A method, device and terminal device for identifying users with high demand response potential

Abstract

The present invention provides a method, apparatus and terminal device for identifying users with high demand response potential. The method includes: collecting load data of users before and after load demand response in existing time-of-use electricity price pilot projects; classifying users according to the load data and assigning different labels to different categories of users; respectively extracting questionnaire features and load features according to user questionnaires and load data; classifying users with the extracted questionnaire features and load features as input values and labels as output values to obtain classified users, and determining users corresponding to preset labels among the classified users as target users according to a preset number of target users. The present invention can identify users with high response potential and suitable for participating in time-of-use electricity prices, provide theoretical support for load aggregators to select high-quality demand response resources, and reduce the risk of load demand response projects.

Description

Technical Field

[0001] The present invention relates to the technical field of electric power, and in particular, to a method, device and terminal device for identifying users with high demand response potential. Background Art

[0002] China's energy system is undergoing changes, and the demand side is gradually becoming the key to the energy system. By participating in demand response projects, it is gradually developing from passive to active.

[0003] Power load demand response (DR) is an important means to achieve a smart grid, and its potential characterizes the available margin of DR. Expanding demand response potential can not only relieve the operation pressure of the power grid, reduce the system operation cost, but also effectively absorb intermittent energy and contribute to energy conservation and emission reduction. Power demand response can be divided into price-based and incentive-based according to the response signal. Price-based means that users adjust their electricity consumption behavior according to electricity price information, and incentive-based means that users adjust their electricity consumption behavior according to the incentive policies formulated by the power dispatching agency. As a price-based demand response, the time-of-use electricity price project has been widely used in demand response projects due to its advantages such as low control cost, easy user participation, and relatively stable user participation rate.

[0004] Under the time-of-use electricity price, the response degrees of different users are not the same, which is also the reason why the implementation effects of most time-of-use electricity price projects are lower than expected. Therefore, it is of great significance to identify users with high potential demand response under the time-of-use electricity price. By predicting the categories of users, the response potential of users can be qualitatively analyzed, providing theoretical support for power supply companies and aggregators to screen high-quality demand response resources. However, at present, it is still impossible to accurately locate users with high response potential and suitable for participating in the demand response project of the time-of-use electricity price, resulting in poor time-of-use electricity price effects. Summary of the Invention

[0005] Embodiments of the present invention provide a method, device and terminal device for identifying users with high demand response potential to solve the problem that it is still impossible to accurately locate users with high response potential and suitable for participating in the demand response project of the time-of-use electricity price.

[0006] In a first aspect, embodiments of the present invention provide a method for identifying users with high demand response potential, including:

[0007] Collecting load data of users before and after load demand response in existing time-of-use electricity price pilot projects;

[0008] Classifying the users according to the load data and assigning different labels to different categories of users;

[0009] Extracting questionnaire features and load features respectively according to user questionnaires and the load data;

[0010] Classify users by using the extracted questionnaire features and the load features as input values and the label as the output value to obtain classified users, and determine users corresponding to the preset label among the classified users as target users according to the preset number of target users.

[0011] In a possible implementation manner, the classifying the users according to the load data and assigning different labels to different categories of users includes:

[0012] Calculate the monthly load demand response reduction amount of each user according to the load data;

[0013] Classify the users according to the monthly load demand response reduction amount, assign different labels to different categories of users, and determine the label corresponding to each user.

[0014] In a possible implementation manner, the calculating the monthly load demand response reduction amount of each user according to the load data includes:

[0015] Perform weekly matching based on the weather characteristics before and after the load demand response to determine the Mth week before the load demand response with similar weather characteristics and the Kth week after the load demand response;

[0016] Calculate the peak period response reduction amount of each user corresponding to the Mth week due to the influence of the load demand response according to the load data corresponding to the Mth week and the load data corresponding to the Kth week;

[0017] Calculate the average load reduction amount of the control group users of each user corresponding to the Mth week according to the load data of the control group users of each user before the load demand response;

[0018] Calculate the load demand response reduction amount of each user in the Mth week according to the peak period response reduction amount and the average load reduction amount;

[0019] Calculate the monthly load demand response reduction amount of each user according to the above method for calculating the load demand response reduction amount of each user in the Mth week.

[0020] In a possible implementation manner, the calculating the peak period response reduction amount of each user corresponding to the Mth week due to the influence of the load demand response according to the load data corresponding to the Mth week and the load data corresponding to the Kth week includes:

[0021] According to Calculate the peak period response reduction amount corresponding to user i in the Mth week due to the influence of the load demand response;

[0022] Wherein, Denote the peak period response reduction of user i due to the impact of load demand response in the M-th week; Denote the load data of user i in the peak period of the K-th week, Denote the load data of user i in the peak period of the M-th week.

[0023] In a possible implementation, calculating the average load reduction of the control group users of each user corresponding to a preset time period according to the load data of the control group users of each user before the load demand response includes:

[0024] According to Calculate the average load reduction corresponding to the control group users of user i in the M-th week;

[0025] Wherein, Denote the average load reduction corresponding to the control group users of user i in the M-th week, Denote the number of elements of the control group users of user i, Denote the load reduction corresponding to the j-th element of the control group users of user i in the M-th week.

[0026] In a possible implementation, calculating the monthly load demand response reduction of each user according to the peak period response reduction and the average load reduction includes:

[0027] Calculate the difference between the reduction matrix corresponding to the peak period response reduction and the reduction matrix corresponding to the average load reduction, and use the difference as the monthly load demand response reduction of the corresponding user.

[0028] In a possible implementation, classifying users by using the extracted questionnaire features and the load features as input values and the label as the output value to obtain the classified users includes:

[0029] Adopt the random forest method to perform dimensionality reduction processing on the extracted questionnaire features and the load features to obtain the features after dimensionality reduction processing;

[0030] Use the extracted questionnaire features and the load features as input values and the label as the output value, and classify users through a support vector classification model to obtain the classified users.

[0031] In a second aspect, an embodiment of the present invention provides an identification device for users with high demand response potential, including:

[0032] A collection module, configured to collect the load data of users before and after the load demand response in the existing time-of-use electricity price pilot project;

[0033] A calculation module, configured to classify the users according to the load data and assign different labels to different categories of users;

[0034] An extraction module, configured to extract questionnaire features and load features respectively according to a user questionnaire and the load data;

[0035] A classification module, configured to classify users by using the extracted questionnaire features and the load features as input values and the labels as output values, obtain the classified users, and determine the users corresponding to the preset labels among the classified users as target users according to a preset number of target users.

[0036] In a third aspect, an embodiment of the present invention provides a terminal, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the method described in the first aspect or any possible implementation manner of the first aspect above are implemented.

[0037] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, the steps of the method described in the first aspect or any possible implementation manner of the first aspect above are implemented.

[0038] An embodiment of the present invention provides a method, an apparatus, a terminal, and a storage medium for identifying users with high demand response potential. By collecting the load data of users before and after load demand response in existing time-of-use electricity price pilot projects; classifying users according to the load data and assigning different labels to different categories of users; then combining the questionnaire features and the load features to construct a feature set, and using the random forest algorithm to extract features highly correlated with the reduction amount, so as to identify users with high response potential and suitable for participating in time-of-use electricity price, provide a theoretical support for load aggregators to select high-quality demand response resources, and reduce the risk of load demand response projects. Description of the Drawings

[0039] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for use in the embodiments or the description of the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0040] Figure 1 is an application scenario diagram of the method for identifying users with high demand response potential provided by the embodiment of the present invention;

[0041] Figure 2It is a schematic diagram for verifying the reduction amount and reduction percentage provided by the embodiments of the present invention;

[0042] Figure 3 It is a schematic structural diagram of an identification device for users with high demand response potential provided by the embodiments of the present invention;

[0043] Figure 4 It is a schematic diagram of a terminal device provided by the embodiments of the present invention. Detailed implementation manners

[0044] In the following description, specific details such as specific system structures and technologies are presented for the purpose of illustration rather than limitation, so as to thoroughly understand the embodiments of the present invention. However, those skilled in the art should clearly understand that the present invention can also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid unnecessary details from hindering the description of the present invention.

[0045] To make the objectives, technical solutions, and advantages of the present invention clearer, the following will be described through specific embodiments with reference to the accompanying drawings.

[0046] Figure 1 It is an application scenario diagram of an identification method for users with high demand response potential provided by the embodiments of the present invention. As Figure 1 shown, it includes the following steps.

[0047] Step 101, collect the load data of users before and after load demand response in existing time-of-use electricity price pilot projects.

[0048] Optionally, the collection of the load data of users before and after load demand response in existing time-of-use electricity price pilot projects may include: based on the existing time-of-use electricity price pilot projects, collect a power data for each user at intervals of Δt before and after the time-of-use electricity price, denoted as P t,i,k , where t is the sampling moment, i is the user number, k is the number of the collection date, and P t,i,k represents the power of the i-th user at the t-th moment on the k-th collection day, t = 1, 2......T, T is the number of moments at the time interval Δt, i = 1, 2.....I, I is the total number of users, k = 1, 2......K, K is the number of the date for collecting load data, and k includes both before and after the time-of-use electricity price.

[0049] Step 102, classify the users according to the load data and assign different labels to different categories of users.

[0050] Optionally, in this step, classifying the users according to the load data and assigning different labels to different categories of users may include:

[0051] Calculating the monthly load demand response reduction amount for each user according to the load data;

[0052] Classifying the users according to the monthly load demand response reduction amount, assigning different labels to different categories of users, and determining the labels corresponding to each user.

[0053] When calculating the monthly load demand response reduction amount for each user, a difference-in-differences model can be used to calculate the monthly peak-hour demand response reduction amount for each user before and after the time-of-use electricity price. The basic idea of the difference-in-differences model is to construct a difference-in-differences statistic reflecting the policy effect by comparing the differences between the control group and the treatment group before and after the implementation of the policy.

[0054] In one embodiment, the calculating the monthly load demand response reduction amount for each user according to the load data may include:

[0055] Performing weekly matching based on the weather characteristics before and after the load demand response to determine the Mth week before the load demand response with similar weather characteristics and the Kth week after the load demand response;

[0056] Calculating the peak-hour response reduction amount for each user corresponding to the Mth week due to the influence of the load demand response according to the load data corresponding to the Mth week and the load data corresponding to the Kth week;

[0057] Calculating the average load reduction amount for the control group users of each user corresponding to the Mth week according to the load data of the control group users of each user before the load demand response;

[0058] Calculating the load demand response reduction amount for each user in the Mth week according to the peak-hour response reduction amount and the average load reduction amount;

[0059] Calculating the monthly load demand response reduction amount for each user according to the above method of calculating the load demand response reduction amount for each user in the Mth week.

[0060] That is, first, the difference method is used to calculate the peak-hour response reduction amount caused before and after the time-of-use electricity price based on the weather matching principle. Calculating the peak-hour response reduction amount for each user corresponding to the Mth week due to the influence of the load demand response according to the load data corresponding to the Mth week and the load data corresponding to the Kth week may include:

[0061] According to Calculating the peak-hour response reduction amount corresponding to user i in the Mth week due to the influence of the load demand response;

[0062] Among them, represents the peak period response reduction amount of user i due to the impact of load demand response in the M-th week; represents the load data of user i in the peak period of the K-th week, represents the load data of user i in the peak period of the M-th week.

[0063] According to the above calculation method, the monthly peak-time demand response reduction amount of each user due to the impact of load demand response can be calculated, and the calculation results can form a reduction amount matrix PDRT.

[0064] Then calculate the average load reduction amount of the control group users. Here, the control group users are those users with similar electricity consumption patterns as the current users when time-of-use electricity prices are not implemented. Calculating the average load reduction amount of the control group users corresponding to the M-th week for each user according to the load data of the control group users of each user before load demand response may include:

[0065] According to calculate the average load reduction amount of the control group users of user i corresponding to the M-th week;

[0066] Among them, represents the average load reduction amount of the control group users of user i corresponding to the M-th week, represents the number of elements of the control group users of user i, represents the load reduction amount corresponding to the j-th element of the control group users of user i in the M-th week.

[0067] According to the above calculation method, the monthly peak-time demand response reduction amount of the control group users of each user due to the impact of load demand response can be calculated, and the calculation results can form a reduction amount matrix Trend.

[0068] Finally, calculating the monthly load demand response reduction amount of each user according to the peak period response reduction amount and the average load reduction amount may include:

[0069] Calculate the difference between the reduction amount matrix PDRT corresponding to the peak period response reduction amount and the reduction amount matrix Trend corresponding to the average load reduction amount, and use the difference as the monthly load demand response reduction amount of the corresponding user.

[0070] Optionally, classifying the users according to the monthly load demand response reduction amount, assigning different labels to different categories of users, and determining the corresponding labels of each user may include:

[0071] Remove the outliers in the monthly load demand response reduction amount by the interquartile range method, divide the remaining users into two categories according to the size of the monthly load demand response reduction amount, one category is high-potential users and the other is low-potential users, and assign label 1 to high-potential users and label 2 to low-potential users.

[0072] Step 103: Extract questionnaire features and load features respectively according to the user questionnaire and the load data.

[0073] Optionally, the extracted questionnaire features may include: social demographics (gender, age, employment status, household size, education level, income), housing characteristics (housing type, years of residence, number of rooms, proportion of energy-saving lamps, proportion of double-glazed windows, whether there is an insulated wall), electrical appliances and heating equipment (number of washing machines, number of dryers, number of dishwashers, number of electric water heaters, number of electric stoves, number of electric heaters, number of standalone refrigerators, TV size, whether there is a desktop computer, laptop and game console), and energy attitude (can change behavior to save energy, can change behavior to protect the environment, have done a lot to save energy).

[0074] The extracted load features may include: (the following data is the power consumption in 30 minutes), peak-valley difference features (peak-valley difference from 0 am to 12 pm, peak-valley difference from 6 am to 11 pm, peak-valley difference from 8 am to 12 am, peak-valley difference from 2 pm to 9 pm, peak-valley difference rate from 0 am to 12 pm, peak-valley difference rate from 6 am to 11 pm, peak-valley difference rate from 14 pm to 21 pm), power load features (maximum load, minimum load, average load, load factor, minimum load factor), and variance features (maximum variance from 0 am to 12 pm, maximum variance from 5 pm to 7 pm, minimum variance from 0 am to 12 pm, minimum variance from 5 pm to 7 pm, average variance from 0 am to 12 pm).

[0075] The questionnaire features and load features can form a feature set.

[0076] Step 104: Classify users with the extracted questionnaire features and the load features as input values and the label as the output value to obtain the classified users, and determine the users corresponding to the preset label among the classified users as target users according to the preset number of target users.

[0077] Optionally, in this step, classifying users with the extracted questionnaire features and the load features as input values and the label as the output value to obtain the classified users may include:

[0078] Use the random forest method to perform dimensionality reduction processing on the extracted questionnaire features and the load features to obtain the features after dimensionality reduction processing;

[0079] Taking the extracted questionnaire features and the load features as input values and the label as the output value, classify users through a support vector classification model to obtain the classified users.

[0080] The outputs are label 1 and label 2, namely high-potential users and low-potential users.

[0081] Here, the extracted questionnaire features and load features in the feature set can be divided into a training set and a test set to train the support vector classification model. The training set is used to train the model, and the test set is used by users to test the trained model to see if the accuracy and reliability meet the preset requirements.

[0082] In this step, when the preset target user quantity is greater than the quantity of high-potential users corresponding to label 1, the target users are all the users corresponding to label 1 and some of the users corresponding to label 2; when the preset target user quantity is less than or equal to the quantity of high-potential users corresponding to label 1, then the target users are the users corresponding to label 1.

[0083] As Figure 2 shown, to verify the effectiveness of the method of the present invention, taking the classification accuracy as the standard, verify the reduction amount and reduction percentage obtained by selecting users in two ways respectively. In this experiment, the number of users after obtaining the monthly load demand response reduction amount and removing outliers is set to 1,299 households. According to the 7:3 principle, the features and class labels of 900 households are used as the training set, and the features of the remaining 399 households are used as the test set. Compare the predicted label obtained by using the support vector classification model with the actual label to obtain the classification accuracy. Finally, the prediction accuracy of the support vector classification model for binary classification is 81.666%. The two selection methods are randomly selecting users and preferentially selecting high-potential users with label 1 according to the user label. If the number of high-potential users is less than the total number of users required to be selected, then select low-potential users with label 2. In this experiment, 50 users are selected for verification under method 1 (random selection) and method 2 (the method for identifying high-demand response potential users provided by the present invention), and the reduction amount and reduction percentage results are as Figure 2 shown.

[0084] As Figure 2 shown, the diagonal line represents method 1, and the horizontal line represents method 2. The total reduction amount obtained according to method 2 is 1,202.86 kWh, and the reduction percentage is 3.22%. The total reduction amount obtained according to method 1 is 1,006.96 kWh, and the reduction percentage is 2.24%. Thus, it shows that the user identification method proposed according to the present invention can achieve more load reduction during peak hours and can provide technical support for aggregators to effectively identify high-potential users in advance.

[0085] The above method for identifying users with high demand response potential collects the load data of users before and after load demand response in existing time-of-use electricity price pilot projects; classifies users according to the load data and assigns different labels to different categories of users; extracts questionnaire features and load features respectively based on user questionnaires and load data; classifies users with the extracted questionnaire features and load features as input values and the labels as output values to obtain the classified users, and determines the users corresponding to the preset labels among the classified users as target users according to the preset number of target users. This application constructs a feature set by combining questionnaire features and load features, and uses the random forest algorithm to extract features highly correlated with the reduction amount, so as to identify users with high response potential and suitable for participating in time-of-use electricity prices, provide theoretical support for load aggregators to select high-quality demand response resources, and reduce the risks of load demand response projects.

[0086] It should be understood that the magnitudes of the sequence numbers of the steps in the above embodiments do not mean the order of execution is prior or posterior. The execution order of each process should be determined according to its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.

[0087] The following is an embodiment of the device of the present invention. For the details not described in detail therein, reference may be made to the corresponding method embodiment above.

[0088] Figure 3 The structural schematic diagram of the device for identifying users with high demand response potential provided by the embodiment of the present invention is shown. For the convenience of description, only the parts related to the embodiment of the present invention are shown and are described in detail as follows:

[0089] As Figure 3 shown, the device 3 for identifying users with high demand response potential includes: a collection module 301, a calculation module 302, an extraction module 303, and a classification module 304.

[0090] The collection module 301 is used to collect the load data of users before and after load demand response in existing time-of-use electricity price pilot projects;

[0091] The calculation module 302 is used to classify the users according to the load data and assign different labels to different categories of users;

[0092] The extraction module 303 is used to extract questionnaire features and load features respectively based on user questionnaires and the load data;

[0093] The classification module 304 is used to classify users with the extracted questionnaire features and the load features as input values and the labels as output values to obtain the classified users, and determine the users corresponding to the preset labels among the classified users as target users according to the preset number of target users.

[0094] In a possible implementation, when the computing module 302 classifies the users according to the load data and assigns different labels to different categories of users, it can be used for:

[0095] Calculate the monthly load demand response reduction amount for each user according to the load data;

[0096] Classify the users according to the monthly load demand response reduction amount, assign different labels to different categories of users, and determine the labels corresponding to each user.

[0097] In a possible implementation, when the computing module 302 calculates the monthly load demand response reduction amount for each user according to the load data, it can be used for:

[0098] Perform weekly matching based on the weather characteristics before and after the load demand response to determine the Mth week before the load demand response and the Kth week after the load demand response with similar weather characteristics;

[0099] Calculate the peak period response reduction amount for each user in the Mth week corresponding to the load demand response according to the load data corresponding to the Mth week and the load data corresponding to the Kth week;

[0100] Calculate the average load reduction amount for the control group users of each user in the Mth week corresponding to the load demand response according to the load data of the control group users of each user before the load demand response;

[0101] Calculate the load demand response reduction amount for each user in the Mth week according to the peak period response reduction amount and the average load reduction amount;

[0102] Calculate the monthly load demand response reduction amount for each user according to the above method of calculating the load demand response reduction amount for each user in the Mth week.

[0103] In a possible implementation, when the computing module 302 calculates the peak period response reduction amount for each user in the Mth week corresponding to the load demand response according to the load data corresponding to the Mth week and the load data corresponding to the Kth week, it can be used for:

[0104] According to Calculate the peak period response reduction amount for user i in the Mth week corresponding to the load demand response;

[0105] Wherein, represents the peak period response reduction amount for user i in the Mth week due to the influence of the load demand response; represents the peak period load data of user i in the Kth week, Indicates the load data of user i during the peak period in the Mth week.

[0106] In a possible implementation, when the calculation module 302 calculates the corresponding load average reduction amount of the control group users of each user in the Mth week according to the load data of the control group users of each user before the load demand response, it can be used for:

[0107] According to Calculate the corresponding load average reduction amount of the control group users of user i in the Mth week;

[0108] Wherein, Indicates the corresponding load average reduction amount of the control group users of user i in the Mth week, Indicates the number of elements of the control group users of user i, Indicates the corresponding load reduction amount of the jth element in the control group users of user i in the Mth week.

[0109] In a possible implementation, when the calculation module 302 calculates the monthly load demand response reduction amount of each user according to the peak period response reduction amount and the load average reduction amount, it can be used for:

[0110] Calculate the difference between the reduction amount matrix corresponding to the peak period response reduction amount and the reduction amount matrix corresponding to the load average reduction amount, and use the difference as the monthly load demand response reduction amount of the corresponding user.

[0111] In a possible implementation, when the classification module 304 classifies users with the extracted questionnaire features and the load features as input values and the label as the output value to obtain the classified users, it can be used for:

[0112] Adopt the random forest method to perform dimensionality reduction processing on the extracted questionnaire features and the load features to obtain the features after dimensionality reduction processing;

[0113] Use the extracted questionnaire features and the load features as input values and the label as the output value, and classify users through a support vector classification model to obtain the classified users.

[0114] The above-mentioned identification device for users with high demand response potential collects the load data of users before and after load demand response in existing time-of-use electricity price pilot projects through a collection module; a calculation module classifies users based on the load data and assigns different labels to different categories of users; an extraction module extracts questionnaire features and load features respectively according to user questionnaires and load data; a classification module classifies users with the extracted questionnaire features and load features as input values and labels as output values, obtains the classified users, and determines the users corresponding to the preset labels among the classified users as target users according to the preset number of target users. This application constructs a feature set by combining questionnaire features and load features, and uses the random forest algorithm to extract features highly correlated with the reduction amount, so as to identify users with high response potential and suitable for participating in time-of-use electricity prices, provide theoretical support for load aggregators to select high-quality demand response resources, and reduce the risk of load demand response projects.

[0115] Figure 4 It is a schematic diagram of the terminal device provided by an embodiment of the present invention. As Figure 4 shown, the terminal device 4 of this embodiment includes: a processor 40, a memory 41, and a computer program 42 stored in the memory 41 and executable on the processor 40. When the processor 40 executes the computer program 42, the steps in the above-mentioned embodiments of the identification method for users with high demand response potential are implemented, such as Figure 1 the steps 101 to 104 shown. Alternatively, when the processor 40 executes the computer program 42, the functions of each module / unit in the above-mentioned device embodiments are implemented, such as Figure 3 the functions of the modules / units 301 to 304 shown.

[0116] Exemplarily, the computer program 42 can be divided into one or more modules / units. The one or more modules / units are stored in the memory 41 and executed by the processor 40 to complete the present invention. The one or more modules / units can be a series of computer program instruction segments capable of performing specific functions, and these instruction segments are used to describe the execution process of the computer program 42 in the terminal device 4. For example, the computer program 42 can be divided into Figure 3 the modules / units 301 to 304 shown.

[0117] The terminal device 4 can be a computing device such as a desktop computer, a notebook, a palm computer, and a cloud server. The terminal device 4 may include, but is not limited to, a processor 40 and a memory 41. Those skilled in the art can understand, Figure 4This is only an example of the terminal device 4, which does not constitute a limitation on the terminal device 4. It may include more or fewer components than those shown in the figure, or combine certain components, or different components. For example, the terminal device may also include input / output devices, network access devices, buses, etc.

[0118] The so-called processor 40 may be a central processing unit (CPU), or may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0119] The memory 41 may be an internal storage unit of the terminal device 4, such as the hard disk or memory of the terminal device 4. The memory 41 may also be an external storage device of the terminal device 4, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the terminal device 4. Further, the memory 41 may also include both an internal storage unit and an external storage device of the terminal device 4. The memory 41 is used to store the computer program and other programs and data required by the terminal device. The memory 41 may also be used to temporarily store data that has been output or is to be output.

[0120] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above functional units and modules is used as an example. In actual applications, the above functions can be assigned to different functional units and modules according to needs, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment can be integrated into a processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above integrated unit can be implemented in the form of hardware or in the form of a software functional unit. In addition, the specific names of the functional units and modules are only for the convenience of mutual distinction and do not limit the protection scope of this application. The specific working processes of the units and modules in the above system can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0121] In the above embodiments, the descriptions of the respective embodiments have their own emphases. For the parts not detailed or recorded in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0122] Those of ordinary skill in the art can realize that the units and algorithm steps of the examples described in conjunction with the embodiments disclosed herein can be implemented by electronic hardware, or by a combination of computer software and electronic hardware. Whether these functions are executed in the form of hardware or software depends on the specific application and design constraints of the technical solution. A professional technician can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0123] In the embodiments provided by the present invention, it should be understood that the disclosed device / terminal device and method can be implemented in other ways. For example, the device / terminal device embodiments described above are merely illustrative. For example, the division of the modules or units is only a logical function division, and there can be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection between each other can be through some interfaces. The indirect coupling or communication connection of the device or unit can be in an electrical, mechanical or other form.

[0124] The unit described as a separate component may or may not be physically separated, and the component displayed as a unit may or may not be a physical unit, that is, it may be located in one place, or may be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0125] In addition, in each embodiment of the present invention, each functional unit can be integrated into a processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above integrated unit can be implemented in the form of hardware or in the form of a software functional unit.

[0126] If the integrated module / unit 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 such an understanding, to implement all or part of the processes in the above-described embodiment methods of the present invention, it can also be completed by a computer program instructing relevant hardware. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above-described embodiments of the method for identifying high-demand response potential users can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, an executable file, or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a mobile hard disk, a magnetic disk, an optical disc, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc. It should be noted that the content included in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable medium does not include electrical carrier signals and telecommunication signals.

[0127] The above-described 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 foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A method for identifying users with high demand response potential, characterized in that, Including: Collecting the load data of users before and after load demand response in existing time-of-use electricity price pilot projects; Perform weekly matching based on the weather characteristics before and after load demand response to determine the week before load demand response with similar weather characteristics, and the week after load demand response; According to the load data corresponding to the th week and the load data corresponding to the th week, calculate the peak period response reduction amount of each user due to the influence of load demand response in the th week; According to the load data of the control group users of each user before the load demand response, calculate the average load reduction amount of the control group users of each user corresponding to the week; wherein, the control group users are users with similar electricity consumption patterns to the current user when time-of-use electricity prices are not implemented. Determine the difference between the peak period response reduction amount and the average load reduction amount as the load demand response reduction amount of each user in the M nth week; Calculating the difference between the reduction matrix corresponding to the peak period response reduction and the reduction matrix corresponding to the average load reduction, and taking the difference as the monthly load demand response reduction of the corresponding user; Classifying the users according to the monthly load demand response reduction, assigning different labels to different categories of users, and determining the corresponding labels for each user; Extracting questionnaire features and load features respectively according to the user questionnaire and the load data; Classifying the users with the questionnaire features and the load features as input values and the label as the output value to obtain the classified users, and determining the users corresponding to the preset label among the classified users as target users according to the preset number of target users.

2. The method according to claim 1, characterized in that, The said according to the said weekly corresponding load data and the said weekly corresponding load data, calculate the peak period response reduction amount of each user due to the influence of load demand response in the weekly corresponding peak period, including: According to calculate the user During the peak period corresponding to the week, the response reduction amount due to the impact of load demand response; Among them, represents the peak period response reduction volume of the user in the week due to the impact of load demand response; represents the load data of the user in the peak period of the week, represents the load data of the user in the peak period of the week.

3. The method according to claim 1, characterized in that, Calculating the average load reduction amount corresponding to the control group users of each user in the week before the load demand response, including: According to calculate the average load reduction of the control group users corresponding to the user in the corresponding week; Among them, represents the average load reduction of the control group users of in the th week, represents the number of elements of the control group users of , represents the load reduction of the th element of the control group users of in the th week.

4. The method according to any one of claims 1 to 3, characterized in that The classifying the users with the questionnaire features and the load features as input values and the label as the output value to obtain the classified users includes: Performing dimensionality reduction processing on the questionnaire features and the load features by using the random forest method to obtain the features after dimensionality reduction processing; Classifying the users with the questionnaire features and the load features as input values and the label as the output value through a support vector classification model to obtain the classified users.

5. An identification device for users with high demand response potential, characterized in that, Including: A collection module for collecting the load data of users before and after load demand response in existing time-of-use electricity price pilot projects; A calculation module, configured to perform weekly matching based on weather characteristics before and after load demand response, to determine the week before load demand response with similar weather characteristics, and the week after load demand response; according to the load data corresponding to the week and the load data corresponding to the week, calculate the peak period response reduction amount of each user due to the influence of load demand response in the week; according to the load data of the control group users of each user before load demand response, calculate the average load reduction amount of the control group users of each user in the week; wherein, the control group users are users with electricity consumption patterns similar to those of the current user when time-of-use electricity prices are not implemented; determine the difference between the peak period response reduction amount and the average load reduction amount as the load demand response reduction amount of each user in the M week; calculate the difference between the reduction amount matrix corresponding to the peak period response reduction amount and the reduction amount matrix corresponding to the average load reduction amount, and use the difference as the monthly load demand response reduction amount of the corresponding user; classify the users according to the monthly load demand response reduction amount, and assign different labels to different categories of users to determine the labels corresponding to each user; An extraction module for extracting questionnaire features and load features respectively according to the user questionnaire and the load data; A classification module for classifying the users with the questionnaire features and the load features as input values and the label as the output value to obtain the classified users, and determining the users corresponding to the preset label among the classified users as target users according to the preset number of target users.

6. A terminal, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, the steps of the method according to any one of claims 1 to 4 above are implemented.

7. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, the steps of the method according to any one of claims 1 to 4 above are implemented.

Images