a third request for registering the first information with the third apparatus, the third request including the first information.

[0181] In some example embodiments, the third apparatus comprises means for receiving, from the first apparatus, a fourth request comprising the updated first information.

[0182] In some example embodiments, the first device includes one of the following: an artificial intelligence machine learning (AI / ML) management service training producer, an AI / ML management service test producer, an AI / ML management service inference producer, a network data analysis function model training logic function, a network data analysis function analysis logic function, a management data analysis function, a cross-domain management data analysis function, a network device or a terminal device; and wherein the second device includes one of the following: an AI / ML management service training consumer, an AI / ML management service test consumer, an AI / ML management service inference consumer, a network data analysis function model training logic function, a network data analysis function analysis logic function, a management data analysis function, a cross-domain management data analysis function, a network device or a terminal device; and wherein the third device includes one of the following: an analysis data repository function or an AI / ML model repository function.

[0183] Figure 8 is a simplified block diagram of a device 800 suitable for implementing an example embodiment of the present disclosure. The device 800 may be configured to implement a communication device, such as Figure 1 As shown in the figure, the device 800 includes one or more processors 810, one or more memories 820 coupled to the processors 810, and one or more communication modules 840 coupled to the processors 810.

[0184] The communication module 840 is configured for bidirectional communication. The communication module 840 has one or more communication interfaces to facilitate communication with one or more other modules or devices. A communication interface may represent any interface necessary to communicate with other network elements. In some example embodiments, the communication module 840 may include at least one antenna.

[0185] Processor 810 can be of any type suitable for the local technology network and can include one or more of the following: as non-limiting examples, a general-purpose computer, a special-purpose computer, a microprocessor, a digital signal processor (DSP), and a processor based on a multi-core processor architecture. Device 800 can have multiple processors, such as application-specific integrated circuit chips that are time-slave to a clock of a synchronized main processor.

[0186] The memory 820 may include one or more non-volatile memories and one or more volatile memories. Examples of non-volatile memories include, but are not limited to, read-only memory (ROM) 824, electrically programmable read-only memory (EPROM), flash memory, hard disks, compact discs (CDs), digital video discs (DVDs), optical discs, laser discs, and other magnetic and / or optical memories. Examples of volatile memories include, but are not limited to, random access memory (RAM) 822 and other volatile memories that will not be maintained during power outages.

[0187] The computer program 830 includes computer-executable instructions executed by the associated processor 810. The instructions of the program 830 may include instructions for performing the operations / actions of some example embodiments of the present disclosure. The program 830 may be stored in a memory (e.g., ROM 824). The processor 810 may perform any suitable actions and processes by loading the program 830 into the RAM 822.

[0188] The exemplary embodiments of the present disclosure may be implemented with the aid of a program 830, so that the device 800 may perform the operations described with reference to FIG. Figure 7 Any process of the present disclosure discussed. The exemplary embodiments of the present disclosure may also be implemented by hardware, or by a combination of hardware and software.

[0189] In some example embodiments, the program 830 may be tangibly embodied in a computer-readable medium that may be included in the device 800 (e.g., memory 820) or other storage device accessible by the device 800. The device 800 may load the program 830 from the computer-readable medium to the RAM 822 for execution. In some example embodiments, the computer-readable medium may include any type of non-transitory storage medium, such as ROM, EPROM, flash memory, hard disk, CD, DVD, etc. The term "non-transitory" as used herein is a limitation of the medium itself (i.e., tangible, not a signal), not a limitation on data storage persistence (e.g., RAM versus ROM).

[0190] Figure 9 An example of a computer readable medium 900 is shown which may be in the form of a CD, DVD, or other optical storage disk. The computer readable medium 900 has a program 830 stored thereon.

[0191] In general, various embodiments of the present disclosure may be implemented in hardware or dedicated circuits, software, logic, or any combination thereof. Some aspects may be implemented in hardware, while other aspects may be implemented in firmware or software that may be executed by a controller, microprocessor, or other computing device. Although various aspects of the embodiments of the present disclosure are shown and described as block diagrams, flow charts, or using some other graphical representation, it should be understood that, as non-limiting examples, the blocks, devices, systems, techniques, or methods described herein may be implemented in hardware, software, firmware, dedicated circuits or logic, general-purpose hardware or a controller or other computing device, or some combination thereof.

[0192] Some example embodiments of the present disclosure also provide at least one computer program product tangibly stored on a computer-readable medium such as a non-transitory computer-readable medium. The computer program product includes computer-executable instructions, such as computer-executable instructions included in a program module executed in a device on a target physical or virtual processor to implement any of the methods described above. Typically, program modules include routines, programs, libraries, objects, classes, components, data structures, etc. that perform specific tasks or implement specific abstract data types. In various embodiments, the functions of the program modules can be combined or split between program modules as needed. The machine-executable instructions for the program modules can be executed in local or distributed devices. In distributed devices, the program modules can be located in both local and remote storage media.

[0193] The program code for implementing the method of the present disclosure can be written in any combination of one or more programming languages. The program code can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device so that when the program code is executed by the processor or controller, the functions / operations specified in the flow chart and / or block diagram are implemented. The program code can be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0194] In the context of the present disclosure, computer program codes or related data may be carried by any suitable carrier to enable a device, apparatus or processor to perform various processes and operations as described above. Examples of carriers include signals, computer-readable media, etc.

[0195] The computer readable medium may be a computer readable signal medium or a computer readable storage medium. The computer readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of computer readable storage media would include an electrical connection having one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0196] In addition, although operations are depicted in a particular order, this should not be understood as requiring that such operations be performed in the particular order shown or in order, or that all operations shown be performed to achieve the desired result. In certain cases, multitasking and parallel processing may be advantageous. Similarly, although several specific implementation details are included in the above discussion, these should not be interpreted as limiting the scope of this disclosure, but rather as describing features that may be specific to a particular embodiment. Unless expressly stated otherwise, the specific features described in the context of a separate embodiment may also be implemented in combination in a single embodiment. On the contrary, unless expressly stated otherwise, the various features described in the context of a single embodiment may also be implemented in multiple embodiments individually or in any suitable subcombination.

[0197] Although the disclosure has been described in language specific to structural features and / or methodological acts, it is to be understood that the disclosure defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are disclosed as example forms of implementing the claims.< / datatype> < / datatype> < / datatype> < / datatype>

Claims

1. A first device, comprising: at least one processor; as well as at least one memory storing instructions that, when executed by the at least one processor, cause the first device to: determining first information for a data processing entity, the first information comprising at least: an identification of the data processing entity and a list of energy-related performance indicators for the data processing entity, wherein the list of energy-related performance indicators comprises at least data processing entity performance; as well as The first information is transmitted to a second device or a third device.

2. The first device of claim 1 , wherein the instructions, when executed by the at least one processor, further cause the first device to at least: When a first request for updating the first information is received, the first information is updated based on the energy consumption requirement included in the first request.

3. The first apparatus according to claim 1 or 2, wherein the list of energy-related performance indicators further comprises at least one of the following: Data processing energy consumption performance indicator, Data processing speed performance indicator, or Metadata related to the data processing entity.

4. The first device according to any one of claims 2 to 3, wherein the energy consumption requirement comprises at least one of the following: system information different from the system information in the first information, Data processing performance metrics, Data processing speed, Energy saving strategies, or The delay in receiving feedback of the update.

5. The first device of any one of claims 2 to 4, wherein the instructions, when executed by the at least one processor, further cause the first device to at least: receiving, from a second device, the first request for updating the first information; as well as transmitting feedback to the second device regarding feasibility of updating the first information based on the energy consumption requirement; or The instructions, when executed by the at least one processor, further cause the first device to at least: receiving, from a third device that receives the first request from the second device, the first request for updating the first information; as well as Feedback regarding feasibility of updating the first information based on the energy consumption requirement is transmitted to the third device.

6. The first device of any one of claims 1 to 5, wherein the instructions, when executed by the at least one processor, further cause the first device to at least: receiving, from the second device, a second request for a set of data processing entities and corresponding first information for the set of data processing entities; and Second information is transmitted to the second device, where the second information includes the group of data processing entities and the corresponding first information. The first apparatus of claim 6 , wherein the set of data processing entities meets performance indicator requirements.

8. The first device of any one of claims 1 to 7, wherein the instructions, when executed by the at least one processor, further cause the first device to at least: Transmitting fourth information to the second device, where the fourth information includes at least one of the following: updated first information for the data processing entity that has been updated based on the energy consumption requirement, or The first information for the further data processing entity comprises at least a further identification of the further data processing entity and a further list of energy-related performance indicators for the further data processing entity.

9. The first device of any one of claims 1 to 5, wherein the instructions, when executed by the at least one processor, further cause the first device to at least: A third request for registering the first information with the third device is transmitted to the third device, the third request including the first information.

10. The first device of any one of claims 1 to 9, wherein the instructions, when executed by the at least one processor, further cause the first device to at least: A fourth request including the updated first information is transmitted to the third device.

11. The first device of any one of claims 1 to 10, wherein the instructions, when executed by the at least one processor, further cause the first device to at least: The updated first information is stored.

12. The first device of any one of claims 1 to 10, wherein the instructions, when executed by the at least one processor, further cause the first device to at least: receiving, from the second device or the third device, a fifth request for one of: training, testing, or inference of the data processing entity based on the energy consumption requirement; and A report including the requested energy consumption information of one of: the training, the testing, or the inference of the data processing entity is transmitted to the second device or the third device.

13. The first device according to claim 12, wherein the energy consumption requirement comprises at least one of the following: Energy-saving strategies, the expected time for processing, or Expected energy.

14. The first device according to any one of claims 1 to 13, wherein the first device comprises one of the following: an artificial intelligence machine learning (AI / ML) management service training producer, an AI / ML management service test producer, an AI / ML management service inference producer, a network data analysis function model training logic function, a network data analysis function analysis logic function, a management data analysis function, a cross-domain management data analysis function, a network device, or a terminal device; and wherein the second device comprises one of the following: an AI / ML management service training consumer, an AI / ML management service testing consumer, an AI / ML management service inference consumer, a network data analysis function model training logic function, a network data analysis function analysis logic function, a management data analysis function, a cross-domain management data analysis function, a network device, or a terminal device; and The third device includes one of the following: analysis data repository function or AI / ML model repository function.

15. A second device comprising: at least one processor; as well as at least one memory storing instructions that, when executed by the at least one processor, cause the second device to: transmitting a request for a data processing entity and first information for the data processing entity to a first device, the first information comprising at least an identification of the data processing entity and a list of energy-related performance indicators for the data processing entity, wherein the list of energy-related performance indicators comprises at least data processing entity performance; as well as Second information including the data processing entity and the first information is received from the first device.

16. The second device of claim 15, wherein the instructions, when executed by the at least one processor, further cause the first device to at least: transmitting a first request for updating the first information to the first device, the first request including an energy consumption requirement; and Feedback is received from the first device regarding a feasibility of updating the first information based on the energy consumption requirement.

17. The second apparatus according to claim 15 or 16, wherein the list of energy-related performance indicators further comprises at least one of the following: Data processing energy consumption performance indicator, Data processing speed performance indicator, or Metadata related to the data processing entity.

18. The second device according to any one of claims 16 to 17, wherein the energy consumption requirement comprises at least one of the following: system information different from the system information in the first information, Data processing performance metrics, Data processing speed, Energy-saving strategies, or The delay in receiving feedback of the update.

19. The second device according to any one of claims 15 to 18, wherein the instructions, when executed by the at least one processor, further cause the second device to at least: transmitting, to the first device, a second request for a group of data processing entities and corresponding first information for the group of data processing entities; and Third information is received from the first device, the third information including the set of data processing entities and the corresponding first information.

20. The second apparatus of claim 19, wherein the set of data processing entities meets performance indicator requirements.

21. The second device of any one of claims 15 to 20, wherein the instructions, when executed by the at least one processor, further cause the first device to at least: Receive fourth information from the first device, wherein the fourth information includes at least one of the following: updated first information for the data processing entity that has been updated based on the energy consumption requirement, or The first information for the further data processing entity comprises at least another identification of the further data processing entity and another list of another energy-related performance indicators for the data processing entity.

22. The second device according to any one of claims 15 to 21, wherein the instructions, when executed by the at least one processor, further cause the second device to at least: transmitting to the first device a fifth request for one of: training, testing, or inference of the data processing entity based on the energy consumption requirement; and A report is received from the first device including actual energy consumption information of the requested one of: the training, the testing, or the inference of the data processing entity.

23. The first device of claim 22, wherein the second device comprises one of: an AI / ML management service training consumer, an AI / ML management service testing consumer, an AI / ML management service inference consumer, a network data analysis function model training logic function, a network data analysis function analysis logic function, a management data analysis function, a cross-domain management data analysis function, a network device, or a terminal device; and wherein the first device includes one of the following: an artificial intelligence machine learning (AI / ML) management service training producer, an AI / ML management service test producer, an AI / ML management service reasoning function, a network data analysis function model training logic function, a network data analysis function analysis logic function, a management data analysis function, a cross-domain management data analysis function, a network device, or a terminal device; or The first device includes one of the following: analysis data repository function or AI / ML model repository function.

24. A third device comprising: at least one processor; as well as at least one memory storing instructions that, when executed by the at least one processor, cause the third device to: receiving first information for a data processing entity from a first device, the first information comprising at least: an identification of the data processing entity and a list of energy-related performance indicators for the data processing entity, wherein the list of energy-related performance indicators comprises at least data processing entity performance; receiving a request for the data processing entity and the first information for the data processing entity from a second device; and Second information including the data processing entity and the first information is transmitted to the second device.

25. The third apparatus of claim 24, wherein the instructions, when executed by the at least one processor, further cause the third apparatus to at least: receiving a first request for updating the first information from the second device, the first request including an energy consumption requirement; transmitting the first request to the first device; receiving feedback from the first device regarding feasibility of updating the first information based on the energy consumption requirement; as well as The feedback is transmitted to the second device.

26. The third apparatus according to claim 24 or 25, wherein the list of energy-related performance indicators further comprises at least one of the following: Data processing energy consumption performance indicator, Data processing speed performance indicator, or Metadata related to the data processing entity.

27. The third device according to any one of claims 24 to 26, wherein the energy consumption requirement comprises at least one of the following: system information different from the system information in the first information, Data processing performance metrics, Data processing speed, Energy saving strategies, or The delay in receiving feedback of the update.

28. The third apparatus according to any one of claims 24 to 26, wherein the instructions, when executed by the at least one processor, further cause the third apparatus to at least: receiving, from a second first device, a second request for a set of data processing entities and corresponding information for the set of data processing entities; and Transmitting third information to the second device, the third information including the group of data processing entities and the corresponding first information.

29. The third apparatus of claim 28, wherein the set of data processing entities meets performance indicator requirements.

30. The third apparatus according to any one of claims 24 to 29, wherein the instructions, when executed by the at least one processor, further cause the third apparatus to at least: A third request for registering the first information with the third device is received from the first device, the third request including the first information.

31. The third apparatus according to any one of claims 24 to 30, wherein the instructions, when executed by the at least one processor, further cause the third apparatus to at least: A fourth request including the updated first information is received from the first device.

32. The third device according to any one of claims 24 to 31, wherein the first device comprises one of the following: an artificial intelligence machine learning (AI / ML) management service training producer, an AI / ML management service test producer, an AI / ML management service inference producer, a network data analysis function model training logic function, a network data analysis function analysis logic function, a management data analysis function, a cross-domain management data analysis function, a network device, or a terminal device; and wherein the second device comprises one of the following: an AI / ML management service training consumer, an AI / ML management service testing consumer, an AI / ML management service inference consumer, a network data analysis function model training logic function, a network data analysis function analysis logic function, a management data analysis function, a cross-domain management data analysis function, a network device, or a terminal device; and The third device includes one of the following: analysis data repository function or AI / ML model repository function.

33. A method comprising: At a first device, first information for a data processing entity is determined, the first information comprising at least an identification of the data processing entity and a list of energy-related performance indicators for the data processing entity, wherein the list of energy-related performance indicators comprises at least data processing entity performance; and The first information is transmitted to a second device or a third device.

34. A method comprising: At the second device, transmitting a request for a data processing entity and first information for the data processing entity to the first device, the first information comprising at least an identification of the data processing entity and a list of energy-related performance indicators for the data processing entity, wherein the list of energy-related performance indicators comprises at least data processing entity performance; and Second information including the data processing entity and the first information is received from the first device.

35. A method comprising: receiving, at a third device, first information for a data processing entity from the first device, the first information comprising at least: an identification of the data processing entity and a list of energy-related performance indicators for the data processing entity, wherein the list of energy-related performance indicators comprises at least data processing entity performance; receiving a request for the data processing entity and the first information for the data processing entity from a second device; and Second information including the data processing entity and the first information is transmitted to the second device.

36. A first device comprising: means for determining first information for a data processing entity, said first information comprising at least an identification of said data processing entity and a list of energy-related performance indicators for said data processing entity, said list of energy-related performance indicators comprising at least data processing entity performance; and A component for transmitting the first information to a second device or a third device.

37. A second device comprising: means for transmitting a request for a data processing entity and first information for said data processing entity to a first device, said first information comprising at least an identification of said data processing entity and a list of energy-related performance indicators for said data processing entity, said list of energy-related performance indicators comprising at least data processing entity performance; and Means for receiving, from said first device, second information comprising said data processing entity and said first information.

38. A third device comprising: means for receiving, at a third device, first information for a data processing entity from a first device, said first information comprising at least: an identification of said data processing entity and a list of energy-related performance indicators for said data processing entity, said list of energy-related performance indicators comprising at least data processing entity performance; means for receiving a request for said data processing entity and said first information for said data processing entity from a second device; and means for transmitting second information comprising said data processing entity and said first information to said second device.

Images