Energy consumption prediction method, electronic equipment and storage medium

Abstract

The invention provides an energy consumption prediction method, electronic equipment and a storage medium. The method comprises the following steps: acquiring energy efficiency data corresponding to target equipment in a preset time period; determining a plurality of influence factors from the energy efficiency data based on a preset energy efficiency index and a feature extraction algorithm; determining a regression prediction model based on the plurality of influence factors and the energy efficiency index; inputting the influence factors into the regression prediction model, and generating a first prediction value corresponding to each moment in the preset time period; and generating an energy consumption trend chart corresponding to the preset time period based on the first predicted value corresponding to each moment. According to the method, the energy consumption prediction efficiency can be improved.

Description

Technical Field

[0001] The present application relates to the field of energy-saving technology, and in particular to an energy consumption prediction method, electronic equipment and storage medium. Background Art

[0002] The factory assembly line generates a lot of production data during the production process. Generally speaking, if users want to know the data of the product during the production process, for example, which operations or machines consume the most energy, they often use reports based on the production data of the production cycle to find the factors that affect the most energy consumption. In this type of method, on the one hand, all production data needs to be input to generate reports, and the data processing efficiency is low due to the large amount of data. On the other hand, this type of method can only find the factors that affect the most energy consumption in this report, and cannot determine the correlation between this factor and the energy efficiency index, and cannot meet the user's more detailed data prediction requirements.

[0003] In order to overcome this problem, in the relevant technology, professional technicians select and test the production data to obtain the factors affecting the energy consumption and the related related factors from the production data. However, this type of method requires high labor and time costs. In addition, due to the diversity of production data, if only relying on the experience of technicians, it is easy to produce errors and cannot test or analyze some data, which affects the detection accuracy. Summary of the invention

[0004] The embodiments of the present application disclose an energy consumption prediction method, an electronic device, and a storage medium, which solve the problem of low efficiency of energy consumption prediction in related technologies.

[0005] The present application provides an energy consumption prediction method, which includes: obtaining energy efficiency data corresponding to a target device in a preset time period; determining multiple influencing factors from the energy efficiency data based on preset energy efficiency indicators and feature extraction algorithms; determining a regression prediction model based on the multiple influencing factors and the energy efficiency indicators; inputting the multiple influencing factors into the regression prediction model to generate a first prediction value corresponding to each moment in the preset time period; and generating an energy consumption trend graph corresponding to the preset time period based on the first prediction value corresponding to each moment.

[0006] In some optional embodiments, the method also includes: obtaining historical energy efficiency data as training data; extracting multiple feature data from the training data based on a preset energy efficiency index and the feature extraction algorithm; randomly inputting one or more feature data into a linear regression model to construct a regression prediction sub-model corresponding to one or more feature data; based on the one or more feature data and the corresponding regression prediction sub-model, obtaining a second prediction value corresponding to the one or more feature data; calculating a score value for each regression prediction sub-model based on the second prediction value and the energy efficiency index; and using at least one regression prediction sub-model whose score value is greater than a preset threshold as the regression prediction model.

[0007] In some optional embodiments, the method further includes: if there is no regression prediction sub-model whose score value is greater than the preset threshold, re-obtaining updated training data, and re-training using the updated training data to obtain an updated regression prediction sub-model.

[0008] In some optional implementations, the reacquiring updated training data includes: eliminating data that does not conform to a preset data type in the historical energy efficiency data to obtain the updated training data.

[0009] In some optional embodiments, the method of determining multiple influencing factors from the energy efficiency data based on a preset energy efficiency index and a feature extraction algorithm includes: obtaining multiple energy consumption factors related to the energy efficiency index; determining multiple target data from the energy efficiency data based on the multiple energy consumption factors and the feature extraction algorithm; obtaining the correlation between the multiple target data and the multiple energy consumption factors; and determining the multiple influencing factors from the multiple target data based on a preset number and a preset sorting of the correlations.

[0010] In some optional embodiments, determining the regression prediction model based on the multiple influencing factors and the energy efficiency index includes: if a prediction request from a user is received, determining at least one influencing factor from the multiple influencing factors based on the prediction request; determining a regression prediction sub-model including the at least one influencing factor as the regression prediction model based on the at least one influencing factor and the energy efficiency index; if the prediction request is not received, determining a regression prediction sub-model including the multiple influencing factors as the regression prediction model based on the multiple influencing factors and the energy efficiency index.

[0011] In some optional implementations, obtaining the energy efficiency data corresponding to the target device in a preset time period includes: obtaining production data of the target device during a production process; and performing a first-order difference calculation on the production data to obtain the energy efficiency data.

[0012] In some optional implementations, the energy consumption trend graph includes a curve formed by the first predicted value at each moment in a preset time period and a curve formed by the energy efficiency index.

[0013] The present application also provides an electronic device, which includes a processor and a memory, and the processor is used to implement the energy consumption prediction method when executing a computer program stored in the memory.

[0014] The present application also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the energy consumption prediction method is implemented.

[0015] In the energy consumption prediction method provided by the present application, energy efficiency data corresponding to the target device to be analyzed in a preset time period is obtained, multiple influencing factors are determined from the energy efficiency data based on preset energy efficiency indicators and feature extraction algorithms, and a regression prediction model is determined based on multiple influencing factors and energy efficiency indicators, so as to generate a first prediction value corresponding to each moment in the preset time period based on the regression prediction model, thereby obtaining an energy consumption trend graph. The present application can improve the efficiency and accuracy of energy consumption prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 This is an application environment architecture diagram of the energy consumption prediction method provided in the embodiment of the present application.

[0017] Figure 2 It is a flow chart of the energy consumption prediction method provided in an embodiment of the present application. DETAILED DESCRIPTION

[0018] To facilitate understanding, some illustrations of concepts related to the embodiments of the present application are given by way of example for reference.

[0019] It should be noted that in this application, "at least one" means one or more, and "more than one" means two or more than two. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone, where A and B can be singular or plural. The terms "first", "second", "third", "fourth", etc. (if any) in the specification, claims and drawings of this application are used to distinguish similar objects, rather than to describe a specific order or sequence.

[0020] The factory assembly line generates a lot of production data during the production process. Generally speaking, if users want to know the data of the product during the production process, for example, which operations or machines consume the most energy, they often use reports based on the production data of the production cycle to find the factors that affect the most energy consumption. In this type of method, on the one hand, all production data needs to be input to generate reports, and the data processing efficiency is low due to the large amount of data. On the other hand, this type of method can only find the factors that affect the most energy consumption in this report, and cannot determine the correlation between this factor and the energy efficiency index, and cannot meet the user's more detailed data prediction requirements.

[0021] In order to overcome this problem, in the relevant technology, professional technicians select and test the production data to obtain the factors affecting the energy consumption and the related related factors from the production data. However, this type of method requires high labor and time costs. In addition, due to the diversity of production data, if only relying on the experience of technicians, it is easy to produce errors and cannot test or analyze some data, which affects the detection accuracy.

[0022] In order to solve the technical problem of low efficiency of energy consumption prediction in related technologies, the energy consumption prediction method, electronic device and storage medium provided in the embodiments of the present application will firstly be described below with respect to the application scenario of the energy consumption prediction method of the present application.

[0023] Figure 1 The energy consumption prediction method provided in the embodiment of the present application is applied in an electronic device 10 , and the electronic device 10 is connected to a database 20 for communication.

[0024] The electronic device 10 is used to obtain and analyze data in the database 20. The electronic device 10 includes, but is not limited to, a memory 120 and at least one processor 130 which are communicatively connected to each other via a communication bus 110.

[0025] The database 20 may be an operational data store (ODS) database that can support the daily operations of the enterprise and store various types of data such as real-time production data, historical production data, and source data. The database 20 may support functions such as fast data access, data integration, data cleaning, and deduplication. The database 20 provides data support for the electronic device 10. In the embodiment of the present application, the database 20 may be constructed on an independent storage device or established in a server or server cluster, and is not limited to the examples in actual applications.

[0026] The indication Figure 1It is only an example of the electronic device 10 and does not constitute a limitation of the electronic device 10. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the electronic device 10 may also include input and output devices, network access devices, etc.

[0027] See also Figure 2 As shown, Figure 2 is a flow chart of the energy consumption prediction method provided in an embodiment of the present application, which is applied to electronic devices (such as Figure 1 According to different requirements, the order of the steps in the flowchart can be changed, and some steps can be omitted.

[0028] Step S201, obtaining energy efficiency data corresponding to a target device in a preset time period.

[0029] In some embodiments of the present application, the target device may be a product produced in a factory workshop, such as a refrigerator, a washing machine, a water heater, etc. The energy efficiency data refers to the energy consumption value generated in the process of producing the target device, such as power consumption, the amount of materials consumed, etc.

[0030] In some embodiments of the present application, the electronic device may receive a detection instruction input by a user, and in response to the received detection instruction, the electronic device obtains the energy boundary value carried by the detection instruction, and the electronic device obtains the production data of the target device in the production process from the database based on the energy boundary value. The energy boundary value refers to the data detection range set by the user, and the present application does not limit this.

[0031] In some embodiments of the present application, in order to obtain energy efficiency data with obvious periodic changes and avoid the phenomenon of cumulative increase of data, which causes difficulty in subsequent modeling, after obtaining the production data, the production data can be first-order difference calculated to obtain energy efficiency data.

[0032] In one example, the acquisition of production data is time-sequential, so the value at the second moment is subtracted from the value at the first moment, which is a first-order difference calculation, where the first moment and the second moment are two consecutive moments, and the first moment precedes the second moment. The production data at each moment is calculated using the first-order difference calculation method until all moments in the preset time period are traversed to obtain energy efficiency data.

[0033] Step S202: determining a plurality of influencing factors from the energy efficiency data based on a preset energy efficiency index and a feature extraction algorithm.

[0034] In some embodiments of the present application, the energy efficiency index refers to the standard for evaluating and measuring energy utilization. In one example, the energy efficiency ratio of an air conditioner is the ratio of cooling capacity to actual power consumption, which is one of the indicators for measuring the energy efficiency of an air conditioner. Similarly, the energy efficiency ratio of a TV refers to the ratio of the TV's power consumption to the actual display power. The smaller the value, the higher the energy efficiency of the TV. In addition, there are different energy efficiency indicators such as the energy efficiency rating of washing machines and the energy efficiency rating of computers. These indicators are important standards for evaluating and improving the energy efficiency of equipment.

[0035] In another example, the energy efficiency index may also be an energy utilization efficiency index, energy saving rate, resource utilization efficiency, etc. The energy utilization efficiency index refers to the ratio of the amount of energy consumed to the benefit obtained in the process of energy utilization. The energy saving rate refers to the energy saving degree of energy-consuming equipment. The higher the energy saving rate, the higher the energy utilization efficiency of the equipment. Resource utilization efficiency refers to the effective utilization degree of resources. Resource utilization efficiency can be improved by reducing waste and increasing recycling rate.

[0036] In some embodiments of the present application, the feature extraction algorithm may be one or more of a filter method, a wrapper method, and an embedded method. The feature extraction algorithm may be an algorithm for evaluating the correlation between each feature and a target variable. The target variable in the feature extraction algorithm is determined based on the energy efficiency index, that is, multiple energy consumption factors. Each feature in the energy efficiency data is traversed based on the feature extraction algorithm, multiple target data are determined from the energy efficiency data, and the correlation between the multiple target data and the multiple energy consumption factors is obtained. Based on a preset number, multiple influencing factors are determined from the multiple target data according to a preset sorting of the correlation. Among them, the preset number may be a number preset by the user, for example, 5, and the preset sorting may be a sorting of correlation from large to small. In one example, based on the sorting of correlation from large to small, the top 5 target data of correlation are obtained as influencing factors.

[0037] Step S203: determining a regression prediction model based on multiple influencing factors and energy efficiency indicators.

[0038] In some embodiments of the present application, the regression prediction model can be a model obtained by training a linear regression model, specifically including: obtaining historical energy efficiency data as training data, extracting multiple feature data from the training data based on preset energy efficiency indicators and feature extraction algorithms, randomly inputting one or more feature data into the linear regression model, constructing a regression prediction sub-model corresponding to one or more feature data, obtaining a second prediction value corresponding to one or more feature data based on the one or more feature data and the corresponding regression prediction sub-model, calculating a score value for each regression prediction sub-model based on the second prediction value and the energy efficiency indicator, and taking at least one regression prediction sub-model whose score value is greater than a preset threshold as the regression prediction model.

[0039] In one example, assume that five feature data are extracted from the training data, including feature data A, feature data B, feature data C, feature data D, and feature data E. These five feature data are randomly input into the linear regression model, and a regression prediction sub-model corresponding to one or more feature data is constructed. The regression prediction sub-model may include the following equation:

[0040] Y1=b0+b1*characteristic data A;

[0041] Y2=b0+b1*feature data B;

[0042] Y3=b0+b1*feature data A+b2*feature data B;

[0043] Y4=b0+b1*feature data C+b2*feature data D;

[0044] Y5=b0+b1*feature data C+b2*feature data D;

[0045] Y6=b0+b1*feature data A+b2*feature data B+b3*feature data C;

[0046] Y7=b0+b1*feature data A+b2*feature data C+b3*feature data E;

[0047] Y8=b0+b1*feature data A+b2*feature data B+b3*feature data C+b4*feature data D;

[0048] Y9=b0+b1*feature data A+b2*feature data B+b3*feature data C+b4*feature data E;

[0049] Y10=b0+b1*feature data A+b2*feature data B+b3*feature data C+b4*feature data D+b5*feature data E;

[0050] Wherein, b0, b1, b2, b3 and b4 are constants. Based on one or more feature data and the corresponding regression prediction sub-model, the second prediction value corresponding to the one or more feature data is obtained, that is, Y1 to Y10. The above is just an example. In actual applications, the regression prediction sub-model can include more situations, which will not be described one by one here.

[0051] In some embodiments of the present application, the score value of each regression prediction sub-model is calculated based on the second prediction value and the energy efficiency index. The energy efficiency index can be a true value, then the regression sum of squares (SSR) and the total sum of squares (SST) can be calculated based on the second prediction value and the true value output by the regression prediction sub-model, and the score value R can be calculated based on SSR and SST. 2 , expressed in formula: R 2 =SSR / SST.

[0052] In some embodiments of the present application, since the score value is used to evaluate the fit of a model, the regression prediction sub-model can be screened based on the score value to screen out at least one regression prediction sub-model whose score value is greater than a preset threshold, wherein the preset threshold can be set according to actual conditions, for example, 0.8, and the present application is not limited to this.

[0053] In some embodiments of the present application, if there is no regression prediction sub-model with a score greater than a preset threshold, updated training data is re-acquired, and re-trained using the updated training data to obtain an updated regression prediction sub-model. Among them, data that does not conform to the preset data type in the historical energy efficiency data is eliminated, and updated training data is re-acquired. The data that does not conform to the preset data type may be data that does not conform to the data detection range corresponding to the energy boundary value.

[0054] In some embodiments of the present application, if an electronic device receives indication information input by a user, the indication information includes the preset number of models stored in the electronic device, that is, the user hopes to store a certain number (for example, 10) of regression prediction sub-models in the electronic device, but the number of regression prediction sub-models with a score value greater than a preset threshold does not meet the preset number of models of 10, then a regression prediction sub-model with a score value less than or equal to the preset threshold is obtained, and the regression prediction sub-model with a score value less than or equal to the preset threshold is trained using updated training data to obtain an updated regression prediction sub-model, so that in the electronic device, the number of regression prediction sub-models with a score value greater than the preset threshold meets the preset number of models.

[0055] In some embodiments of the present application, after storing multiple regression prediction sub-models in the electronic device, a regression prediction model is determined from the multiple regression prediction sub-models based on multiple influencing factors and energy efficiency indicators. If the electronic device receives a prediction request from a user, at least one influencing factor is determined from the multiple influencing factors based on the prediction request, and a regression prediction sub-model including the at least one influencing factor is determined as the regression prediction model based on the at least one influencing factor and the energy efficiency indicator.

[0056] In one example, the prediction request carries an influencing factor selected by a user, and based on the influencing factor selected by the user and the energy efficiency index, a determined regression prediction sub-model is used as a regression prediction model.

[0057] In some embodiments of the present application, if a prediction request is not received, the electronic device determines a regression prediction sub-model containing multiple influencing factors as a regression prediction model based on multiple influencing factors and energy efficiency indicators. Among them, the multiple regression prediction sub-models stored in the electronic device have priorities. For example, the priority of the regression prediction sub-model corresponding to 5 influencing factors is greater than the priority of the regression prediction sub-model corresponding to 4 influencing factors. If a prediction request is not received, the regression prediction sub-model corresponding to 5 influencing factors is used as the regression prediction model (such as Y10 above). If a prediction request is not received and 4 influencing factors are included, the regression prediction sub-model corresponding to 4 influencing factors is used as the regression prediction model (such as Y8 above).

[0058] In other embodiments of the present application, in addition to the method of training the regression prediction model described in the above embodiments, a machine learning algorithm or a deep learning algorithm can also be used to train a regression prediction model. For example, a random forest regression algorithm can be used to train a regression prediction model, and the present application is not limited to this.

[0059] Step S204: input multiple influencing factors into the regression prediction model to generate a first prediction value corresponding to each moment in a preset time period.

[0060] In some embodiments of the present application, after the regression prediction model is determined, multiple influencing factors can be input into the regression prediction model to obtain a prediction result. Since the multiple influencing factors are the influencing factors corresponding to each moment in the preset time period, the prediction result output by the regression prediction model includes the first prediction value corresponding to each moment in the preset time period.

[0061] Step S205: generating an energy consumption trend graph corresponding to a preset time period based on the first prediction value corresponding to each moment.

[0062] In some embodiments of the present application, in order to intuitively show the difference between the first predicted value and the standard value to the user, the energy consumption trend graph may include a curve formed by the first predicted value at each moment in the preset time period and a curve formed by the energy efficiency index. The curves in the energy consumption trend graph may be marked with different colors or marked with different curve types, which is not limited by the present application.

[0063] In other embodiments of the present application, the energy consumption trend graph may also be a bar graph, a pie chart, a line chart, a scatter plot, a histogram, or a box plot, and the present application does not limit this.

[0064] In an embodiment of the present application, the energy efficiency data corresponding to the target equipment to be analyzed in a preset time period is obtained, and based on the preset energy efficiency index and feature extraction algorithm, multiple influencing factors are determined from the energy efficiency data. Based on the multiple influencing factors and energy efficiency index, a regression prediction model is determined, so that based on the regression prediction model, a first prediction value corresponding to each moment in the preset time period is generated, thereby obtaining an energy consumption trend graph. The present application can improve the efficiency and accuracy of energy consumption prediction. In addition, the present application can perform intelligent analysis and intelligent modeling on the data on the production line, without the need for professional technicians to select influencing factors and manual testing, thereby reducing labor costs.

[0065] Please continue reading Figure 1 In this embodiment, the memory 120 may be an internal memory of the electronic device 10, that is, a memory built into the electronic device 10. In other embodiments, the memory 120 may also be an external memory of the electronic device 10, that is, a memory externally connected to the electronic device 10.

[0066] In some embodiments, the memory 120 is used to store program codes and various data, and to achieve high-speed and automatic access to programs or data during the operation of the electronic device 10 .

[0067] The memory 120 may include a random access memory and may also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0068] In one embodiment, the processor 130 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor, or the processor may be any other conventional processor, etc.

[0069] If the program code and various data in the memory 120 are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, such as the energy consumption prediction method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device that can carry the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), etc.

[0070] It is understandable that the module division described above is a logical function division, and there may be other division methods in actual implementation. In addition, the functional modules in each embodiment of the present application may be integrated in the same processing unit, or each module may exist physically separately, or two or more modules may be integrated in the same unit. The above-mentioned integrated modules may be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0071] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present application and are not intended to limit it. Although the present application has been described in detail with reference to the preferred embodiments, a person of ordinary skill in the art should understand that the technical solution of the present application may be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present application.

Claims

1. A method for predicting energy consumption, characterized in that: The method comprises: Obtain energy efficiency data corresponding to the target device in a preset time period; Based on a preset energy efficiency index and a feature extraction algorithm, a plurality of influencing factors are determined from the energy efficiency data; Determining a regression prediction model based on the multiple influencing factors and the energy efficiency index; Inputting the multiple influencing factors into the regression prediction model to generate a first prediction value corresponding to each moment in the preset time period; Based on the first prediction value corresponding to each moment, an energy consumption trend graph corresponding to the preset time period is generated.

2. The energy consumption prediction method according to claim 1, characterized in that: The method further comprises: Obtain historical energy efficiency data as training data; Based on the preset energy efficiency index and the feature extraction algorithm, extracting a plurality of feature data from the training data; Randomly input one or more feature data into the linear regression model to construct a regression prediction sub-model corresponding to the one or more feature data; Based on the one or more feature data and the corresponding regression prediction sub-model, obtain a second prediction value corresponding to the one or more feature data; Calculate the score of each regression prediction sub-model according to the second prediction value and the energy efficiency index; At least one regression prediction sub-model whose score value is greater than a preset threshold is used as the regression prediction model.

3. The energy consumption prediction method according to claim 2, characterized in that: The method further comprises: If there is no regression prediction sub-model whose score value is greater than the preset threshold, the updated training data is re-acquired, and the updated training data is used for re-training to obtain an updated regression prediction sub-model.

4. The energy consumption prediction method according to claim 3, characterized in that: The step of reacquiring updated training data comprises: Data that does not conform to a preset data type is eliminated from the historical energy efficiency data to obtain the updated training data.

5. The energy consumption prediction method according to claim 1, characterized in that: The method of determining multiple influencing factors from the energy efficiency data based on the preset energy efficiency index and feature extraction algorithm includes: Acquire multiple energy consumption factors related to the energy efficiency indicator; Based on the multiple energy consumption factors and the feature extraction algorithm, determining multiple target data from the energy efficiency data; Acquire the correlation between the plurality of target data and the plurality of energy consumption factors; Based on a preset number, the plurality of influencing factors are determined from the plurality of target data according to a preset order of relevance.

6. The energy consumption prediction method according to claim 1, characterized in that: The step of determining a regression prediction model based on the multiple influencing factors and the energy efficiency index includes: If a prediction request from a user is received, determining at least one influencing factor from the multiple influencing factors based on the prediction request; and determining a regression prediction sub-model including the at least one influencing factor as the regression prediction model according to the at least one influencing factor and the energy efficiency index; If the prediction request is not received, based on the multiple influencing factors and the energy efficiency index, a regression prediction sub-model including the multiple influencing factors is determined as the regression prediction model.

7. The energy consumption prediction method according to claim 1, characterized in that: The obtaining of energy efficiency data corresponding to the target device in a preset time period includes: Acquiring production data of the target device during the production process; Performing first-order difference calculation on the production data to obtain the energy efficiency data.

8. The energy consumption prediction method according to claim 1, characterized in that: The energy consumption trend graph includes a curve formed by the first prediction value at each moment in a preset time period and a curve formed by the energy efficiency index.

9. An electronic device, characterized in that: The electronic device comprises a processor and a memory, wherein the processor is used to execute a computer program stored in the memory to implement the energy consumption prediction method according to any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores at least one instruction, and when the at least one instruction is executed by a processor, the energy consumption prediction method according to any one of claims 1 to 8 is implemented.

Images