Residential charging facility load identification method and system, electronic equipment and storage medium

Abstract

The invention discloses a residential charging facility load identification method and system, electronic equipment and a storage medium, and the method comprises the steps: firstly collecting a historical daily power utilization characteristic data sequence and a historical charging state data sequence of each residential charging facility; through calculation and analysis of correlation between a historical daily power utilization characteristic data sequence and a historical charging state data sequence, a deep association relationship between power utilization characteristic data and charging state data of different charging facilities can be mined. Taking the correlation sequence as a feature vector, adding a label according to the type of the residential charging facility, constructing to obtain a training data set corresponding to each type of residential charging facility, training the support vector machine model by using the training data set to obtain a load identification model, and finally identifying the load of the residential charging facility according to the load identification model. Real-time load identification can be carried out after the real-time power utilization characteristic data and the real-time charging state data of the charging facility to be identified are collected and the characteristics are extracted, so that the accuracy of load identification is greatly improved.

Description

Technical Field

[0001] The present invention relates to the technical field of load identification, and in particular, to a method and system for identifying the load of a residential charging facility, an electronic device, and a computer-readable storage medium. Background Art

[0002] With the rapid construction of charging facilities, the abnormal status monitoring and safety management of residential charging facilities have become a key problem restricting the development of electric vehicles. How to analyze the charging load characteristics of charging facilities to accurately determine the type of charging facilities, so as to realize the intelligent identification of residential charging facilities, has become an urgent problem to be solved. At present, the load identification methods of charging facilities mainly include optimization algorithms and pattern recognition algorithms. Among them, with the increase of load types in the feature library, the optimization algorithm is difficult to meet the requirements of accuracy and real-time performance; and the existing pattern recognition algorithm usually includes steps such as data collection, data preprocessing, feature extraction, model training and load identification. The process is relatively complicated, and the existing pattern recognition algorithm simply uses time domain features and frequency domain features for model training, lacks analysis of the correlation between data, and makes the accuracy of load identification low. Summary of the invention

[0003] The present invention provides a method and system for identifying the load of residential charging facilities, an electronic device, and a computer-readable storage medium, which can mine the deep correlation between the power consumption characteristic data of different charging facilities and their charging status data, greatly improving the accuracy of load identification.

[0004] According to one aspect of the present invention, a method for identifying a residential charging facility load is provided, comprising the following contents:

[0005] Obtain historical daily power characteristics data and historical charging status data of different types of residential charging facilities, and construct a historical daily power characteristics data sequence and a historical charging status data sequence for each type of residential charging facility;

[0006] Calculate the correlation between the historical daily power consumption characteristic data series and the historical charging status data series of each residential charging facility to obtain the correlation series of each residential charging facility at each moment;

[0007] The correlation series is used as a feature vector and labels are added according to the type of residential charging facilities to construct a training data set corresponding to each type of residential charging facility;

[0008] Construct a support vector machine model, and use the training data set to train the support vector machine model to obtain a load identification model;

[0009] The real-time daily power characteristic data sequence and the real-time charging status data sequence of the residential charging facilities to be identified are collected, and their correlation series are calculated, and the correlation series is input into the load identification model for load identification.

[0010] Furthermore, the process of calculating the correlation between the historical daily power consumption characteristic data series and the historical charging state data series of each residential charging facility to obtain the correlation series of each residential charging facility at each moment includes the following:

[0011] Dimensionless processing of historical daily electrical characteristic data series;

[0012] Calculate the monomer correlation between each historical daily power characteristic data and the historical charging state data at each moment after dimensionless processing;

[0013] Based on the correlation of all monomers, the overall correlation of the historical daily power characteristic data and the historical charging state data at each moment is calculated;

[0014] Based on the individual correlation and overall correlation at each moment, a correlation series of each type of residential charging facility at each moment is constructed.

[0015] Furthermore, the monomer correlation is calculated based on the following formula:

[0016]

[0017] Among them, ρ(x i (m),y(m)) represents the monomer correlation between the i-th historical daily electrical characteristic data and the charging state data at the m-th moment, Δ m x i y=|x i (m)-y(m)|, which represents the absolute difference between the i-th historical daily electrical characteristic data and the charging state data at the m-th moment, Δmin i and Δmax i They respectively represent the minimum and maximum values ​​of the absolute difference between the i-th historical daily electrical characteristic data and the charging state data at all times, and ξ represents the adjustment coefficient.

[0018] Furthermore, the overall correlation is calculated based on the following formula:

[0019]

[0020] Among them, γ m (x, y) represents the overall correlation between the historical daily power characteristic data and the historical charging state data at the mth moment, and n represents the number of historical daily power characteristic data.

[0021] Furthermore, the number of support vector machine models is consistent with the number of types of residential charging facilities, and each support vector machine model is trained separately using the corresponding training data set to obtain a load identification model corresponding to each type of residential charging facility.

[0022] Furthermore, the daily power characteristic data of the residential charging facilities include at least one of the charging voltage, charging current, charging active power, charging reactive power, charging start time, daily charging times, total charging amount and daily charging time.

[0023] Furthermore, residential charging facilities include battery vehicles, electric vehicles and household energy storage.

[0024] In addition, the present invention also provides a residential charging facility load identification system, comprising:

[0025] A historical data collection module is used to obtain historical daily power characteristics data and historical charging status data of different types of residential charging facilities, and construct a historical daily power characteristics data sequence and a historical charging status data sequence for each type of residential charging facility;

[0026] A sequence correlation calculation module is used to calculate the correlation between the historical daily power consumption characteristic data sequence and the historical charging state data sequence of each residential charging facility, and obtain the correlation sequence of each residential charging facility at each moment;

[0027] A training data set construction module is used to use the correlation series as a feature vector and add labels according to the types of residential charging facilities to construct a training data set corresponding to each type of residential charging facility;

[0028] The model building and training module is used to build a support vector machine model and train the support vector machine model using a training data set to obtain a load identification model;

[0029] The real-time load identification module is used to collect the real-time daily power characteristic data sequence and the real-time charging status data sequence of the residential charging facilities to be identified, calculate their correlation series, and input the correlation series into the load identification model for load identification.

[0030] In addition, the present invention also provides an electronic device, including a processor and a memory, wherein the memory stores a computer program, and the processor executes the steps of the above method by calling the computer program stored in the memory.

[0031] In addition, the present invention also provides a computer-readable storage medium for storing a computer program for identifying the load of residential charging facilities, wherein the computer program executes the steps of the method described above when running on a computer.

[0032] The present invention has the following beneficial effects:

[0033] The method for identifying the load of residential charging facilities of the present invention first collects historical daily power characteristic data and historical charging status data of different types of charging facilities to construct a historical daily power characteristic data sequence and a historical charging status data sequence for each type of residential charging facility; then, the correlation between the historical daily power characteristic data sequence and the historical charging status data sequence of each type of residential charging facility is calculated to obtain a correlation series of each type of residential charging facility at each moment, and by calculating and analyzing the correlation between the historical daily power characteristic data sequence and the historical charging status data sequence, the deep-level correlation between the power characteristic data of different charging facilities and their charging status data can be mined; then, the correlation series is used as a feature vector and a label is added according to the type of residential charging facility to construct a training data set corresponding to each type of residential charging facility, and the support vector machine model is trained using the training data set to obtain a load identification model; finally, real-time load identification can be performed after collecting the real-time power characteristic data and real-time charging status data of the charging facility to be identified and extracting features, thereby greatly improving the accuracy of load identification.

[0034] In addition, the residential charging facility load identification system of the present invention also has the above advantages.

[0035] In addition to the above-described purposes, features and advantages, the present invention has other purposes, features and advantages. The present invention will be further described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] The drawings constituting a part of this 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:

[0037] Figure 1 It is a flowchart of a method for identifying a load of a residential charging facility according to a preferred embodiment of the present application;

[0038] Figure 2 yes Figure 1 Schematic diagram of the sub-process of step S2;

[0039] Figure 3 It is a schematic diagram of the module structure of a residential charging facility load identification system according to another embodiment of the present application. DETAILED DESCRIPTION

[0040] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0041] Reference Figure 1 The preferred embodiment of the present application provides a method for identifying the load of a residential charging facility, comprising the following contents:

[0042] Step S1: Acquire historical daily power characteristics data and historical charging status data of different types of residential charging facilities, and construct a historical daily power characteristics data sequence and a historical charging status data sequence for each type of residential charging facility;

[0043] Step S2: Calculate the correlation between the historical daily power consumption characteristic data series and the historical charging state data series of each residential charging facility to obtain the correlation series of each residential charging facility at each moment;

[0044] Step S3: taking the correlation series as a feature vector and adding labels according to the types of residential charging facilities, thereby constructing a training data set corresponding to each type of residential charging facility;

[0045] Step S4: construct a support vector machine model, and use the training data set to train the support vector machine model to obtain a load identification model;

[0046] Step S5: Collect the real-time daily power characteristic data sequence and the real-time charging status data sequence of the residential charging facilities to be identified, calculate their correlation series, and input the correlation series into the load identification model for load identification.

[0047] It can be understood that the load identification method for residential charging facilities of the present embodiment first collects historical daily power characteristics data and historical charging status data of different types of charging facilities to construct a historical daily power characteristics data sequence and a historical charging status data sequence for each type of residential charging facility; then, the correlation between the historical daily power characteristics data sequence and the historical charging status data sequence for each type of residential charging facility is calculated to obtain a correlation series for each type of residential charging facility at each moment; by calculating and analyzing the correlation between the historical daily power characteristics data sequence and the historical charging status data sequence, the deep correlation between the power characteristics data of different charging facilities and their charging status data can be mined; then, the correlation series is used as a feature vector and labels are added according to the type of residential charging facilities to construct a training data set corresponding to each type of residential charging facility, and the support vector machine model is trained using the training data set to obtain a load identification model; finally, real-time load identification can be performed after collecting the real-time power characteristics data and real-time charging status data of the charging facility to be identified and extracting features, which greatly improves the accuracy of load identification.

[0048] It can be understood that in step S1, the historical daily power characteristics data and historical charging status data of different charging facilities in the residential power usage scenario are collected, so that the historical daily power characteristics data sequence {X} and the historical charging status data sequence {Y} of each residential charging facility can be constructed, and the data collection frequency can be collected at the minute level or the hour level. Among them, residential charging facilities include battery vehicles, electric vehicles and household energy storage. Of course, in other embodiments of the present invention, they can also include common household electrical appliances such as refrigerators, air conditioners, and televisions. No specific limitation is made here. The present invention uses battery vehicles, electric vehicles and household energy storage as residential charging facilities for exemplary description. Optionally, the daily electrical characteristic data of residential charging facilities include at least one of charging voltage, charging current, charging active power, charging reactive power, charging start time, daily charging times, total charging amount and daily charging duration. Preferably, the present invention uses these eight types of electrical data as daily electrical characteristic data at the same time, which can more comprehensively characterize the charging characteristics of each charging facility. In addition, the charging voltage, charging current, charging active power and charging reactive power are instantaneous values, while the charging start time, daily charging times, total charging amount and daily charging duration are cumulative values. In addition, the historical charging status data includes eight types of status data, namely, the starting charging state, the normal charging state, the fast charging state, the slow charging state, the charging completion state, the charging fault state, the artificial interruption charging state and the illegal charging state. For example, the historical daily electrical characteristic data at each moment can be expressed as: X = {x1, x2, x3, x4, x5, x6, x7, x8}, and the historical charging status data sequence at each moment can be expressed as Y = {y j},y j ∈{y1, y2, y3, y4, y5, y6, y7, y8}, x1, x2, x3, x4, x5, x6, x7 and x8 represent charging voltage, charging current, charging active power, charging reactive power, starting charging time, daily charging times, total charging capacity and daily charging time respectively, y1, y2, y3, y4, y5, y6, y7 and y8 represent starting charging state data value, normal charging state data value, fast charging state data value, slow charging state data value, charging completion state data value, charging fault state data value, artificial interruption charging state data value and illegal charging state data value respectively, wherein different charging state data values ​​can be preset with different values ​​according to actual needs, for example, in a specific embodiment of the present invention, let y1=100, y2=80, y3=120, y4=40, y5=20, y6=0, y7=-20, y8=-40.

[0049] Optionally, after collecting historical data, the data may be standardized, such as cleaning the data, removing noise and outliers, and normalizing the data.

[0050] It is understandable that Figure 2 As shown, in step S2, the process of calculating the correlation between the historical daily power consumption characteristic data series and the historical charging state data series of each residential charging facility to obtain the correlation series of each residential charging facility at each moment includes the following:

[0051] Step S21: performing dimensionless processing on the historical daily electrical characteristic data series;

[0052] Step S22: Calculate the monomer correlation between each historical daily power characteristic data and the historical charging state data at each moment after dimensionless processing;

[0053] Step S23: Calculate the overall correlation between the historical daily power characteristic data and the historical charging state data at each moment based on the correlation of all monomers;

[0054] Step S24: Based on the individual correlation and overall correlation at each moment, a correlation series of each type of residential charging facility at each moment is constructed.

[0055] Specifically, since the dimensions of different daily power characteristic data are different, in order to facilitate subsequent calculations, the historical daily power characteristic data series is first dimensionally processed. For example, assuming that the historical daily power characteristic data collected at a certain moment is X = {220V, 10A, 2.2kW, 0.5kvar, 8:00, 2, 20kWh, 2 hours}, then the dimensionless processing process of the charging voltage x1 is: 220V / 1V = 220; the dimensionless processing process of the charging current x2 is: 10A / 0.1A = 100; the dimensionless processing process of the charging active power x3 is: 2.2kW / 10W = 22 0; the dimensionless processing process of charging reactive power x4 is: 0.5kvar / 10kvar=50; the dimensionless processing process of starting charging time x5 is: 8 / 0.1=80; the dimensionless processing process of daily charging times x6 is: 2 / 0.01=200; the dimensionless processing process of total charging capacity x7 is: 20kWh / 100W=200; the dimensionless processing process of daily charging time x8 is: 2h / 0.05h=40.

[0056] Then, the monomer correlation between each historical daily power characteristic data and the historical charging state data at each moment after dimensionless processing is calculated based on the following formula:

[0057]

[0058] Among them, ρ(x i (m),y(m)) represents the monomer correlation between the i-th historical daily electrical characteristic data and the charging state data at the m-th moment, Δ m xi y=|x i (m)-y(m)|, which represents the absolute difference between the i-th historical daily electrical characteristic data and the charging state data at the m-th moment, Δmin i and Δmax i They respectively represent the minimum and maximum values ​​of the absolute difference between the i-th historical daily electrical characteristic data and the charging status data at all times; ξ represents the adjustment coefficient, which can be set according to actual needs and is generally set to 0.5.

[0059] After calculating the individual correlations of the eight historical daily electrical characteristic data and the charging state data at the same time, the overall correlation of the historical daily electrical characteristic data and the historical charging state data at the same time is calculated based on the following formula:

[0060]

[0061] Among them, γ m (x, y) represents the overall correlation between the historical daily power characteristic data and the historical charging state data at the mth moment, and n represents the number of historical daily power characteristic data.

[0062] Finally, based on the eight individual correlations and one overall correlation at the same time, the correlation series of the historical daily power characteristics data series and the historical charging status data series at that time can be constructed, that is, the correlation series of each residential charging facility at each time, which can be expressed as:

[0063]

[0064] In order to better illustrate the above correlation calculation process, the present invention is explained by the following example: Assume that the data of a certain charging facility collected between 8:00 and 15:00 is dimensionlessly processed as shown in Table 1.

[0065] Table 1. Data collected after dimensionless processing of a charging facility

[0066]

[0067] For the charging voltage data x1 collected at 8:00, it can be seen that Δmin1 = 80, Δmax1 = 280, and ξ = 0.5, so the monomer correlation between the charging voltage and the charging status data at 8:00 can be calculated. Among them, m is 1, indicating the first collection time. Similarly, the monomer correlations of the remaining historical daily electrical characteristic data and charging status data at 8:00 can be calculated as follows: ρ(x2(1), y(1)) = 1, ρ(x3(1), y(1)) = 1.34, ρ(x4(1), y(1)) = 0.51, ρ(x5(1), y(1)) = 0.81, ρ(x6(1), y(1)) = 1.32, ρ(x7(1), y(1)) = 1.32, ρ(x8(1), y(1)) = 0.4.

[0068] Therefore, it can be calculated that The overall correlation between the historical daily power characteristics data and the historical charging status data at 8:00 can be calculated. Then the correlation series of this type of charging facility at 8:00 is: {1.34, 1, 1.34, 0.51, 0.81, 1.32, 1.32, 0.4, 0.0155}. Based on the same principle, the correlation series of this type of charging facility at other collection times can be calculated.

[0069] It can be understood that in step S3, the correlation series of each type of residential charging facility is used as a feature vector and a label is added according to the type of residential charging facility, so that a training data set corresponding to each type of residential charging facility can be constructed. For example, in the present invention, training data sets for electric vehicles, battery vehicles, and household energy storage can be constructed separately.

[0070] It can be understood that in step S4, the support vector machine model is used as the basic model of the load identification model, and the optimal classification hyperplane equation of the support vector machine model can be expressed as: Among them, λ represents the input sample, that is, the feature vector in step S3, that is, the correlation series, w represents the weight vector, and each component ω in the feature vector w i Corresponding to the i-th feature in the input sample, represents the bias, which represents the model's initial judgment of the load type even without feature input, and the superscript T represents transposition. The objective function of the support vector machine model can be expressed as:

[0071]

[0072] Among them, i represents the relaxation constant, ζ i ≥0, C represents the penalty factor, μ i Represents the corresponding category label. The process of solving the objective function is roughly as follows:

[0073] 1) Construct Lagrangian function:

[0074]

[0075] Among them, α i Represents the constructed Lagrange multiplier, which, in the above formula, must satisfy:

[0076] α i ≥0;

[0077] 1-ξ i -μ i (w T λ i +b)≥0;

[0078] α i [1-ξ i -μ i (w T λ i + b)] = 0;

[0079] 2) Convert the Lagrangian function into a dual problem, specifically, find the partial derivatives of w and b, and then substitute them into the Lagrangian function to obtain the objective function of the dual problem, which is expressed as follows:

[0080]

[0081] 3) Use the quadratic programming solver to find all α i Sample points > 0;

[0082] 4) Construct a classification model for load identification. The classification model constructed is as follows:

[0083]

[0084] Among them, α i is the Lagrange multiplier obtained in sample training, K(λ i ,λ) is the kernel function. Taking the identification of electric vehicles as an example, when f(x) = 1, it means that the identified sample is an electric vehicle, and when f(x) = 0 or -1, it means that it is not an electric vehicle.

[0085] Optionally, the number of support vector machine models is consistent with the number of types of residential charging facilities, and each support vector machine model is trained separately using the corresponding training data set to obtain a load identification model corresponding to each type of residential charging facility. For example, assuming that it is necessary to identify three types of charging facilities: battery vehicles, electric vehicles, and household energy storage, three support vector machine models are constructed, that is, three hyperplanes and three kernel functions are constructed. It is assumed that the first hyperplane sets the battery vehicle as a positive sample and the rest as negative samples, the second hyperplane sets the electric vehicle as a positive sample and the rest as negative samples, and the third hyperplane sets the household energy storage as a positive sample and the rest as negative samples. After the samples are input, they can be judged in sequence to achieve classification. Subsequently, three load identification models are used for classification and identification, which is conducive to further improving the accuracy of load identification.

[0086] It can be understood that in the step S5, in the real-time load identification stage, the bilateral cumulative and event detection algorithm based on the sliding window is first used to perform event detection. After the charging event is detected, the real-time daily power characteristic data sequence and the real-time charging status data sequence of the residential charging facilities to be identified are collected, and after standardization and dimensionless processing, the correlation series is calculated, and then the correlation series is input into the load identification model, and real-time load identification can be performed. Among them, the bilateral cumulative and event detection algorithm based on the sliding window belongs to the existing algorithm and will not be repeated here. The correlation series calculation process is the same as the above step S2 and will not be repeated here. Optionally, after the load identification model of each charging facility is constructed, the correlation series can be simultaneously input into multiple load identification models, which is conducive to improving the accuracy of load identification.

[0087] In addition, if Figure 3 As shown, another embodiment of the present invention further provides a residential charging facility load identification system, preferably using the load identification method as described above, the system comprising:

[0088] A historical data collection module is used to obtain historical daily power characteristics data and historical charging status data of different types of residential charging facilities, and construct a historical daily power characteristics data sequence and a historical charging status data sequence for each type of residential charging facility;

[0089] A sequence correlation calculation module is used to calculate the correlation between the historical daily power consumption characteristic data sequence and the historical charging state data sequence of each residential charging facility, and obtain the correlation sequence of each residential charging facility at each moment;

[0090] A training data set construction module is used to use the correlation series as a feature vector and add labels according to the types of residential charging facilities to construct a training data set corresponding to each type of residential charging facility;

[0091] The model building and training module is used to build a support vector machine model and train the support vector machine model using a training data set to obtain a load identification model;

[0092] The real-time load identification module is used to collect the real-time daily power characteristic data sequence and the real-time charging status data sequence of the residential charging facilities to be identified, calculate their correlation series, and input the correlation series into the load identification model for load identification.

[0093] It can be understood that the residential charging facility load identification system of the present embodiment first collects historical daily power characteristics data and historical charging status data of different types of charging facilities to construct a historical daily power characteristics data sequence and a historical charging status data sequence for each residential charging facility; then, the correlation between the historical daily power characteristics data sequence and the historical charging status data sequence of each residential charging facility is calculated to obtain a correlation series for each residential charging facility at each moment; by calculating and analyzing the correlation between the historical daily power characteristics data sequence and the historical charging status data sequence, the deep correlation between the power characteristics data of different charging facilities and their charging status data can be mined; then, the correlation series is used as a feature vector and labels are added according to the type of residential charging facilities to construct a training data set corresponding to each residential charging facility, and the support vector machine model is trained using the training data set to obtain a load identification model; finally, real-time load identification can be performed after collecting the real-time power characteristics data and real-time charging status data of the charging facility to be identified and extracting features, which greatly improves the accuracy of load identification.

[0094] In addition, another embodiment of the present invention further provides an electronic device, including a processor and a memory, wherein the memory stores a computer program, and the processor executes the steps of the above method by calling the computer program stored in the memory.

[0095] In addition, another embodiment of the present invention further provides a computer-readable storage medium for storing a computer program for identifying the load of residential charging facilities, wherein the computer program executes the steps of the method described above when running on a computer.

[0096] The general form of computer readable storage media includes: floppy disk, flexible disk, hard disk, magnetic tape, any other magnetic medium, CD-ROM, any other optical medium, punch cards, paper tape, any other physical medium with a pattern of holes, random access memory (RAM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), flash erasable programmable read-only memory (FLASH-EPROM), any other memory chip or cartridge, or any other medium that can be read by a computer. The instructions can further be transmitted or received by a transmission medium. The term transmission medium can include any tangible or intangible medium that can be used to store, encode or carry instructions for execution by a machine, and includes digital or analog communication signals or other intangible media that facilitate the communication of the above instructions. Transmission media include coaxial cables, copper wires and optical fibers, which include the wires of a bus used to transmit a computer data signal.

[0097] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of complete hardware embodiments, complete software embodiments, or embodiments in combination with software and hardware. Moreover, the present application can adopt 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.) that contain computer-usable program code. The scheme in the embodiments of the present application can be implemented in various computer languages, for example, object-oriented programming language Java and literal scripting language JavaScript, etc.

[0098] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes 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 generate 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.

[0099] 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.

[0100] 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.

[0101] Although the preferred embodiments of the present application have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0102] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

[0103] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for identifying load of residential charging facilities, characterized in that: Includes the following: Obtain historical daily power characteristics data and historical charging status data of different types of residential charging facilities, and construct a historical daily power characteristics data sequence and a historical charging status data sequence for each type of residential charging facility; Calculate the correlation between the historical daily power consumption characteristic data series and the historical charging status data series of each residential charging facility to obtain the correlation series of each residential charging facility at each moment; The correlation series is used as a feature vector and labels are added according to the type of residential charging facilities to construct a training data set corresponding to each type of residential charging facility; Construct a support vector machine model, and use the training data set to train the support vector machine model to obtain a load identification model; The real-time daily power characteristic data sequence and the real-time charging status data sequence of the residential charging facilities to be identified are collected, and their correlation series are calculated, and the correlation series is input into the load identification model for load identification.

2. The method for identifying the load of residential charging facilities according to claim 1, characterized in that: The process of calculating the correlation between the historical daily power consumption characteristic data series and the historical charging state data series of each residential charging facility to obtain the correlation series of each residential charging facility at each moment includes the following: Dimensionless processing of historical daily electrical characteristic data series; Calculate the monomer correlation between each historical daily power characteristic data and the historical charging state data at each moment after dimensionless processing; Based on the correlation of all monomers, the overall correlation of the historical daily power characteristic data and the historical charging state data at each moment is calculated; Based on the individual correlation and overall correlation at each moment, a correlation series of each type of residential charging facility at each moment is constructed.

3. The method for identifying the load of residential charging facilities according to claim 2, characterized in that: The monomer correlation is calculated based on the following formula: Among them, ρ(x i (m),y(m)) represents the monomer correlation between the i-th historical daily electrical characteristic data and the charging state data at the m-th moment, Δ m x i y=|x i (m)-y(m)|, which represents the absolute difference between the i-th historical daily electrical characteristic data and the charging state data at the m-th moment, Δmin i and Δmax i They respectively represent the minimum and maximum values ​​of the absolute difference between the i-th historical daily electrical characteristic data and the charging state data at all times, and ξ represents the adjustment coefficient.

4. The method for identifying the load of residential charging facilities according to claim 3, characterized in that: The overall correlation is calculated based on the following formula: Among them, γ m (x, y) represents the overall correlation between the historical daily power characteristic data and the historical charging state data at the mth moment, and n represents the number of historical daily power characteristic data.

5. The method for identifying the load of residential charging facilities according to claim 1, characterized in that: The number of support vector machine models is consistent with the number of types of residential charging facilities, and each support vector machine model is trained separately using the corresponding training data set to obtain the load identification model corresponding to each type of residential charging facility.

6. The method for identifying the load of residential charging facilities according to claim 1, characterized in that: The daily power characteristic data of the residential charging facilities include at least one of the charging voltage, charging current, charging active power, charging reactive power, charging start time, daily charging times, total charging capacity and daily charging duration.

7. The method for identifying the load of residential charging facilities according to claim 1, characterized in that: Residential charging facilities include battery vehicles, electric vehicles and household energy storage.

8. A residential charging facility load identification system, characterized in that: include: A historical data collection module is used to obtain historical daily power characteristics data and historical charging status data of different types of residential charging facilities, and construct a historical daily power characteristics data sequence and a historical charging status data sequence for each type of residential charging facility; A sequence correlation calculation module is used to calculate the correlation between the historical daily power consumption characteristic data sequence and the historical charging state data sequence of each residential charging facility, and obtain the correlation sequence of each residential charging facility at each moment; A training data set construction module is used to use the correlation series as a feature vector and add labels according to the types of residential charging facilities to construct a training data set corresponding to each type of residential charging facility; The model building and training module is used to build a support vector machine model and obtain a load identification model after training the support vector machine model using a training data set; The real-time load identification module is used to collect the real-time daily power characteristic data sequence and the real-time charging status data sequence of the residential charging facilities to be identified, calculate their correlation series, and input the correlation series into the load identification model for load identification.

9. An electronic device, characterized in that: The method comprises a processor and a memory, wherein the memory stores a computer program, and the processor executes the steps of the method according to any one of claims 1 to 7 by calling the computer program stored in the memory.

10. A computer-readable storage medium for storing a computer program for identifying a residential charging facility load, characterized in that: When the computer program is run on a computer, the steps of the method according to any one of claims 1 to 7 are executed.

Images