Electric heating load adjustable capability evaluation method, device, equipment and medium

Abstract

The invention provides an electric heating load adjustable capacity evaluation method, device and equipment and a medium, and belongs to the technical field of electric heating. Decomposing the meteorological data into modal function components of the meteorological data by adopting a complete set empirical mode decomposition method of adaptive noise; taking the modal function component of the meteorological data as the input of a trained long short-term memory network evaluation model, wherein the long short-term memory network evaluation model outputs the maximum adjustable power and the modal function component of the continuous adjustable time data; and the modal function components of the maximum adjustable power and the continuously adjustable time data are superposed and reconstructed to obtain an evaluation result, and the evaluation result is the maximum adjustable power and the continuously adjustable time data. And an electric heating load adjustable capability evaluation model is established, and the maximum adjustable power and continuous adjustable time of a single electric heating user can be evaluated.

Description

Technical Field

[0001] The present invention relates to electric heating, and in particular to an electric heating load adjustable capacity evaluation method, device, equipment and medium. Background Art

[0002] In recent years, due to the continuous implementation of the "coal to electricity" plan in northern China, the traditional winter coal-fired heating method has been replaced by clean heating methods such as electric heating equipment, resulting in a continuous increase in the proportion of winter electric heating loads, which has brought certain pressure to ensure the heating needs of rural areas in various regions. Electric heating loads are mainly air source heat pump equipment, which has a relatively flexible control method and a certain active adjustment capability. It can participate in the optimization and dispatch of the distribution network as a flexible resource on the demand side, and strengthen the interaction between adjustable loads and the power grid.

[0003] Due to changes in ambient temperature and different usage habits of heating users, the electric heating load has strong randomness and volatility, and the load capacity of a single heating user is small and dispersed, making it difficult to estimate the adjustable capacity of each user's electric heating load, resulting in difficult and inefficient system scheduling. Summary of the invention

[0004] The purpose of the present invention is to provide a method for evaluating the adjustable capacity of electric heating load, so as to solve the problem in the background technology that the adjustable capacity of the load of a single heating user is difficult to estimate.

[0005] In order to achieve the above object, the present invention adopts the following technical solution: In a first aspect, the present invention provides a method for evaluating the adjustable capacity of electric heating load, the specific steps of which are: Get meteorological data, including indoor temperature, outdoor temperature, relative humidity, wind level, and snowfall probability; The meteorological data are decomposed into the modal function components of meteorological data using the complete ensemble empirical mode decomposition method with adaptive noise; The modal function components of the meteorological data are used as the input of the trained long short-term memory network evaluation model, and the modal function components of the maximum adjustable power and the continuous adjustable time data are output; The modal function components of the maximum adjustable power and the continuous adjustable time data are superimposed and reconstructed to obtain an evaluation result, where the evaluation result is the maximum adjustable power and the continuous adjustable time data.

[0006] Furthermore, the long short-term memory network evaluation model is constructed as follows: Obtain the maximum adjustable power and continuous adjustable time data of electric heating equipment under different meteorological data; The meteorological data, the maximum adjustable power corresponding to the meteorological data, and the continuous adjustable time data are decomposed by using the complete set empirical mode decomposition method of adaptive noise, and the modal functions of the meteorological data, the maximum adjustable power corresponding to the meteorological data, and the continuous adjustable time data are obtained respectively; The modal function of the meteorological data is used as the model input, and the modal function of the corresponding maximum adjustable power and continuous adjustable time data is used as the model output to construct a training set; The long short-term memory network is trained based on the training set. After the training is completed, a long short-term memory network evaluation model is obtained.

[0007] Furthermore, the steps of obtaining the maximum adjustable power and continuous adjustable time data corresponding to the electric heating equipment under different meteorological data are as follows: Collect electric heating user information and obtain user feature data sets; Based on the k-prototype algorithm, user feature data is clustered and grouped to obtain clustered electric heating users; Typical electric heating equipment is selected according to the clustered electric heating users. By simulating the selected typical electric heating equipment, the maximum adjustable power and continuous adjustable time data of the electric heating equipment under different meteorological data are obtained.

[0008] Furthermore, in the step of decomposing the meteorological data, the maximum adjustable power and the continuous adjustable time data using the complete set empirical mode decomposition method with adaptive noise: 1) In the original data Y ( t ) N Sub-Gaussian white noise, we get N Preprocessing sequence Y n ( t ): (1); In the formula, is the weight coefficient of Gaussian white noise, It is n Gaussian white noise during the processing, n =1,2,… N ; The original data are the acquired meteorological data and the maximum adjustable power and continuous adjustable time data; 2) For all preprocessed sequences Y n ( t ) performs EMD decomposition to obtain the first group of IMF components ,calculate The average value of The average value of is taken as the first IMF component decomposed by CEEMDAN , as shown in formula (2): (2); At the same time, we get the first residual sequence , as shown in formula (3): (3); 3) The residual sequence join in N Sub-Gaussian white noise is constructed into N new sequences , where E 1 (•) represents the first IMF component after EMD decomposition of the new sequence. The second IMF component is obtained by performing EMD decomposition on N new sequences and calculating the average value as shown in formula (4): : (4); The corresponding residual is , as shown in formula (5): (5); By analogy, m The residual of the stage is: (6); 4) For m Sequence of stages conduct N The first EMD decomposition, that is, the first m +1 IMF sequence, as shown in formula (7): (7); 5) Repeat the decomposition sequence and calculate the residual sequence until the decomposition stops after reaching the preset number of iterations. The final residual sequence is formula (8): (8); go through M After the iteration, the data Y(t) is decomposed by CEEMDAN into equation (9): (9).

[0009] Furthermore, the electric heating user information includes maximum age, minimum age, annual household income, typical heating load curve, and user heating comfort preference; The numerical attribute data of the user's maximum age, minimum age, annual household income and typical heating load curve are normalized according to formula (10): (10); in, is the original value, is the normalized value, and Represent the maximum and minimum values ​​in the sequence respectively; Users' heating comfort preferences are classified.

[0010] Furthermore, in the step of clustering and grouping user characteristic data based on the k-prototype algorithm to obtain clustered electric heating users: 1) Randomly select k feature data from the feature data set as the initial clustering center; 2) Classify each feature data according to the mixed distance from each initial cluster center; After all feature data are classified, the cluster center of the numerical attribute data is updated according to the mean, and the cluster center of the categorical attribute data is updated with the category that appears the most times. Each feature data is then classified according to the mixed distance with the updated cluster center; 3) Repeatedly update the cluster center until the cluster center does not change or the upper limit of the iteration number is reached, completing the clustering of electric heating users and obtaining clustered electric heating users.

[0011] Furthermore, the mixed distance between each feature data and the cluster center is calculated as follows: When the feature data is numerical attribute data, the distance , n is the length of the numerical sequence; When the feature data is categorical attribute data, the distance ; In the formula, x i and x j From the normalized numerical attribute data Any two values ​​selected from The formula for calculating the mixing distance is: ,in Represents the weight coefficient of the classification attribute feature, with a value of [0,1]. The classification attribute feature refers to the user's heating comfort preference after classification processing. The size of determines the degree to which the power company accepts the user's subjective wishes when regulating the electric heating load.

[0012] In a second aspect of the present invention, there is provided an electric heating load adjustable capacity evaluation device, comprising: Acquisition module, used to obtain meteorological data; A decomposition module, for decomposing the meteorological data into modal function components of the meteorological data by using a complete ensemble empirical mode decomposition method with adaptive noise; An input-output module is used to use the modal function components of the meteorological data as inputs of the trained long short-term memory network evaluation model, and the long short-term memory network evaluation model outputs the modal function components of the maximum adjustable power and the continuous adjustable time data; The evaluation module is used for superimposing and reconstructing the modal function components of the maximum adjustable power and the continuous adjustable time data to obtain an evaluation result, wherein the evaluation result is the maximum adjustable power and the continuous adjustable time data.

[0013] According to a third aspect of the present invention, there is provided an electronic device, comprising a processor and a memory, wherein the processor is configured to execute a computer program stored in the memory to implement the method for evaluating the adjustable capacity of an electric heating load.

[0014] According to a fourth aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores at least one instruction, and when the at least one instruction is executed by a processor, the method for evaluating the adjustable capacity of an electric heating load is implemented.

[0015] Compared with the prior art, the beneficial effects of the present invention are as follows: A long short-term memory network evaluation model for evaluating the adjustable capacity of electric heating loads is established, which can evaluate the maximum adjustable power and continuous adjustable time of a single electric heating user, enhance the data feature extraction capability, give full play to the long short-term memory network to capture the long-term and short-term dependencies in the time series, better learn the time series characteristics of each component, and improve the overall evaluation accuracy of the model; The users of electric heating are clustered according to their characteristics. The k-prototype algorithm is used to improve the clustering effect of processing numerical attribute data and categorical attribute data. The loads of users with the same characteristics are aggregated and then centrally regulated, which improves the efficiency of load regulation and reduces the complexity of regulation. The complete ensemble empirical mode decomposition method based on adaptive noise performs modal decomposition on the original meteorological data, maximum adjustable power and continuous adjustable time data. The introduction of noise effectively improves the model's adaptability to nonlinear and non-stationary data and reduces noise interference. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The drawings constituting a part of the present application are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings: Figure 1 This is a flow chart of a method for evaluating the adjustable capacity of electric heating loads according to Embodiment 1 of the present invention; Figure 2 This is a structural block diagram of a device for evaluating the adjustable capacity of electric heating loads according to Embodiment 2 of the present invention; Figure 3 This is a structural block diagram of an electronic device according to embodiment 3 of the present invention. DETAILED DESCRIPTION

[0017] The present invention will be described in detail below with reference to the accompanying drawings and in combination with embodiments. It should be noted that the embodiments and features in the embodiments of the present application can be combined with each other without conflict.

[0018] The following detailed description is an exemplary description, which is intended to provide further detailed description of the present invention. Unless otherwise specified, all technical terms used in the present invention have the same meaning as those generally understood by those skilled in the art to which the present application belongs. The terms used in the present invention are only for describing specific embodiments, and are not intended to limit exemplary embodiments according to the present invention.

[0019] Example 1 The specific implementation scheme of the method for evaluating the adjustable capacity of electric heating load of the present invention is as follows: Step 1: Cluster users based on their electric heating user characteristics (1) Acquisition and preprocessing of electric heating user characteristic data By surveying electric heating users, we obtained basic user information and calculated the maximum and minimum age, annual household income and heating comfort preference of each electric heating user.

[0020] Among them, the heating comfort preference can be divided into three levels: Level I is a low temperature requirement, Level II is a moderate temperature requirement, and Level III is a high temperature requirement. The heating comfort preference is categorical attribute data, and in data processing, it is represented by one-hot vector encoding as

[001] ,

[010] , and

[100] respectively.

[0021] The power company’s electricity consumption information collection system is used to obtain users’ daily electricity load data during the winter heating period of the previous year. The collection frequency is one data point every 15 minutes, 96 data points per day. The average daily load of each user each month is calculated and spliced ​​to form a typical load curve for the user during the heating period.

[0022] For example, the winter heating period in the north is from November 15 to March 15 of the following year, a total of four months. The average daily electricity load of each user from November to March of the following year is calculated separately, and after splicing, a load data curve with a length of 480 is obtained.

[0023] The data of numerical attributes such as the user's maximum age, minimum age, annual household income, and typical heating load curve are normalized according to the following formula: ; in, is the original value, is the normalized value, and Represent the maximum and minimum values ​​in the sequence respectively.

[0024] (2) Clustering of electric heating users based on the k-prototype algorithm The characteristics of electric heating users after data processing can be expressed as ,in, A Represents the maximum age of the user's family members. a Represents the youngest age of the user's family members. I Represents the user's annual household income, P Represents the typical heating load curve of the user, Q represents the user's heating comfort preference. A, a, I, P is a numerical attribute, feature Q is a classification attribute.

[0025] The specific steps of applying k-prototype algorithm clustering are as follows: 1) Randomly select k feature data from the user feature data set as the initial clustering center; 2) Calculate the distance from each feature data to each cluster center and divide it into the class with the closest distance. After each division, update the cluster center.

[0026] The distance from each feature data to the cluster center is calculated as follows: If the feature is numerical attribute data, the distance , n is the length of the numerical sequence; If the feature is categorical attribute data, the distance ; The formula for calculating the mixing distance is: ,in The weight coefficient representing the classification attribute feature is [0,1]. In this patent, the classification attribute feature specifically refers to the user's heating comfort preference. The size of determines the degree to which the power company accepts the user's subjective wishes when regulating the electric heating load.

[0027] 3) After all feature data are classified, the cluster center of the numerical attribute data is updated according to the mean, and the cluster center of the categorical attribute data is updated according to the category with the most occurrences; 4) Repeat step 3) until the cluster center does not change or the upper limit of the number of iterations is reached, and the clustering of electric heating users is completed.

[0028] Step 2: Construct an evaluation model for the adjustable capacity of electric heating load (1) Construct model input and output data sets The maximum adjustable power and continuous adjustable time are used as evaluation indicators of the adjustable capacity of the electric heating load. For the electric heating users clustered in step 1, typical electric heating equipment is selected according to the clustered electric heating users. By simulating the selected typical electric heating equipment, the maximum adjustable power and continuous adjustable time data corresponding to the electric heating equipment under different meteorological data are obtained, wherein the specific meteorological data include indoor temperature, outdoor temperature, relative humidity, wind force level, snowfall probability, and the data acquisition period is no less than 1 hour.

[0029] (2) Modal decomposition of time series data The Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) method is used. In this method, white noise is gradually added to the intrinsic mode function (IMF) after empirical mode decomposition (EMD) in each iteration. This method can effectively reduce the impact of white noise on the decomposition results, improve the accuracy and stability of the decomposition, and is suitable for fluctuating data such as weather and load.

[0030] The specific steps are as follows: 1) In the original data Y ( t ) N Sub-Gaussian white noise, we get N Preprocessing sequence Y n ( t ): ; in, is the weight coefficient of Gaussian white noise, It is n Gaussian white noise during the processing, n =1,2,… N ; The original data are the acquired meteorological data and the maximum adjustable power and continuous adjustable time data; 2) For all preprocessed sequences Y n ( t ) performs EMD decomposition to obtain the first group of IMF components ,calculate The average value of The average value of is taken as the first IMF component decomposed by CEEMDAN , as shown below: ; At the same time, we get the first residual sequence , as shown below: ; 3) Continue to convert the residual sequence Add Gaussian white noise to construct N new sequences ,in E 1 (•) indicates the first 1 IMF components, perform EMD decomposition on the new sequence and calculate the average value to get the second IMF component , the corresponding residual is , as shown below: ; ; By analogy, m The residual of the stage is: ; 4) For m Sequence of stages conduct N The first EMD decomposition, that is, the first m +1 IMF sequence, as follows: ; 5) Repeat the decomposition sequence and calculate the residual sequence until the decomposition stops after reaching the preset number of iterations. The final residual sequence is: ; go through M After the iteration, the expression of the data Y(t) after decomposition by CEEMDAN is: ; (3) Using the long short-term memory (LSTM) network to build an evaluation model The data set obtained in step (1) is decomposed by CEEMDAN in step (2) to obtain IMF components. Each IMF component represents a different frequency component in the data. After decomposition, the local characteristics and trends of the data can be better captured.

[0031] The LSTM model is defined. The model input is the IMF components of the meteorological data after being decomposed by CEEMDAN. The model output is the IMF components of the maximum adjustable power and continuous adjustable time of the electric heating load under the corresponding meteorological data conditions after being decomposed by CEEMDAN. Each IMF component corresponds to different LSTM model parameters, which specifically include the number of LSTM layers and the number of units in each layer.

[0032] The constructed LSTM model is trained, the model parameters are adjusted to minimize the error, each IMF component is input into the corresponding LSTM model, the output result of each IMF component is obtained, the output results of all IMF components are superimposed and reconstructed to obtain the result of the final evaluation model.

[0033] Application of the evaluation model for the adjustable capacity of electric heating Through the above steps, the adjustable capacity of the electric heating load of each user can be obtained, that is, the maximum adjustable power and continuous adjustable time of the electric heating load. The maximum adjustable powers of the electric heating loads of users of the same category are aggregated, and users of the same category are uniformly regulated in subsequent adjustments.

[0034] The relevant control departments of the power company consider the safety and economy of the distribution network operation, evaluate the adjustable capacity of the user's electric heating load, and issue control instructions to the user's electric heating load, including the load control amount and control time, and set different load adjustment ratios for users with different clustering results, taking into account the economy of the power grid operation and the comfort of user heating.

[0035] Example 2 like Figure 2 As shown, based on the same inventive concept as the above embodiment, the present invention also provides an electric heating load adjustable capacity evaluation device, comprising: Acquisition module, used to obtain meteorological data; A decomposition module, for decomposing the meteorological data into modal function components of the meteorological data by using a complete ensemble empirical mode decomposition method with adaptive noise; An input-output module, used for taking the modal function components of the meteorological data as the input of the trained long short-term memory network evaluation model, and outputting the modal function components of the maximum adjustable power and the continuous adjustable time data; The evaluation module is used for superimposing and reconstructing the modal function components of the maximum adjustable power and the continuous adjustable time data to obtain the evaluation result.

[0036] Example 3 like Figure 3 As shown, the present invention also provides an electronic device 100 for evaluating the adjustable capacity of electric heating load; The electronic device 100 includes a memory 101 , at least one processor 102 , a computer program 103 stored in the memory 101 and executable on the at least one processor 102 , and at least one communication bus 104 .

[0037] The memory 101 may be used to store a computer program 103 , and the processor 102 implements the steps of Example 1 by running or executing the computer program stored in the memory 101 and calling the data stored in the memory 101 .

[0038] The memory 101 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area may store data (such as audio data) created according to the use of the electronic device 100, etc. In addition, the memory 101 may include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other non-volatile solid-state storage devices.

[0039] At least one processor 102 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. The processor 102 may be a microprocessor or any conventional processor, etc. The processor 102 is the control center of the electronic device 100, and uses various interfaces and lines to connect various parts of the entire electronic device 100.

[0040] The memory 101 in the electronic device 100 stores a plurality of instructions to implement the evaluation of the adjustable capacity of the electric heating load, and the processor 102 can execute the plurality of instructions to implement: Get weather data; The meteorological data are decomposed into the modal function components of meteorological data using the complete ensemble empirical mode decomposition method with adaptive noise; The modal function components of the meteorological data are used as the input of the trained long short-term memory network evaluation model, and the modal function components of the maximum adjustable power and the continuous adjustable time data are output; The modal function components of the maximum adjustable power and the continuous adjustable time data are superimposed and reconstructed to obtain an evaluation result, where the evaluation result is the maximum adjustable power and the continuous adjustable time data.

[0041] Example 4 If the module / unit integrated in the electronic device 100 is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiment 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 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. Computer-readable media may include: any entity or device capable of carrying computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory and read-only memory (ROM, Read-Only Memory).

[0042] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0043] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0044] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0045] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0046] In the description of this specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0047] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A method for evaluating the adjustable capacity of electric heating load, characterized in that: The specific steps are: Get weather data; The meteorological data are decomposed into the modal function components of meteorological data using the complete ensemble empirical mode decomposition method with adaptive noise; The modal function components of the meteorological data are used as inputs of the trained long short-term memory network evaluation model, and the long short-term memory network evaluation model outputs the modal function components of the maximum adjustable power and the continuous adjustable time data; The modal function components of the maximum adjustable power and the continuous adjustable time data are superimposed and reconstructed to obtain an evaluation result, where the evaluation result is the maximum adjustable power and the continuous adjustable time data.

2. The method for evaluating the adjustable capacity of electric heating load according to claim 1, characterized in that: The construction of the long short-term memory network evaluation model is: Obtain the maximum adjustable power and continuous adjustable time data of electric heating equipment under different meteorological data; The meteorological data, the maximum adjustable power corresponding to the meteorological data, and the continuous adjustable time data are decomposed by using the complete set empirical mode decomposition method of adaptive noise, and the modal functions of the meteorological data, the maximum adjustable power corresponding to the meteorological data, and the continuous adjustable time data are obtained respectively; The modal function of the meteorological data is used as the model input, and the modal function of the corresponding maximum adjustable power and continuous adjustable time data is used as the model output to construct a training set; The long short-term memory network is trained based on the training set. After the training is completed, a long short-term memory network evaluation model is obtained.

3. The method for evaluating the adjustable capacity of electric heating load according to claim 2, characterized in that: The steps for obtaining the maximum adjustable power and continuous adjustable time data of the electric heating equipment under different meteorological data are as follows: Collect electric heating user information and obtain user feature data sets; Clustering and grouping the feature data in the user feature data set to obtain clustered electric heating users; Typical electric heating equipment is selected according to the clustered electric heating users. By simulating the selected typical electric heating equipment, the maximum adjustable power and continuous adjustable time data of the electric heating equipment under different meteorological data are obtained.

4. The method for evaluating the adjustable capacity of electric heating load according to claim 2, characterized in that: The meteorological data, maximum adjustable power and continuous adjustable time data are decomposed using the complete ensemble empirical mode decomposition method with adaptive noise, including: 1) In the original data Y ( t ) N Sub-Gaussian white noise, we get N Preprocessing sequence Y n ( t ): （1）； In the formula, is the weight coefficient of Gaussian white noise, It is n Gaussian white noise during the processing, n =1,2,… N ; The original data are the acquired meteorological data and the maximum adjustable power and continuous adjustable time data; 2) For all preprocessed sequences Y n ( t ) performs EMD decomposition to obtain the first group of IMF components ,calculate The average value of The average value of is taken as the first IMF component decomposed by CEEMDAN , as shown in formula (2): （2）； At the same time, we get the first residual sequence , as shown in formula (3): （3）； 3) The residual sequence join in N Sub-Gaussian white noise is constructed into N new sequences , where E 1(•) represents the first IMF component after EMD decomposition of the new sequence. The second IMF component is obtained by performing EMD decomposition on N new sequences and calculating the average value as shown in formula (4): : （4）； The corresponding residual is , as shown in formula (5): （5）； By analogy, m The residual of the stage is: （6）； 4) For m Sequence of stages conduct N The first EMD decomposition, that is, the first m +1 IMF sequence, as shown in formula (7): （7）； 5) Repeat the decomposition sequence and calculate the residual sequence until the decomposition stops after reaching the preset number of iterations. The final residual sequence is formula (8): （8）； go through M After the iteration, the data Y(t) is decomposed by CEEMDAN into equation (9): （9）。 5. The method for evaluating the adjustable capacity of electric heating load according to claim 3, characterized in that: Electric heating user information includes maximum age, minimum age, annual household income, typical heating load curve, and user heating comfort preference; The numerical attribute data of the user's maximum age, minimum age, annual household income and typical heating load curve are normalized according to formula (10): （10）； in, is the original value, is the normalized value, and Represent the maximum and minimum values ​​in the sequence respectively; Users' heating comfort preferences are classified.

6. The method for evaluating the adjustable capacity of electric heating load according to claim 5, characterized in that: The user feature data set is clustered and grouped to obtain clustered electric heating users, including: 1) Randomly select k feature data from the feature data set as the initial clustering center; 2) Classify each feature data according to the mixed distance from each initial cluster center; After all feature data are classified, the cluster center of the numerical attribute data is updated according to the mean, and the cluster center of the categorical attribute data is updated according to the category with the most occurrences. Each feature data is then classified according to the mixed distance with the updated cluster center; 3) Repeatedly update the cluster center until the cluster center does not change or the upper limit of the iteration number is reached, completing the clustering of electric heating users and obtaining clustered electric heating users.

7. The method for evaluating the adjustable capacity of electric heating load according to claim 6, characterized in that: The mixed distance between each feature data and the cluster center is calculated as follows: When the feature data is numerical attribute data, the distance , n is the length of the numerical sequence; When the feature data is categorical attribute data, the distance ; In the formula, x i and x j From the normalized numerical attribute data Any two values ​​selected from The formula for calculating the mixing distance is: ,in Represents the weight coefficient of the classification attribute feature; The classification attribute feature refers to the user's heating comfort preference after classification processing.

8. An electric heating load adjustable capacity evaluation device, characterized in that: include: Acquisition module, used to obtain meteorological data; A decomposition module, for decomposing the meteorological data into modal function components of the meteorological data by using a complete ensemble empirical mode decomposition method with adaptive noise; An input-output module is used to use the modal function components of the meteorological data as inputs of the trained long short-term memory network evaluation model, and the long short-term memory network evaluation model outputs the modal function components of the maximum adjustable power and the continuous adjustable time data; The evaluation module is used for superimposing and reconstructing the modal function components of the maximum adjustable power and the continuous adjustable time data to obtain an evaluation result, wherein the evaluation result is the maximum adjustable power and the continuous adjustable time data.

9. An electronic device, characterized in that: It comprises a processor and a memory, wherein the processor is used to execute a computer program stored in the memory to implement the method for evaluating the adjustable capacity of electric heating load as described in any one of claims 1 to 7.

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 the processor, the method for evaluating the adjustable capacity of the electric heating load according to any one of claims 1 to 7 is implemented.

Images