Multi-level quantitative measurement and evaluation method and device for energy consumption of digital intelligent base station

Abstract

This application relates to a multi-level quantitative measurement and evaluation method and apparatus for the energy consumption of intelligent data base stations. The method includes: determining typical tasks corresponding to each intelligent data base station; acquiring test datasets corresponding to the typical tasks and executing the typical tasks to obtain the corresponding running time, total energy consumption, real-time power, and time-period energy consumption; determining an energy consumption evaluation strategy for the typical tasks, calculating the average power corresponding to the typical tasks based on the energy consumption evaluation strategy, running time, real-time power, time-period energy consumption, and total energy consumption, constructing an energy consumption measurement index value group based on the average power, running time, and corresponding energy consumption, and using the average power and energy consumption measurement index value group to perform multi-level quantitative measurement and evaluation of the operating energy consumption of each intelligent data base station. This solves the current problems of lacking energy consumption measurement methods for intelligent data base stations and being unable to evaluate the performance of numerous intelligent data applications in terms of green, environmental protection, and energy conservation.

Description

Technical Field

[0001] This application relates to the fields of intelligent devices and energy management technology, and in particular to a multi-level quantitative measurement and evaluation method and device for energy consumption of a digital intelligent base station. Background Technology

[0002] With the advent of the intelligent era, digital intelligence infrastructure applications, represented by AI big data models and high-performance database systems, have developed rapidly and are gradually penetrating into all walks of life, becoming an important driving force for digital transformation.

[0003] However, the application of these digital infrastructures, especially large-scale modeling technologies, requires a large amount of electricity to maintain operation, which not only exacerbates the pressure on energy supply but also leads to increased carbon emissions, posing challenges to environmental protection and sustainable development, and urgently needs to be addressed. Summary of the Invention

[0004] This application provides a multi-level quantitative measurement and evaluation method and device for the energy consumption of digital intelligent base stations, in order to solve the problems of the current lack of energy consumption measurement methods for digital intelligent base stations, and the inability to evaluate the performance of a large number of digital intelligent applications in terms of green, environmental protection and energy saving.

[0005] The first aspect of this application provides a multi-level quantitative measurement and evaluation method for the energy consumption of a smart data base, comprising the following steps: determining a target smart data base typical task corresponding to each of at least one preset smart data bases; obtaining a test dataset corresponding to the target smart data base typical task; executing the target smart data base typical task based on the test dataset to obtain the running time, total energy consumption, real-time power, and time-period energy consumption corresponding to the target smart data base typical task; determining a target energy consumption evaluation strategy corresponding to the target smart data base typical task; calculating the average power corresponding to the target smart data base typical task based on the target energy consumption evaluation strategy, the running time, the real-time power, the time-period energy consumption, and the total energy consumption; constructing an energy consumption measurement index value group based on the average power, the running time, and the total energy consumption; and obtaining a multi-level quantitative measurement and evaluation result of the operating energy consumption of each preset smart data base using the average power and the energy consumption measurement index value group.

[0006] Optionally, in one embodiment of this application, determining the target digital intelligence base typical task corresponding to each preset digital intelligence base in at least one preset digital intelligence base includes: identifying the digital intelligence base type corresponding to each preset digital intelligence base; selecting the target digital intelligence base typical task corresponding to each preset digital intelligence base according to the digital intelligence base type, wherein the at least one preset digital intelligence base includes at least one of the target AI big data model, target database, target big data management software and computing platform IT infrastructure.

[0007] Optionally, in one embodiment of this application, the step of obtaining the test dataset corresponding to the typical task of the target intelligent infrastructure, and executing the typical task of the target intelligent infrastructure based on the test dataset to obtain the running time, total energy consumption, real-time power, and time-period energy consumption of the preset intelligent infrastructure corresponding to the typical task of the target intelligent infrastructure includes: obtaining the test dataset of the preset intelligent infrastructure executing the typical task of the target intelligent infrastructure based on the typical task of the target intelligent infrastructure, wherein the typical task of the target intelligent infrastructure includes any one of the preset large model typical task, the preset big data processing typical task, and the preset large model-big data hybrid task; executing the typical task of the target intelligent infrastructure according to the test dataset to generate the running time, total energy consumption, real-time power, and time-period energy consumption of the preset intelligent infrastructure executing the typical task of the target intelligent infrastructure.

[0008] Optionally, in one embodiment of this application, determining the target energy consumption assessment strategy corresponding to the typical task of the target intelligent base station, and calculating the average power corresponding to the typical task of the target intelligent base station based on the target energy consumption assessment strategy, the running time, the real-time power, the time-segmented energy consumption, and the total energy consumption, constructing an energy consumption metric value group based on the average power, the running time, and the total energy consumption, and obtaining a multi-level quantitative measurement and assessment result of the running energy consumption of each preset intelligent base station using the average power and the energy consumption metric value group, includes: when the target energy consumption assessment strategy is an assessment strategy based on total energy consumption, determining the first actual running time corresponding to the assessment strategy based on total energy consumption based on the running time, determining the first actual total energy consumption of the preset intelligent base station based on the total energy consumption, and calculating the ratio of the first actual total energy consumption to the first actual running time. The average power of a preset smart base station executing the typical task of the target smart base station is obtained. When the target energy consumption assessment strategy is an idle energy consumption assessment strategy, the start execution time of the typical task of the target smart base station corresponding to the idle energy consumption assessment strategy is determined according to the running time, and the return idle time of the preset smart base station is calculated according to the start execution time and the return idle time. The idle energy consumption in the total energy consumption is removed to obtain the second actual total energy consumption of the preset smart base station. The ratio of the second actual total energy consumption to the second actual running time is calculated to obtain the average power of the preset smart base station executing the typical task of the target smart base station. The operating energy consumption of each preset smart base station is evaluated by first-level quantitative measurement using the average power corresponding to the idle energy consumption assessment strategy or the assessment strategy based on total energy consumption.

[0009] Optionally, in one embodiment of this application, the step of constructing an energy consumption metric value group based on the average power, the operating time, and the total energy consumption, and obtaining a multi-level quantitative measurement and evaluation result of the operating energy consumption of each preset smart base station using the average power and the energy consumption metric value group, further includes: constructing an energy consumption metric value group corresponding to a typical task of each target smart base station based on the average power, the operating time, and the total energy consumption, and constructing an index vector space based on the energy consumption metric value groups of all typical tasks of the target smart base stations; and performing a second-level quantitative measurement and evaluation of the operating energy consumption of each preset smart base station through the index vector space.

[0010] A second aspect of this application provides a multi-level quantitative measurement and evaluation device for the energy consumption of a smart base station, comprising: a determination module, configured to determine a target smart base station typical task corresponding to each of at least one preset smart base station; an execution module, configured to acquire a test dataset corresponding to the target smart base station typical task, and execute the target smart base station typical task based on the test dataset to obtain the running time, total energy consumption, real-time power, and time-period energy consumption of the preset smart base station corresponding to the target smart base station typical task; and an evaluation module, configured to determine a target energy consumption evaluation strategy corresponding to the target smart base station typical task, calculate the average power corresponding to the target smart base station typical task based on the target energy consumption evaluation strategy, the running time, the real-time power, the time-period energy consumption, and the total energy consumption, construct an energy consumption measurement index value group based on the average power, the running time, and the total energy consumption, and obtain a multi-level quantitative measurement and evaluation result of the running energy consumption of each preset smart base station using the average power and the energy consumption measurement index value group.

[0011] Optionally, in one embodiment of this application, the determining module includes: a type analysis unit, used to identify the type of digital intelligence base corresponding to each preset digital intelligence base; and a selection unit, used to select a typical task of a target digital intelligence base corresponding to each preset digital intelligence base according to the type of digital intelligence base, wherein the at least one preset digital intelligence base includes at least one of a target AI big model, a target database, a target big data management software and computing platform IT infrastructure.

[0012] Optionally, in one embodiment of this application, the execution module includes: an acquisition unit, configured to acquire a test dataset of a preset digital intelligence base executing the target digital intelligence base typical task based on the target digital intelligence base typical task, wherein the target digital intelligence base typical task includes any one of a preset large model typical task, a preset big data processing typical task, and a preset large model-big data hybrid task; and a generation unit, configured to execute the target digital intelligence base typical task according to the test dataset to generate the running time, total energy consumption, real-time power, and time-period energy consumption of the preset digital intelligence base executing the target digital intelligence base typical task.

[0013] Optionally, in one embodiment of this application, the evaluation module includes: a total energy consumption evaluation unit, configured to, when the target energy consumption evaluation strategy is a total energy consumption-based evaluation strategy, determine the first actual running time corresponding to the total energy consumption-based evaluation strategy based on the running time, and determine the first actual total energy consumption of the preset digital intelligent base based on the total energy consumption, and calculate the ratio of the first actual total energy consumption to the first actual running time to obtain the average power of the preset digital intelligent base performing the typical task of the target digital intelligent base; and an idle energy consumption exclusion evaluation unit, configured to, when the target energy consumption evaluation strategy is an idle energy consumption exclusion evaluation strategy, determine the target energy consumption of the preset digital intelligent base corresponding to the idle energy consumption exclusion evaluation strategy based on the running time. The system calculates the start execution time of a typical task on the smart base station and the return idle time of the preset smart base station. It then calculates the second actual running time corresponding to the typical task on the target smart base station based on the start execution time and the return idle time, and removes the idle energy consumption from the total energy consumption to obtain the second actual total energy consumption of the preset smart base station. Finally, it calculates the ratio of the second actual total energy consumption to the second actual running time to obtain the average power of the preset smart base station executing the typical task on the target smart base station. A first-level evaluation unit is used to perform a first-level quantitative measurement and evaluation of the operating energy consumption of each preset smart base station using the average power corresponding to the evaluation strategy excluding idle energy consumption or the evaluation strategy based on total energy consumption.

[0014] Optionally, in one embodiment of this application, the evaluation module further includes: a vector space construction unit, used to construct a set of energy consumption measurement index values ​​corresponding to the typical tasks of each target smart base based on the average power, the running time and the total energy consumption, and to construct an index vector space based on the energy consumption measurement index value sets of all target smart base typical tasks; and a secondary evaluation unit, used to perform secondary quantitative measurement and evaluation of the operating energy consumption of each preset smart base through the index vector space.

[0015] A third aspect of this application provides an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor. The processor executes the program to implement the multi-level quantitative measurement and evaluation method for the energy consumption of a digital intelligent base station as described in the above embodiments.

[0016] A fourth aspect of this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described multi-level quantitative measurement and evaluation method for the energy consumption of a smart infrastructure.

[0017] A fifth aspect of this application provides a computer program product, including a computer program that is executed to implement the above-described multi-level quantitative measurement and evaluation method for the energy consumption of a digital intelligent base station.

[0018] Therefore, the embodiments of this application have the following beneficial effects:

[0019] The embodiments of this application can determine a typical task for each of the at least one preset smart base stations; obtain a test dataset corresponding to the typical task; execute the typical task based on the test dataset to obtain the running time, total energy consumption, real-time power, and time-period energy consumption corresponding to the typical task; determine a target energy consumption evaluation strategy for the typical task; calculate the average power corresponding to the typical task based on the target energy consumption evaluation strategy, running time, real-time power, time-period energy consumption, and total energy consumption; construct an energy consumption measurement index value group based on the average power, running time, and total energy consumption; and obtain a multi-level quantitative measurement and evaluation result of the operating energy consumption of each preset smart base station using the average power and the energy consumption measurement index value group. This application selects appropriate typical tasks for testing according to different smart base station types, quantitatively analyzes the energy consumption data of the smart base station in operation, and selects an appropriate evaluation method for evaluation, providing a feasible way for energy consumption evaluation of smart base stations, thereby making it possible to reduce the energy consumption of smart base station resources and improve operating efficiency. This solves the current problems of lacking energy consumption measurement methods for digital intelligence base stations and being unable to evaluate the performance of a large number of digital intelligence applications in terms of green, environmental protection and energy conservation.

[0020] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through practice of the present application. Attached Figure Description

[0021] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0022] Figure 1This is a flowchart of a multi-level quantitative measurement and evaluation method for the energy consumption of a digital intelligent base station according to an embodiment of this application;

[0023] Figure 2 A schematic diagram of the logical architecture of a multi-level quantitative measurement and evaluation method for energy consumption of a digital intelligent base station provided in one embodiment of this application;

[0024] Figure 3 A schematic diagram illustrating the power variation over time of a digital intelligent base device, provided as an embodiment of this application;

[0025] Figure 4 A schematic diagram of the average power calculation strategy for a large-scale model energy consumption assessment scheme provided in one embodiment of this application;

[0026] Figure 5 This is an example diagram of a multi-level quantitative measurement and evaluation device for the energy consumption of a digital intelligent base station according to an embodiment of this application;

[0027] Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application.

[0028] Among them, 10 is a multi-level quantitative measurement and evaluation device for the energy consumption of the digital intelligent base; 100 is a determination module, 200 is an execution module, and 300 is an evaluation module; 601 is a memory, 602 is a processor, and 603 is a communication interface. Detailed Implementation

[0029] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0030] The following describes a multi-level quantitative measurement and evaluation method and apparatus for the energy consumption of smart base stations according to embodiments of this application, with reference to the accompanying drawings. Addressing the problems mentioned in the background art, this application provides a multi-level quantitative measurement and evaluation method for the energy consumption of smart base stations. In this method, a target smart base station typical task is determined for each of at least one preset smart base station; a test dataset corresponding to the target smart base station typical task is obtained; based on the test dataset, the target smart base station typical task is executed to obtain the running time, total energy consumption, real-time power, and time-period energy consumption corresponding to the target smart base station typical task; a target energy consumption evaluation strategy is determined for the target smart base station typical task; based on the target energy consumption evaluation strategy, running time, real-time power, time-period energy consumption, and total energy consumption, the average power corresponding to the target smart base station typical task is calculated; and an energy consumption measurement index value group is constructed based on the average power, running time, and total energy consumption; and the multi-level quantitative measurement and evaluation result of the operating energy consumption of each preset smart base station is obtained using the average power and the energy consumption measurement index value group. This application selects appropriate typical tasks for testing based on different types of intelligent data bases, quantifies and analyzes the energy consumption data of the intelligent data bases in operation, and selects a suitable evaluation method for assessment. This provides a feasible approach to energy consumption assessment of intelligent data bases, thereby offering possibilities for reducing resource energy consumption and improving operational efficiency. Thus, it solves the current problems of lacking energy consumption measurement methods for intelligent data bases and being unable to evaluate the performance of numerous intelligent data applications in terms of green, environmental protection, and energy conservation.

[0031] Specifically, Figure 1 A flowchart illustrating a multi-level quantitative measurement and evaluation method for the energy consumption of a digital intelligent base station, provided as an embodiment of this application.

[0032] like Figure 1 As shown, the multi-level quantitative measurement and evaluation method for the energy consumption of this intelligent infrastructure includes the following steps:

[0033] In step S101, the target digital intelligent base typical task corresponding to each preset digital intelligent base in at least one preset digital intelligent base is determined.

[0034] The embodiments of this application can first select appropriate typical tasks for each preset smart base station, thereby providing technical and data support for the realization of multi-level quantitative measurement and evaluation of smart base station energy consumption.

[0035] Optionally, in one embodiment of this application, determining the target digital intelligence base typical task corresponding to each preset digital intelligence base in at least one preset digital intelligence base includes: identifying the digital intelligence base type corresponding to each preset digital intelligence base; selecting the target digital intelligence base typical task corresponding to each preset digital intelligence base according to the digital intelligence base type, wherein at least one preset digital intelligence base includes at least one of the target AI big model, target database, target big data management software and computing platform IT infrastructure.

[0036] In actual implementation, such as Figure 2 As shown, the digital infrastructure in the embodiments of this application mainly includes IT infrastructure such as AI big data models, databases, big data management related software, and computing platforms.

[0037] It should be noted that the aforementioned large AI model refers to a deep learning model with extremely large parameters and computing power. It can be widely used in fields such as natural language processing, and is capable of handling complex tasks and has the ability to understand and generate data.

[0038] The embodiments of this application can determine the type of digital base station corresponding to each digital base station, so as to select and execute appropriate typical tasks according to different digital base station types, and provide corresponding parameter data for subsequent energy consumption assessment and analysis.

[0039] In step S102, a test dataset corresponding to the typical task of the target smart base is obtained. Based on the test dataset, the typical task of the target smart base is executed to obtain the running time, total energy consumption, real-time power and time-period energy consumption of the preset smart base corresponding to the typical task of the target smart base.

[0040] Furthermore, embodiments of this application also provide the corresponding digital infrastructure facility with the dataset required for testing through typical tasks of the target digital infrastructure, and use the dataset required for testing as input to enable the digital infrastructure facility to generate parameter data that can be used for energy consumption analysis.

[0041] Optionally, in one embodiment of this application, a test dataset corresponding to a typical task of the target smart base is obtained, and based on the test dataset, a typical task of the target smart base is executed to obtain energy consumption data of a preset smart base corresponding to the typical task of the target smart base. This includes: obtaining a test dataset of a preset smart base executing the typical task of the target smart base, wherein the typical task of the target smart base includes any one of a preset large model typical task, a preset big data processing typical task, and a preset large model-big data hybrid task; and executing the typical task of the target smart base according to the test dataset to generate the running time, total energy consumption, real-time power, and time-period energy consumption of the preset smart base executing the typical task of the target smart base.

[0042] It should be noted that the typical tasks of the digital intelligence infrastructure in this application embodiment include typical tasks of large models, typical tasks of big data processing, and tasks that combine the two.

[0043] The typical tasks for large models include datasets related to the functions of large models, such as the Alpaca dataset and the GSM8K dataset. The Alpaca dataset contains text data in multiple languages, which can be used for a series of natural language processing tasks, such as sentiment analysis and text classification. The GSM8K dataset contains thousands of mathematical problems to test the model's logical reasoning and problem-solving abilities. By using the above datasets together, we can evaluate the model's performance in various tasks and assess how different types of data affect energy consumption and inference performance.

[0044] Typical big data processing tasks include those that simulate complex business-related query operations in databases and other big data-related software to test the performance of these databases and software. Examples include benchmark tasks like TPC-H, TPC-IoT, and TPC-AI. TPC-H simulates complex queries and large-scale data processing scenarios, consisting of a set of ad-hoc business-oriented queries and concurrent data modifications. It tests database performance using metrics such as QphH@Size (queries per hour), $ / kQphH@Size (cost per thousand queries), and system availability dates through multiple predefined complex SQL operations. TPC-IoT is a benchmark specifically designed to measure the performance of IoT gateway systems, primarily using metrics such as IoTps (IoT transactions per second), $ / kIoTps (cost per thousand IoT transactions), and system availability dates. TPCx-AI is a benchmark for evaluating the performance of artificial intelligence and machine learning applications, primarily using metrics such as AIUCpm (AI user queries per minute), $ / AIUCpm (cost per AI user query), and system availability dates.

[0045] Subsequently, embodiments of this application can obtain a test dataset of the digital intelligent base performing typical tasks, and execute the target digital intelligent base's typical tasks based on the test dataset, thereby generating multiple energy consumption data such as the running time, total energy consumption, real-time power, and segmented energy consumption at different time periods of the corresponding preset digital intelligent base.

[0046] In step S103, a target energy consumption assessment strategy corresponding to the typical tasks of the target smart base is determined. Based on the target energy consumption assessment strategy, running time, real-time power, time-segmented energy consumption and total energy consumption, the average power corresponding to the typical tasks of the target smart base is calculated. An energy consumption measurement index value group is constructed according to the average power, running time and total energy consumption. The multi-level quantitative measurement and assessment results of the operating energy consumption of each preset smart base are obtained by using the average power and the energy consumption measurement index value group.

[0047] Furthermore, as one possible approach, the embodiments of this application include an energy consumption assessment strategy for big data and databases, which includes multiple indicators capable of evaluating the energy consumption of big data and database-related software. This strategy can utilize a series of indicators to assess the energy consumption of big data and database-related software. These indicators include TPC-Energy assessment metrics, such as power consumption per unit performance throughput and idle power, and use these as the average power corresponding to each digital infrastructure.

[0048] Those skilled in the art should understand that, due to the different optimization strategies of different digital intelligence platforms, there may be situations where the average power is similar but the completion speed is different, resulting in differences in total power consumption. In order to more completely and comprehensively describe and measure the energy consumption of digital intelligence base stations, the embodiments of this application also need to introduce a multi-level quantitative measurement and evaluation strategy (such as a two-level quantitative measurement and evaluation) to evaluate the operating energy consumption of each digital intelligence base station.

[0049] Optionally, in one embodiment of this application, a target energy consumption assessment strategy corresponding to a typical task of the target intelligent base station is determined. Based on the target energy consumption assessment strategy, running time, real-time power, time-segmented energy consumption, and total energy consumption, the average power corresponding to the typical task of the target intelligent base station is calculated. An energy consumption measurement index value group is constructed based on the average power, running time, and total energy consumption. The average power and energy consumption measurement index value group are used to obtain a multi-level quantitative measurement and assessment result of the operating energy consumption of each preset intelligent base station. This includes: when the target energy consumption assessment strategy is an assessment strategy based on total energy consumption, determining the first actual running time corresponding to the assessment strategy based on total energy consumption based on the running time, and determining the first actual total energy consumption of the preset intelligent base station based on the total energy consumption, and calculating the ratio of the first actual total energy consumption to the first actual running time to obtain the execution... The average power of the preset smart base for typical tasks of the target smart base; when the target energy consumption assessment strategy is to exclude idle energy consumption assessment strategy, the start execution time of the target smart base typical task corresponding to the idle energy consumption assessment strategy is determined according to the running time, and the return idle time of the preset smart base is calculated according to the start execution time and return idle time. The second actual running time corresponding to the target smart base typical task is calculated, and the idle energy consumption in the total energy consumption is removed to obtain the second actual total energy consumption of the preset smart base. The ratio of the second actual total energy consumption and the second actual running time is calculated to obtain the average power of the preset smart base for executing the target smart base typical task; the running energy consumption of each preset smart base is evaluated by first-level quantitative measurement using the average power corresponding to the idle energy consumption assessment strategy or the assessment strategy based on all energy consumption.

[0050] It should be noted that the embodiments of this application can divide the energy consumption assessment strategy into two parts according to different tasks: an energy consumption assessment strategy for large AI models and an energy consumption assessment strategy for big data and databases. Among them, the large model energy consumption assessment scheme (i.e., energy consumption assessment strategy) for large AI models mainly includes an assessment method that considers all energy consumption (i.e., an assessment strategy based on all energy consumption) and an assessment method that excludes idle time consumption when there is no task (i.e., an assessment strategy excluding idle time consumption), so as to accurately assess the energy consumption of large models.

[0051] Figure 3 This is a schematic diagram illustrating the power variation of the digital intelligence base device over time. (Example:) Figure 3 As shown, the orange curve represents the power function curve P(t) as a function of time, and the green dashed line represents the idling power P0 when there is no task. Figure 3 The CCP inputs two tasks. Task 1 begins execution at time t1, and the power increases. It reaches a stable power P1 at time t2 and is maintained for a period of time before the task ends. The power returns to P0 at time t3. Task 2 begins execution at time t4, and the power reaches a stable power P2 at time t5. The task is completed, and the power returns to the idle power P0 at time t6.

[0052] In the specific implementation process, when the target energy consumption assessment strategy is an assessment strategy based on total energy consumption, the average power of a specific digital intelligent base station is calculated as the ratio of the total energy consumption of the task execution (i.e., the first actual total energy consumption) to the total running time (i.e., the first actual running time) in this embodiment of the application. The total running time is the time from the start of task execution to the end of task execution. Figure 3 The total energy consumption during the time period from t1 to t6 (i.e., the first actual running time) is... Figure 3 The integral of the real-time power P(t) over the time interval t1 to t6 (i.e., the first actual total energy consumption); such as Figure 4 As shown, the average power calculation expression corresponding to this evaluation strategy based on total energy consumption is as follows:

[0053]

[0054] When the target energy consumption assessment strategy is to exclude idle energy consumption assessment, the embodiments of this application can take the energy consumption of executing the task minus the idling energy consumption as the total energy consumption (i.e., the second actual total energy consumption), and calculate the ratio of this total energy consumption (i.e., the second actual total energy consumption) to the running time (i.e., the second actual running time) to obtain the corresponding average power; wherein, the running time (i.e., the second actual running time) can be the running time of a single task from start to finish (i.e., returning to idling) or the running time of a batch of tasks from start to finish (i.e., returning to idling). If only a single task is calculated, Figure 3 Taking Task 1 as an example, its running time is from t1 to t3 (i.e., the second actual running time). The total energy consumption is the integral of P(t) during the period from t1 to t3 (i.e., the second actual total energy consumption). The idling power is constant, and the idling energy consumption during this period is P0*(t3-t1) (i.e., the second actual total energy consumption). If a batch of tasks is calculated, taking... Figure 3 Taking all tasks as an example, the running time (i.e., the second actual running time) is from t1 to t6, the total energy consumption is the integral of P(t) over the period from t1 to t6 (i.e., the second actual total energy consumption), and the idling energy consumption is P0*(t6-t1). Dividing these values ​​by the running time (i.e., the second actual running time) yields the corresponding average power. Figure 4 As shown, the average power calculation expression corresponding to this exclusion strategy for air consumption assessment is as follows:

[0055] or

[0056] Therefore, the embodiments of this application can obtain the corresponding average power through the above-mentioned different energy consumption assessment strategies, thereby performing a first-level quantitative assessment of the operating energy consumption of each preset smart base station.

[0057] Optionally, in one embodiment of this application, a target energy consumption assessment strategy corresponding to a typical task of a target smart base is determined, and an energy consumption assessment operation is performed using energy consumption data through the target energy consumption assessment strategy to obtain the average power corresponding to each preset smart base. The method further includes: constructing a set of energy consumption measurement index values ​​corresponding to a typical task of each target smart base based on the average power, running time and total energy consumption, and constructing an index vector space based on the energy consumption measurement index value sets of all typical tasks of the target smart base; and performing a secondary quantitative measurement and assessment of the operating energy consumption of each preset smart base through the index vector space.

[0058] As one possible approach, embodiments of this application may also combine the average power P, completion time t (i.e., running time), and total energy consumption W of each typical task of the target intelligent base station to construct a set of energy consumption metrics (P, t, W). m Given n typical tasks for intelligent infrastructure targets, a corresponding index vector space (P, t, W) can be constructed using n sets of energy consumption measurement index values. m Where m ranges from 1 to n, the energy consumption of each digital intelligent base is quantitatively evaluated using the index vector space and the energy consumption measurement index value group.

[0059] Therefore, the embodiments of this application introduce a two-level quantitative measurement and evaluation operation to more comprehensively and completely describe and measure the energy consumption of the digital intelligent base, thereby greatly improving the reliability of energy consumption assessment.

[0060] In summary, the embodiments of this application select appropriate typical tasks for testing based on different types of intelligent digital base stations, quantify and analyze the energy consumption data of the intelligent digital base stations in operation, and select an appropriate evaluation method for evaluation, thus providing a feasible way for energy consumption assessment of intelligent digital base stations, and making it possible to reduce the energy consumption of intelligent digital base station resources and improve operational efficiency.

[0061] According to the multi-level quantitative measurement and evaluation method for the energy consumption of smart base stations proposed in this application, the method involves: determining a typical task for each of the at least one preset smart base stations; obtaining a test dataset corresponding to the typical task; executing the typical task based on the test dataset to obtain the running time, total energy consumption, real-time power, and time-period energy consumption corresponding to the typical task; determining a target energy consumption evaluation strategy for the typical task; calculating the average power corresponding to the typical task based on the target energy consumption evaluation strategy, running time, real-time power, time-period energy consumption, and total energy consumption; constructing an energy consumption measurement index value group based on the average power, running time, and total energy consumption; and using the average power and the energy consumption measurement index value group to obtain the multi-level quantitative measurement and evaluation result of the operating energy consumption of each preset smart base station. This application selects appropriate typical tasks for testing based on different types of digital intelligence bases, quantifies and analyzes the energy consumption data of digital intelligence bases in operation, selects a suitable evaluation method for evaluation, and provides a feasible way for energy consumption assessment of digital intelligence bases, thereby providing the possibility for reducing the energy consumption of digital intelligence base resources and improving operational efficiency.

[0062] Secondly, with reference to the accompanying drawings, a multi-level quantitative measurement and evaluation device for the energy consumption of a digital intelligent base station proposed according to an embodiment of this application is described.

[0063] Figure 5 This is a block diagram of a multi-level quantitative measurement and evaluation device for the energy consumption of a digital intelligent base station according to an embodiment of this application.

[0064] like Figure 5 As shown, the multi-level quantitative measurement and evaluation device 10 for the energy consumption of the digital intelligent base includes: a determination module 100, an execution module 200, and an evaluation module 300.

[0065] The determining module 100 is used to determine the target digital intelligence base typical task corresponding to each preset digital intelligence base in at least one preset digital intelligence base.

[0066] The execution module 200 is used to obtain the test dataset corresponding to the typical tasks of the target smart base, and execute the typical tasks of the target smart base based on the test dataset to obtain the running time, total energy consumption, real-time power and time-period energy consumption of the preset smart base corresponding to the typical tasks of the target smart base.

[0067] The evaluation module 300 is used to determine the target energy consumption evaluation strategy corresponding to the typical tasks of the target smart base. Based on the target energy consumption evaluation strategy, running time, real-time power, time-segmented energy consumption and total energy consumption, it calculates the average power corresponding to the typical tasks of the target smart base. It also constructs a set of energy consumption measurement index values ​​based on the average power, running time and total energy consumption, and uses the average power and the set of energy consumption measurement index values ​​to obtain the multi-level quantitative measurement and evaluation results of the operating energy consumption of each preset smart base.

[0068] Optionally, in one embodiment of this application, the determining module 100 includes a type analysis unit and a selection unit.

[0069] The type analysis unit is used to identify the type of digital base corresponding to each preset digital base.

[0070] The selection unit is used to select the target digital intelligence base typical task corresponding to each preset digital intelligence base according to the type of digital intelligence base, wherein at least one preset digital intelligence base includes at least one of the target AI big model, target database, target big data management software and computing platform IT infrastructure.

[0071] Optionally, in one embodiment of this application, the execution module 200 includes an acquisition unit and a generation unit.

[0072] The acquisition unit is used to acquire a test dataset of a preset digital intelligence base that performs the typical tasks of the target digital intelligence base, based on the typical tasks of the target digital intelligence base. The typical tasks of the target digital intelligence base include any one of the following: a preset large model typical task, a preset big data processing typical task, and a preset large model-big data hybrid task.

[0073] The generation unit is used to execute typical tasks of the target smart base based on the test dataset to generate the running time, total energy consumption, real-time power and time-period energy consumption of the preset smart base for executing the typical tasks of the target smart base.

[0074] Optionally, in one embodiment of this application, the evaluation module 300 includes: a total energy consumption evaluation unit, an energy consumption exclusion evaluation unit, and a primary evaluation unit.

[0075] The total energy consumption assessment unit is used to determine the first actual running time corresponding to the total energy consumption assessment strategy when the target energy consumption assessment strategy is a total energy consumption assessment strategy, and to determine the first actual total energy consumption of the preset digital intelligent base based on the total energy consumption, and to calculate the ratio of the first actual total energy consumption to the first actual running time, so as to obtain the average power of the preset digital intelligent base for performing typical tasks of the target digital intelligent base.

[0076] The idle time assessment unit is used to determine the start execution time of the typical task of the target smart base corresponding to the idle time assessment strategy based on the running time, and the return idle time of the preset smart base when the target energy consumption assessment strategy is the idle time assessment strategy. It calculates the second actual running time corresponding to the typical task of the target smart base based on the start execution time and the return idle time, and removes the idle energy consumption in the total energy consumption to obtain the second actual total energy consumption of the preset smart base. It also calculates the ratio of the second actual total energy consumption and the second actual running time to obtain the average power of the preset smart base executing the typical task of the target smart base.

[0077] The first-level evaluation unit is used to perform a first-level quantitative measurement and evaluation of the operating energy consumption of each preset smart base by excluding the energy consumption evaluation strategy or the average power corresponding to the evaluation strategy based on all energy consumption.

[0078] Optionally, in one embodiment of this application, the evaluation module 300 further includes a vector space construction unit and a secondary evaluation unit.

[0079] The vector space construction unit is used to construct a set of energy consumption measurement index values ​​corresponding to the typical tasks of each target smart infrastructure based on average power, running time and total energy consumption, and to construct an index vector space based on the set of energy consumption measurement index values ​​of all typical tasks of the target smart infrastructure.

[0080] The secondary evaluation unit is used to perform secondary quantitative measurement and evaluation of the operating energy consumption of each preset digital intelligent base through the indicator vector space.

[0081] It should be noted that the explanation of the above-mentioned embodiment of the multi-level quantitative measurement and evaluation method for the energy consumption of the smart base also applies to the multi-level quantitative measurement and evaluation device for the energy consumption of the smart base in this embodiment, and will not be repeated here.

[0082] The multi-level quantitative measurement and evaluation device for the energy consumption of smart base stations proposed in this application includes a determination module for determining a target smart base station typical task corresponding to each of at least one preset smart base station; an execution module for acquiring a test dataset corresponding to the target smart base station typical task, and executing the target smart base station typical task based on the test dataset to obtain the running time, total energy consumption, real-time power, and time-period energy consumption of the preset smart base station corresponding to the target smart base station typical task; and an evaluation module for determining a target energy consumption evaluation strategy corresponding to the target smart base station typical task, calculating the average power corresponding to the target smart base station typical task based on the target energy consumption evaluation strategy, running time, real-time power, time-period energy consumption, and total energy consumption, constructing an energy consumption measurement index value group based on the average power, running time, and total energy consumption, and obtaining the multi-level quantitative measurement and evaluation result of the running energy consumption of each preset smart base station using the average power and the energy consumption measurement index value group. This application selects appropriate typical tasks for testing based on different types of digital intelligence bases, quantifies and analyzes the energy consumption data of digital intelligence bases in operation, selects a suitable evaluation method for evaluation, and provides a feasible way for energy consumption assessment of digital intelligence bases, thereby providing the possibility for reducing the energy consumption of digital intelligence base resources and improving operational efficiency.

[0083] Figure 6 A schematic diagram of the structure of an electronic device provided in an embodiment of this application. The electronic device may include:

[0084] The memory 601, the processor 602, and the computer program stored on the memory 601 and capable of running on the processor 602.

[0085] When the processor 602 executes the program, it implements the multi-level quantitative measurement and evaluation method for the energy consumption of the digital intelligent base provided in the above embodiments.

[0086] Furthermore, electronic devices also include:

[0087] Communication interface 603 is used for communication between memory 601 and processor 602.

[0088] The memory 601 is used to store computer programs that can run on the processor 602.

[0089] The memory 601 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.

[0090] If the memory 601, processor 602, and communication interface 603 are implemented independently, then the communication interface 603, memory 601, and processor 602 can be interconnected via a bus to complete communication between them. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of representation, Figure 6 Only one thick line is used in the diagram, but this does not mean that there is only one bus or one type of bus.

[0091] Optionally, in a specific implementation, if the memory 601, processor 602, and communication interface 603 are integrated on a single chip, then the memory 601, processor 602, and communication interface 603 can communicate with each other through an internal interface.

[0092] The processor 602 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application.

[0093] This application also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the above-described multi-level quantitative measurement and evaluation method for the energy consumption of the smart base station.

[0094] This application also provides a computer program product, including a computer program, which, when executed, is used to implement the above-described multi-level quantitative measurement and evaluation method for the energy consumption of the digital intelligent base station.

[0095] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0096] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be understood to indicate or imply relative importance or implicitly specify the number of technical features indicated. Thus, a feature specified as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of this application, "N" means at least two, for example, two, three, etc., unless otherwise specifically defined.

[0097] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or N executable instructions for implementing a custom logical function or process step, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may be performed in a different order than shown or discussed, including performing functions in a substantially simultaneous manner or in a reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present application pertain.

[0098] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0099] It should be understood that the various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. If implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0100] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0101] Furthermore, the functional units in the various embodiments of this application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0102] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of this application.

Claims

1. A multi-level quantitative measurement and evaluation method for the energy consumption of a digital intelligent base station, characterized in that, Includes the following steps: Determine the typical task of the target digital intelligence base corresponding to each preset digital intelligence base in at least one preset digital intelligence base; Obtain the test dataset corresponding to the typical task of the target smart base; based on the test dataset, execute the typical task of the target smart base to obtain the running time, total energy consumption, real-time power and time-period energy consumption of the typical task of the target smart base. A target energy consumption assessment strategy is determined for the typical tasks of the target smart base. Based on the target energy consumption assessment strategy, the running time, the real-time power, the time-segmented energy consumption, and the total energy consumption, the average power corresponding to the typical tasks of the target smart base is calculated. An energy consumption measurement index value group is constructed according to the average power, the running time, and the total energy consumption. The multi-level quantitative measurement and assessment results of the operating energy consumption of each preset smart base are obtained using the average power and the energy consumption measurement index value group. The process of determining the target energy consumption assessment strategy corresponding to the typical tasks of the target intelligent base station involves calculating the average power corresponding to the typical tasks of the target intelligent base station based on the target energy consumption assessment strategy, the running time, the real-time power, the time-segmented energy consumption, and the total energy consumption. It also involves constructing an energy consumption metric value group based on the average power, the running time, and the total energy consumption, and using the average power and the energy consumption metric value group to obtain a multi-level quantitative measurement and assessment result of the operating energy consumption of each preset intelligent base station, including: When the target energy consumption assessment strategy is an assessment strategy based on total energy consumption, the first actual running time corresponding to the assessment strategy based on total energy consumption is determined according to the running time, and the first actual total energy consumption of the preset digital intelligent base is determined according to the total energy consumption. The ratio of the first actual total energy consumption to the first actual running time is calculated to obtain the average power of the preset digital intelligent base performing the typical task of the target digital intelligent base. When the target energy consumption assessment strategy is an idling assessment strategy, the start execution time of the typical task of the target smart base corresponding to the idling assessment strategy is determined according to the running time, and the return idling time of the preset smart base is determined according to the start execution time and the return idling time. The second actual running time corresponding to the typical task of the target smart base is calculated according to the start execution time and the return idling time, and the idling energy consumption in the total energy consumption is removed to obtain the second actual total energy consumption of the preset smart base. The ratio of the second actual total energy consumption to the second actual running time is calculated to obtain the average power of the preset smart base executing the typical task of the target smart base. The operating energy consumption of each preset smart base station is quantitatively measured and evaluated using the average power corresponding to the exclusion of empty consumption evaluation strategy or the evaluation strategy based on total energy consumption. The step of constructing an energy consumption metric value group based on the average power, the operating time, and the total energy consumption, and obtaining a multi-level quantitative measurement and evaluation result of the operating energy consumption of each preset smart base station using the average power and the energy consumption metric value group, further includes: Based on the average power, the running time and the total energy consumption, construct a set of energy consumption measurement index values ​​corresponding to the typical tasks of each target smart base, and construct an index vector space based on the energy consumption measurement index value sets of all typical tasks of the target smart base. The energy consumption of each preset digital intelligent base station is evaluated using a secondary quantitative measurement through the indicator vector space.

2. The method according to claim 1, characterized in that, The step of determining the typical task of the target digital intelligence base corresponding to each preset digital intelligence base in at least one preset digital intelligence base includes: Identify the type of digital base station corresponding to each preset digital base station; Select the target digital intelligence base typical task corresponding to each preset digital intelligence base according to the digital intelligence base type, wherein the at least one preset digital intelligence base includes at least one of the target AI big model, target database, target big data management software and computing platform IT infrastructure.

3. The method according to claim 1, characterized in that, The step of obtaining the test dataset corresponding to the typical task of the target smart base, and executing the typical task of the target smart base based on the test dataset to obtain the running time, total energy consumption, real-time power, and time-of-day energy consumption of the preset smart base corresponding to the typical task of the target smart base, includes: Based on the typical tasks of the target digital intelligence infrastructure, a test dataset of a preset digital intelligence infrastructure for executing the typical tasks of the target digital intelligence infrastructure is obtained, wherein the typical tasks of the target digital intelligence infrastructure include any one of the preset large model typical tasks, the preset big data processing typical tasks, and the preset large model-big data hybrid tasks. The target smart base is executed according to the test dataset to generate the running time, total energy consumption, real-time power and time-period energy consumption of the preset smart base for executing the target smart base typical tasks.

4. A multi-level quantitative measurement and evaluation device for the energy consumption of a digital intelligent base station, characterized in that, include: The determination module is used to determine the target digital intelligence base typical task corresponding to each preset digital intelligence base in at least one preset digital intelligence base; The execution module is used to obtain the test dataset corresponding to the typical task of the target smart base, and execute the typical task of the target smart base based on the test dataset to obtain the running time, total energy consumption, real-time power and time-period energy consumption of the preset smart base corresponding to the typical task of the target smart base. The evaluation module is used to determine the target energy consumption evaluation strategy corresponding to the typical tasks of the target smart base, and to calculate the average power corresponding to the typical tasks of the target smart base based on the target energy consumption evaluation strategy, the running time, the real-time power, the time-segmented energy consumption and the total energy consumption. It also constructs an energy consumption measurement index value group based on the average power, the running time and the total energy consumption, and uses the average power and the energy consumption measurement index value group to obtain the multi-level quantitative measurement and evaluation results of the operating energy consumption of each preset smart base. The evaluation module includes: The total energy consumption assessment unit is used to determine the first actual running time corresponding to the total energy consumption assessment strategy based on the running time when the target energy consumption assessment strategy is a total energy consumption assessment strategy, and to determine the first actual total energy consumption of the preset digital intelligent base based on the total energy consumption, and to calculate the ratio of the first actual total energy consumption to the first actual running time, so as to obtain the average power of the preset digital intelligent base for performing the typical task of the target digital intelligent base. An idling assessment unit is used to determine the start execution time of the typical task of the target smart base corresponding to the idling assessment strategy and the return idling time of the preset smart base based on the running time when the target energy consumption assessment strategy is an idling assessment strategy. It also calculates the second actual running time corresponding to the typical task of the target smart base based on the start execution time and the return idling time, removes the idling energy consumption from the total energy consumption to obtain the second actual total energy consumption of the preset smart base, and calculates the ratio of the second actual total energy consumption to the second actual running time to obtain the average power of the preset smart base executing the typical task of the target smart base. The first-level evaluation unit is used to perform a first-level quantitative measurement and evaluation of the operating energy consumption of each preset smart base station by using the average power corresponding to the evaluation strategy excluding empty consumption or the evaluation strategy based on total energy consumption. The evaluation module also includes: The vector space construction unit is used to construct a set of energy consumption measurement index values ​​corresponding to each typical task of the target intelligent base based on the average power, the running time and the total energy consumption, and to construct an index vector space based on the set of energy consumption measurement index values ​​of all typical tasks of the target intelligent base. The secondary evaluation unit is used to perform secondary quantitative measurement and evaluation of the operating energy consumption of each preset digital intelligent base through the index vector space.

5. The apparatus according to claim 4, characterized in that, The determining module includes: The type analysis unit is used to identify the type of digital smart base corresponding to each preset digital smart base; The selection unit is used to select the target digital intelligence base typical task corresponding to each preset digital intelligence base according to the type of digital intelligence base, wherein the at least one preset digital intelligence base includes at least one of the target AI big model, target database, target big data management software and computing platform IT infrastructure.

6. An electronic device, characterized in that, include: The memory, the processor, and the computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the multi-level quantitative measurement and evaluation method for energy consumption of the digital intelligent base as described in any one of claims 1-3.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that, The program is executed by the processor to implement the multi-level quantitative measurement and evaluation method for the energy consumption of the smart base station as described in any one of claims 1-3.

8. A computer program product, comprising a computer program, characterized in that, The computer program is executed to implement the multi-level quantitative measurement and evaluation method for the energy consumption of the smart base station as described in any one of claims 1-3.

Images