Operation identification method and equipment for user-side energy storage device

Abstract

The invention relates to the technical field of energy management, and particularly provides an operation identification method and equipment for a user side energy storage device. The method comprises the following steps: acquiring original data of a target enterprise and a contrast enterprise; wherein the control enterprise is put into operation of the energy storage device. And performing data processing on the original data to obtain to-be-verified data of the target enterprise and annotation data of the contrast enterprise. And inputting the labeled data into a clustering algorithm, and outputting clustering results before and after the energy storage device is put into operation. And according to a clustering result, obtaining an identification threshold before and after the energy storage device is put into operation by the contrast enterprise. And identifying whether the target enterprise is put into operation of the energy storage device according to the identification threshold and the to-be-verified data. According to the method, the clustering algorithm is introduced to discover the internal structure characteristics of the data in an unsupervised manner, and support is provided for operation research of energy storage devices of enterprises. The limitation of data disclosure limitation on energy storage operation identification is overcome, the accuracy is good, and a basis is provided for energy management and optimal scheduling.

Description

Technical Field

[0001] The invention relates to the technical field of energy management, and in particular to an operation identification method and equipment for a user-side energy storage device. Background Art

[0002] In the power system, the rational use of energy storage devices plays a key role in the balance and stable operation of power loads. Energy storage devices can achieve peak load shaving and valley filling by storing and releasing power resources, thereby improving energy utilization.

[0003] User-side energy storage is divided into household energy storage and industrial and commercial energy storage according to different end users. Enterprises, as industrial and commercial users, are important entities of user-side energy storage. Industrial parks, communication base stations, shopping malls, hospitals and other users can achieve dynamic capacity expansion through the operation of energy storage devices.

[0004] Due to the limited available public data disclosed by corporate users, the operation status of corporate energy storage devices is hidden in the overall electricity consumption data and cannot be determined; the existing technology lacks accurate identification of the actual operation behavior of corporate user energy storage devices, which affects the optimal scheduling of energy and the comprehensive evaluation of energy storage benefits. Summary of the invention

[0005] The operation identification method and device of the user-side energy storage device provided by the embodiments of the present invention at least solve the problem that it is impossible to accurately identify whether the energy storage device is put into operation due to restrictions on data disclosure.

[0006] In a first aspect, the present invention provides an operation identification method for a user-side energy storage device, the method comprising: Obtaining original data of the target enterprise and the control enterprise; wherein the control enterprise has put the energy storage device into operation; Processing the original data to obtain the target enterprise's data to be verified and the reference enterprise's labeled data; Inputting the labeled data into a clustering algorithm, and outputting clustering results of the energy storage device before and after it is put into operation; Obtaining, according to the clustering result, the identification threshold before and after the control enterprise puts the energy storage device into operation; It is determined whether the target enterprise has put the energy storage device into operation according to the identification threshold and the data to be verified.

[0007] The operation identification method of the user-side energy storage device provided by the embodiment of the present invention obtains the original data of the target enterprise and the control enterprise, including: Obtaining the time when the reference enterprise puts the energy storage device into operation; Acquire first power consumption data of the reference enterprise; wherein the time period corresponding to the first power consumption data includes the time when the reference enterprise puts the energy storage device into operation; Acquire second electric power consumption data of the target enterprise; wherein the time period corresponding to the second electric power consumption data includes the target time to be identified.

[0008] The operation identification method of the user-side energy storage device provided by the embodiment of the present invention processes the original data to obtain the data to be verified of the target enterprise and the labeled data of the control enterprise, including: performing data cleaning on the first electric power data and the second electric power data; Using labels assigned before and after the energy storage device is put into operation, the cleaned result of the first power consumption data is annotated to obtain the annotated data; The cleaned result of the second electric power data is marked with labels before and after the target time to obtain the data to be verified.

[0009] The operation identification method of the user-side energy storage device provided by the embodiment of the present invention performs data cleaning on the first power consumption data and the second power consumption data, including: Merging the first electric power data into a first data file, and merging the second electric power data into a second data file; Detect and remove abnormal data in the first data file by using the quartile method, and detect and remove abnormal data in the second data file by using the quartile method; In the first data file, fill the data at the previous moment of the abnormal data into the position of the abnormal data; In the second data file, the data at a previous moment of the abnormal data is filled into the position of the abnormal data.

[0010] The operation identification method of the user-side energy storage device provided by the embodiment of the present invention inputs the labeled data into a clustering algorithm, and outputs the clustering results before and after the energy storage device is put into operation, including: Dividing the labeled data into a plurality of time series, and inputting the time series into a clustering algorithm; Initialize the cluster to which the time series belongs, and initialize the central time series of each cluster; Iteratively updating the clustering division of the time series; When the clustering is stable or the maximum number of iterations is reached, the clustering results of the energy storage device before and after it is put into operation are output.

[0011] The operation identification method of the user-side energy storage device provided by the embodiment of the present invention iteratively updates the clustering division of the time series, including: Calculate and update the central time series of the cluster according to the time series in each cluster under the current clustering division; Calculate the distance between each time series and each updated central time series; According to the distance calculation result, the time series is assigned to the cluster where the nearest central time series is located; The clustering division is updated according to the allocation result of the time series.

[0012] The operation identification method of the user-side energy storage device provided by the embodiment of the present invention calculates and updates the central time series of the cluster according to the time series in each cluster under the current cluster division, including: Multiplying the transpose of the time series matrix in the cluster by the time series matrix to obtain an autocorrelation matrix of the time series matrix; Obtaining a centering matrix according to the length of the time series; Multiplying the transpose of the centering matrix, the autocorrelation matrix, and the centering matrix to obtain a centered covariance matrix; Perform eigenvalue decomposition on the covariance matrix to obtain the maximum eigenvalue of the covariance matrix, and the eigenvector corresponding to the maximum eigenvalue is the updated central time series.

[0013] The operation identification method of the user-side energy storage device provided by the embodiment of the present invention calculates the distance between each time series and each updated central time series, including: Calculating a cross-correlation sequence between the time series and the updated central time series; performing normalization processing on the cross-correlation sequence; The maximum value of the mutual correlation is calculated, and the distance between the time series and the updated central time series is obtained according to the maximum value of the mutual correlation.

[0014] The operation identification method of the user-side energy storage device provided by the embodiment of the present invention obtains the identification threshold before and after the control enterprise puts the energy storage device into operation according to the clustering result, including: Dividing the time series of the labeled data into a number of data points at equal intervals; Dividing the time series of the labeled data into a charging period and a discharging period according to the segmented electricity price; Calculate the average power consumption of the data points in the charging period and the average power consumption of the data points in the discharging period according to the clustering result before the energy storage device is put into operation; Calculate the average power consumption of the data points in the charging period and the average power consumption of the data points in the discharging period according to the clustering result after the energy storage device is put into operation; The power consumption difference of the control enterprise is obtained according to the difference between the average power consumption of the energy storage device before and after it is put into operation during the charging period, and the difference between the average power consumption of the energy storage device before and after it is put into operation during the discharging period; The identification threshold is obtained by calculating the average value of the electricity usage difference; wherein, there are multiple reference enterprises, and each reference enterprise has one electricity usage difference.

[0015] The operation identification method of the user-side energy storage device provided by the embodiment of the present invention identifies whether the target enterprise has put the energy storage device into operation according to the identification threshold and the data to be verified, including: The difference between the power consumption of the data to be verified after the target time and before the target time is used as the value to be verified of the target enterprise; When the value to be verified is greater than or equal to the identification threshold, the target enterprise has an energy storage device put into operation; When the value to be verified is less than the identification threshold, the target enterprise has not put the energy storage device into operation at the target time.

[0016] In a second aspect, the present invention further provides an electronic device, comprising a processor and a memory for storing a program, wherein the program comprises instructions, and when the instructions are executed by the processor, the processor executes the operation identification method of the user-side energy storage device described in any of the above embodiments.

[0017] The method and device for identifying the operation of the energy storage device on the user side provided by the invention embodiment acquires the electricity consumption data of the enterprise that has invested in the energy storage device, introduces the clustering algorithm to unsupervisedly discover the inherent structural characteristics of the data, and provides support for the operation research of the enterprise's energy storage device. It overcomes the limitation of data disclosure on the identification of energy storage operation, has good accuracy, and provides a basis for energy management and optimized scheduling. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings described below are only some embodiments of the present invention, and for ordinary technicians in this field, other embodiments can be obtained based on these drawings without creative work.

[0019] Figure 1 It is a flow chart of an operation identification method of a user-side energy storage device in an embodiment created by the present invention.

[0020] Figure 2 It is a schematic diagram of clustering results with data labels for a target enterprise in an embodiment of the invention. DETAILED DESCRIPTION

[0021] The embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present invention are shown in the accompanying drawings, it should be understood that the present invention can be implemented in various forms and should not be construed as being limited to the embodiments described herein, which are instead provided to provide a more thorough and complete understanding of the present invention. It should be understood that the drawings and embodiments of the present invention are only for exemplary purposes and are not intended to limit the scope of protection of the present invention.

[0022] As the global energy crisis intensifies and climate change becomes increasingly serious, the transformation and optimization of energy structure has become the focus of current research. Energy management is an important path to achieve economic and green development. In the power system, energy storage devices are used rationally to store excess electricity during low electricity consumption and release it during peak electricity consumption; by balancing electricity supply and demand through peak load shaving, the operation of the power grid is made more stable, while the absorption capacity of renewable energy is improved, providing support for the economy and flexibility of the power grid operation.

[0023] According to the different types of energy storage devices, it can be divided into power generation side energy storage, grid side energy storage and user side energy storage. Among them, user side energy storage refers to the energy storage device installed at the end customer of the power system, which is managed by the user independently to reduce the user's electricity cost.

[0024] The user types of user-side energy storage devices include industrial and commercial users such as factories, enterprises, shopping malls, hotels, office buildings, public utility users such as hospitals and schools, and residential users. Since industrial and commercial users usually have large electricity loads and high electricity price costs, in recent years, the penetration rate of user-side energy storage devices represented by industrial and commercial users has greatly increased, and more and more users have introduced energy storage devices.

[0025] After an enterprise introduces an energy storage device, although the installation of the energy storage device is recorded, it is unknown whether it is actually put into operation. The operation status and operation data are not public, and the operation status of the energy storage device is hidden in the overall power data of the enterprise. Due to the limited available public data, the power supply company or the grid side cannot accurately understand whether the enterprise has put the energy storage device into actual operation. There is insufficient research on the identification of the operation behavior of enterprise-level user energy storage devices, which in turn brings inconvenience to energy scheduling and energy storage benefit evaluation.

[0026] Accordingly, refer to Figure 1As shown, this embodiment provides an operation identification method for a user-side energy storage device. By introducing a clustering algorithm and combining the general law of operation of the energy storage device, the operation identification of the energy storage device is realized by analyzing the load characteristic changes before and after the operation of the energy storage device, which provides an important basis for optimizing energy scheduling and evaluating energy storage benefits.

[0027] Specifically, the operation identification method of the user-side energy storage device includes the following steps: Step S100, obtaining the original data of the target enterprise and the control enterprise.

[0028] Among them, both the target enterprise and the control enterprise have introduced energy storage devices. The target enterprise is unknown about the operation of the energy storage device, and the control enterprise has determined that the energy storage device has been put into operation. The method provided in this embodiment mines the intrinsic structure characteristics of the data through the electricity consumption data of the control enterprise, providing a basis and support for the operation identification of the energy storage device of the target enterprise.

[0029] As an implementable method, step S100 includes the following steps: Step S110, obtaining the time when the control enterprise puts the energy storage device into operation.

[0030] Step S120, obtaining first power consumption data of the reference enterprise; wherein the time period corresponding to the first power consumption data includes the time when the reference enterprise puts the energy storage device into operation.

[0031] Step S130, obtaining second power consumption data of the target enterprise; wherein the time period corresponding to the second power consumption data includes the target time to be identified.

[0032] The operation identification method provided in this embodiment is used to identify whether the target enterprise has put the energy storage device into operation before and after the target time. Therefore, the original data of the target enterprise needs to cover the target time to be identified, and correspondingly, the original data of the control enterprise also needs to include the power consumption data before and after the energy storage device is put into operation.

[0033] The enterprise power consumption data includes various types of power consumption information such as power consumption, power consumption time, power consumption power, etc. In this embodiment, preferably, the first power consumption data and the second power consumption data in the original data are both the total power consumption of enterprise users that can be obtained and disclosed.

[0034] Step S200, processing the original data to obtain the target enterprise's data to be verified and the labeled data of the control enterprise.

[0035] As an implementable method, step S200 includes the following steps: Step S210 , performing data cleaning on the first power data and the second power data of the original data respectively.

[0036] In this embodiment, data cleaning specifically includes the following steps: Step S211: if the first power consumption data includes multiple data files, the multiple data files are merged into one first data file to facilitate subsequent processing.

[0037] If the second electric power consumption data includes multiple data files, the multiple data files are merged into one second data file to facilitate subsequent processing.

[0038] Step S212, detecting and removing abnormal data in the first data file by using the quartile method; detecting and removing abnormal data in the second data file by using the quartile method.

[0039] The quartile method identifies and removes outliers in the data based on the interquartile range. The quartile method does not require the data to follow a specific distribution and has good robustness.

[0040] Specifically, the data of the first data file is sorted by size. After sorting, the first quartile is calculated. , third quartile and interquartile range , and determine the upper and lower limits of normal data.

[0041] Among them, the first quartile It is the value at the 25% position in the data. If the 25% position is not an integer due to the amount of data, the mean of the previous and next data is taken as the first quartile. . Third quartile It is the value at the 75% position in the data. If the 75% position is not an integer due to the amount of data, the mean of the previous and next data is taken as the third quartile. . Interquartile range According to the first quartile and the third quartile Calculate. Interquartile range The upper and lower limits of normal data are calculated by referring to the following formula: ; ; ; In the formula, is the upper limit of normal data, and data exceeding the upper limit will be removed as abnormal data; is the lower limit of normal data, and data below the lower limit is removed as abnormal data. For the second data file, the step of removing abnormal data by quartile method is the same as that of the first data file, which will not be repeated here.

[0042] Step S213, in the first data file and the second data file after the anomalies are removed, the positions where the abnormal data are located are filled by using the forward filling strategy.

[0043] The forward filling strategy is to fill the abnormal data with the data at the previous moment. Refer to the following formula for filling: ; In the formula, for The data at the moment, when the data When missing due to exclusion, use the data from the previous moment Fill to Location.

[0044] Step S220, labeling the data cleaned in step S210.

[0045] The label is assigned before and after the energy storage device is put into operation, and the result after the comparison enterprise data cleaning is labeled to obtain the labeled data. The labeled data has the label before the operation is put into operation or the label after the operation is put into operation.

[0046] The target enterprise data after cleaning is labeled with labels before and after the target time to obtain the data to be verified. In this embodiment, the association between the data to be verified with labels before the current time and labels after the target time is similar to the association between the labeled data with labels before and after the operation, to verify whether there is an energy storage device put into operation before and after the target time.

[0047] Step S300, inputting the labeled data obtained in step S200 into a clustering algorithm, and outputting clustering results before and after the energy storage device is put into operation.

[0048] As an implementable method, step S300 includes the following steps: Step S310, dividing the labeled data into multiple time series according to a certain time scale, and inputting the time series into a clustering algorithm.

[0049] Step S310 determines the number and length of the time series. In this embodiment, the time period corresponding to the first data file can reach one month or several months. Corresponding to the time period length of the first data file, the time series can be divided into 24 hours as a scale, and a total of N time series are obtained as inputs of the clustering algorithm, and the length of each time series is 24 hours. In other embodiments, the time series can be divided according to other scales, and are not limited thereto.

[0050] In this embodiment, the clustering algorithm is set to the k-shape algorithm, which is based on the idea of ​​k-means clustering and is improved according to the characteristics of time series data. The k-shape algorithm uses shape-based distance measurement to capture the shape characteristics of the time series, which can better reflect the true similarity between time series.

[0051] Similar to the k-means clustering algorithm, the k-shape algorithm needs to implement the specified number of clusters K. In this embodiment, the number of clusters K=2, that is, the clustering result output by the clustering algorithm includes two clusters, corresponding to the energy storage device before and after it is put into operation.

[0052] Step S320, initializing the clusters to which the time series belong, and initializing the central time series of each cluster.

[0053] The N time series input to the clustering algorithm are randomly initialized to one of the clusters. All data points of the central time series of the two clusters are initialized to 0.

[0054] Step 330, iteratively update the clustering division of the time series.

[0055] Specifically, step S330 includes: Step S331, calculate and update the central time series of the cluster according to the time series in each cluster under the current cluster division. For the first iteration, the current cluster division is the initialization result in step S320. The central time series based on the current cluster is calculated with reference to the following formula: ; ; ; .

[0056] In the formula, express The length is In this embodiment, when the time series is divided into 24 hours, the length of the time series is 24 hours, and m is the number of data points within the 24-hour scale. When calculating the central time series of one cluster, is the number of time series in the calculated cluster, ≤ N. Therefore, when the clustering division changes, the time series and the number of time series in each cluster are likely to change, and when the time series or the number of time series changes, the central time series of the cluster also changes.

[0057] Transpose the time series matrix in the cluster With the time series matrix Multiply to get the time series matrix The autocorrelation matrix of ; Autocorrelation matrix Used to reflect the similarity between time series in a cluster.

[0058] Continue, according to the length of the time series Get the centralization matrix ; In the formula represents the identity matrix, represents a matrix of all 1s, matrix All elements in are 1. The centered matrix The mean component of the time series in the cluster is removed.

[0059] Taking into account the similarity between time series and the central adjustment, the transpose of the central matrix is , autocorrelation matrix , and the centralization matrix Multiply them together to get the covariance matrix after centralization .

[0060] Then, based on the covariance matrix Perform eigenvalue decomposition to obtain the covariance matrix The eigenvalue of The eigenvector corresponding to the maximum eigenvalue is used as the new central time series of the calculated cluster .

[0061] For another cluster, when updating the central time series, the time series in the other cluster is used as the time series matrix, and the calculation process is the same.

[0062] Step S332, calculating the distance between each time series and each central time series updated in step S331.

[0063] Take the central time series of one of the clusters updated in step S331 For example, the distance calculation refers to the following formula: ; In the formula, Indicates the first time series; Representing time series With the central time series The length of the cross-correlation sequence. The above formula is used to calculate the time series With the central time series The distance between a time series and the center time series of another cluster is calculated in the same way. To return a time series Length. Indicates the value that is closest to the input in a direction larger than the input and is an integer power of 2. For example, Input , the function will find an integer q such that ≥ ,and <a, and returns the integer q.

[0064] ; ; Continue, where Representing time series With the central time series The cross-correlation sequence. represents the fast Fourier transform, represents the inverse fast Fourier transform. Perform normalization processing, represents the normalized cross-correlation sequence.

[0065] ; Next, calculate the maximum value of the cross-correlation , according to the maximum value of the cross-correlation Get time series With the updated central time series Distance .

[0066] Step S333, based on the distance in step S332 The calculation results of the time series Assign to the cluster where the nearest central time series is located. In other words, for the time series , respectively calculate the distance between it and the updated central time series of the two clusters, and take the central time series corresponding to the minimum value to represent the time series The distance to the central time series is the closest, and then the time series Assigned to the cluster where the central time series lies.

[0067] Step S334, the calculation and allocation in step S333 are performed on all N time series, and the clustering division is updated according to the allocation results of the N time series. It should be noted that when the cluster to which the time series belongs changes, the central time series of the corresponding cluster may also change.

[0068] Based on the cluster division updated in step S334, steps S331 to S334 are iterated repeatedly to continuously update the clusters until the loop process meets the iteration termination condition.

[0069] Step 340 , when the clustering is stable or the maximum number of iterations is reached, the iteration is stopped, and the clustering results before and after the energy storage device is put into operation are output.

[0070] The stabilization of clustering or reaching the maximum number of iterations is used as the iteration termination condition. Among them, when the cluster affiliation of all N time series does not change between two adjacent iterations, the clustering is considered stable. In the case of stable clustering, since the cluster affiliation of the time series has not changed compared with the previous iteration, the corresponding central time series and distance calculation results have not changed, so continued iteration will not output other clustering results, and the clustering is considered stable. The maximum number of iterations is preset. When the preset threshold of the number of iterations is reached, the iteration is also stopped and the clustering results are output. The clustering results include two clusters before and after the energy storage device is put into operation, and there are several time series in the clusters.

[0071] Step S400, obtaining the recognition threshold before and after the control enterprise puts the energy storage device into operation according to the clustering result output in step S300.

[0072] As an implementable method, step S400 includes the following steps: Step S410, dividing the time series of the labeled data into a number of data points at equal intervals.

[0073] In this embodiment, the annotated data is divided into 24-hour scales for time alignment, and the annotated data records the power consumption of the control enterprise with 15 minutes as a data point. In other embodiments, the division scale of the time series and the division of the data points are not limited to this.

[0074] Step S420 , dividing the time series of the labeled data into a charging period and a discharging period according to the segmented electricity price.

[0075] In this embodiment, the segmented electricity prices corresponding to each time period in the 24-hour time scale in the area where the enterprise is located are obtained. See Table 1: Table 1

[0076] Enterprise energy storage devices are usually charged in the valley period when electricity prices are lower, and discharged in the peak period when electricity prices are higher, reducing electricity costs through peak-valley arbitrage. The inventors of this embodiment have found that enterprise energy storage devices usually complete two charges and two discharges within 24 hours according to the segmented electricity prices, and there is no significant difference in the changes in electricity consumption between the two charges and discharges. Therefore, in this embodiment, 00:00-08:00 is used as the charging period (excluding 00:00), and 08:00-11:00 is used as the discharging period (excluding 08:00) to calculate the difference in electricity consumption before and after the operation of the energy storage device. In other embodiments, it can also be calculated based on 11:00-17:00 as the charging period and 17:00-22:00 as the discharging period.

[0077] Step S430, based on the clustering result before the energy storage device is put into operation, the average power consumption of the data points in the charging period and the average power consumption of the data points in the discharging period are calculated.

[0078] According to the clustering results after the energy storage device is put into operation, the average power consumption of the data points in the charging period and the average power consumption of the data points in the discharging period are calculated.

[0079] In this embodiment, if one data point is divided into 15 minutes, the charging period includes 32 data points, and the discharging period includes 12 data points. The average power consumption is calculated within the range of these data points. The specific calculation process is referred to the following formula: ; ; .

[0080] In the formula, Indicates Group data in time period The average value within Indicates that the algorithm belongs to the Group, Time The data points within Indicates that the algorithm belongs to the Group, Time The number of data points. The value of is 1 or 2, the first group represents before the energy storage device is put into operation, and the second group represents after the energy storage device is put into operation. The value of is 1 or 2, period 1 represents the charging period, and period 2 represents the discharging period.

[0081] Step S440, obtaining the power consumption difference of the control enterprise according to the difference between the average power consumption of the energy storage device before and after it is put into operation in the charging period and the difference between the average power consumption of the energy storage device before and after it is put into operation in the discharging period.

[0082] Specifically, the difference in the average power consumption of the energy storage device before and after it is put into operation during the charging period is calculated with reference to the following formula: ; In the formula, It indicates the difference between the average power consumption after the energy storage operation and before the operation in period 1, which is the charging period.

[0083] The difference in the average power consumption before and after the energy storage device is put into operation during the discharge period is calculated by referring to the following formula: ; In the formula, It represents the difference between the average power consumption after the energy storage operation and before the operation in period 2, which is the discharge period.

[0084] Compare the difference in electricity consumption of enterprises Refer to the following formula for calculation: .

[0085] Step S450, calculating the power consumption difference The average value of the recognition threshold Among them, there are multiple control enterprises, and each control enterprise has an electricity consumption difference . Identification threshold Refer to the following formula for calculation: .

[0086] In the formula, represents the total number of control enterprises, Indicates The difference in electricity consumption between the two control enterprises.

[0087] Step S500: according to the recognition threshold and the data to be verified to identify whether the target enterprise has put the energy storage device into operation.

[0088] In some embodiments, the identification threshold Determined according to the calculation result of step S400. In other embodiments, the identification threshold It can also be appropriately scaled and then compared with the data to be verified.

[0089] The difference in power consumption between the data to be verified after the target time and before the target time is used as the value to be verified for the target enterprise; for example, when identifying whether the target enterprise has an energy storage device put into operation within the 24 hours from 00:00 to 24:00, 00:00-08:00 is taken as the possible charging stage according to the segmented electricity price, and 08:00-11:00 is taken as the possible discharging stage for verification. The 24 hours when the target time is located is taken as the period to be verified, and the difference before and after the target time is taken as the value to be verified, to verify whether the energy storage device is put into operation within the period to be verified.

[0090] The value to be verified is greater than or equal to the recognition threshold When , the identification result is that the target enterprise has an energy storage device put into operation before and after the target time, and the operation of the energy storage device occurs within the period to be verified.

[0091] The value to be verified is less than the recognition threshold When , the identification result is that the target enterprise did not put the energy storage device into operation at the target time, and there was no operation behavior.

[0092] Table 2 shows one implementation of this embodiment, comparing the average power consumption data and the power consumption difference calculation of the enterprise. In this embodiment, the data shown in Table 2 is used as an example to specifically illustrate steps S400 to S500: Table 2

[0093] According to the general rules of energy storage operation, the total power consumption of the enterprise after it is put into operation increases compared with that before it is put into operation due to the charging consumption of the energy storage device during the charging period. is 0.0206; the mean of each data point after the energy storage device is put into operation during the charging period 0.0424; the difference in the average power consumption before and after the energy storage operation during the charging period is 0.02175. Is a positive number, the difference The larger the value, the greater the change in electricity consumption before and after the energy storage device is operated.

[0094] During the discharge period, due to the power supply of the energy storage device, the total power consumption of the enterprise after it was put into operation decreased compared with before it was put into operation. The average of each data point before the energy storage device was put into operation during the discharge period is 0.1113; the mean of each data point after the energy storage device is put into operation during the discharge period 0.0540; the difference between the average power consumption before and after the energy storage operation during the discharge period is -0.0574. is a negative number, the difference The smaller it is, the greater the change in electricity consumption before and after the energy storage device is operated.

[0095] Next, for the control enterprise, the difference in electricity consumption The larger the difference in electricity consumption, the more obvious the change in the electricity consumption behavior of the control enterprise before and after the energy storage device is put into operation. Take the average to get the approximate change level of enterprise electricity consumption behavior caused by energy storage operation, and finally get the identification threshold The value is 0.0625, while the threshold used for identification by the target enterprise is 0.0801. Therefore, it is judged that the target enterprise has put the energy storage device into operation.

[0096] This embodiment also clusters the data of the target enterprise to verify the accuracy of the method provided in this embodiment. The results are shown in Figure 2As shown in the figure. Different color backgrounds are used to distinguish different electricity price periods. The blue background part is the electricity price valley period, which represents the charging period of the energy storage device for the target enterprise. The orange background part is the electricity price peak period, and the orange background part adjacent to the blue background corresponds to the discharge period of the energy storage device.

[0097] Figure 2 The sub-figure in the upper middle corresponds to the electricity consumption waveform under the real label. The pink curve represents the daily curve before the energy storage is operated, and the blue curve represents the daily curve after the energy storage is operated. Figure 2 The sub-graph in the lower middle corresponds to the result obtained by the clustering algorithm. The green curve represents the curve where the algorithm classifies correctly, the pink curve represents the pre-operation power consumption data where the algorithm incorrectly predicts it to be the post-operation power consumption data, and the blue curve represents the post-operation power consumption data where the algorithm incorrectly predicts it to be the pre-operation power consumption data. The accuracy of the algorithm clustering is 0.87.

[0098] Reference Figure 2 As can be seen from the sub-graph above, during the charging period, the blue post-operation curve is higher than the pink pre-operation curve, indicating that the energy storage charging is consumed and the power consumption increases. During the discharging period, the blue post-operation curve is lower than the pink pre-operation curve, indicating that the energy storage is discharged and replenished, and the power consumption decreases, which is consistent with the general law of energy storage operation. The operation identification method of the user-side energy storage device provided in this embodiment correctly identifies the target enterprise.

[0099] The operation identification method of the user-side energy storage device provided in this embodiment obtains the electricity consumption data of the enterprise that has invested in the energy storage device, introduces the clustering algorithm to unsupervisedly discover the intrinsic structural characteristics of the data, mines the load characteristic changes before and after the operation of the energy storage device, and reasonably designs the algorithm steps in combination with the general rules of energy storage operation, so as to provide support for the operation research of the enterprise energy storage device.

[0100] This embodiment can accurately identify the operation of an enterprise's energy storage device, help relevant departments monitor the use of energy storage devices, and is of great significance to energy management and green energy development. This embodiment overcomes the limitations of data disclosure on energy storage operation identification, has good accuracy, provides a basis for energy management and optimized scheduling, and is of great significance to optimizing energy management and promoting the construction of smart grids.

[0101] This embodiment also provides an electronic device, including: at least one processor; and a memory connected to the at least one processor. The memory stores a computer program that can be executed by the at least one processor, and when the at least one processor executes the computer program, the electronic device executes the operation identification method of the user-side energy storage device. The electronic device has all the technical effects of the above method.

[0102] Electronic devices are intended to represent various forms of digital electronic computer devices, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. Electronic devices may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the inventions described and / or claimed herein.

[0103] This embodiment also provides a non-transitory machine-readable medium storing a computer program, wherein the computer program, when executed by a processor of a computer, is used to enable the computer to execute the operation identification method of the user-side energy storage device.

[0104] This embodiment also provides a computer program product, including a computer program, wherein the computer program, when executed by a processor of a computer, is used to enable the computer to execute the above-mentioned operation identification method of the user-side energy storage device.

[0105] The computer program for implementing the method of the present embodiment can be written in any combination of one or more programming languages. These computer programs can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor or controller, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program can be executed entirely on the machine, partially on the machine, partially on the machine as a stand-alone software package and partially on a remote machine, or entirely on a remote machine or server.

[0106] In the context of the present invention, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or apparatus. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable signal medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, or infrared systems, devices, or equipment, or any suitable combination of the foregoing. More specific examples of machine-readable storage media may include electrical connections based on one or more lines, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROMs), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0107] It should be noted that the term "including" and its variations used in the embodiments of the present invention are open inclusions, that is, "including but not limited to". The term "based on" means "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one other embodiment"; the term "some embodiments" means "at least some embodiments". The modifications of "one" and "multiple" mentioned in the embodiments of the present invention are illustrative and not restrictive. Those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0108] The user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in the embodiments of the present invention are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0109] The various steps described in the method implementation methods provided by the embodiments of the present invention can be performed in different orders and / or in parallel. In addition, the method implementation methods may include additional steps and / or omit the steps shown. The scope of protection of the present invention is not limited in this respect.

[0110] The term "embodiment" in this specification refers to specific features, structures or characteristics described in conjunction with the embodiment that can be included in at least one embodiment of the invention. The appearance of this phrase in various places in the specification does not necessarily mean the same embodiment, nor does it mean that it is mutually exclusive with other embodiments and is independent or optional. The various embodiments in this specification are described in a related manner, and the same and similar parts between the various embodiments refer to each other. In particular, for the device, equipment, and system embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts refer to the partial description of the method embodiment.

[0111] The above-described embodiments only express several implementation methods of the present invention, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of protection. It should be pointed out that, for a person of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present invention, and these all belong to the scope of protection of the present invention. Therefore, the scope of protection of the present invention shall be subject to the attached claims.

Claims

1. A method for identifying the operation of a user-side energy storage device, characterized in that: The method comprises: Obtaining original data of the target enterprise and the control enterprise; wherein the control enterprise has put the energy storage device into operation; Processing the original data to obtain the target enterprise's data to be verified and the reference enterprise's labeled data; Inputting the labeled data into a clustering algorithm, and outputting clustering results of the energy storage device before and after it is put into operation; Obtaining, according to the clustering result, the identification threshold before and after the control enterprise puts the energy storage device into operation; It is determined whether the target enterprise has put the energy storage device into operation according to the identification threshold and the data to be verified.

2. The operation identification method of the user-side energy storage device according to claim 1, characterized in that: Obtain the original data of the target and control enterprises, including: Obtaining the time when the reference enterprise puts the energy storage device into operation; Acquire first power consumption data of the reference enterprise; wherein the time period corresponding to the first power consumption data includes the time when the reference enterprise puts the energy storage device into operation; Acquire second electric power consumption data of the target enterprise; wherein the time period corresponding to the second electric power consumption data includes the target time to be identified.

3. The operation identification method of the user-side energy storage device according to claim 2, characterized in that: Processing the original data to obtain the target enterprise's data to be verified and the reference enterprise's labeled data includes: performing data cleaning on the first electric power data and the second electric power data; Using labels assigned before and after the energy storage device is put into operation, the cleaned result of the first power consumption data is annotated to obtain the annotated data; The cleaned result of the second electric power data is marked with labels before and after the target time to obtain the data to be verified.

4. The operation identification method of the user-side energy storage device according to claim 3, characterized in that: The first power consumption data and the second power consumption data are cleansed, including: Merging the first electric power data into a first data file, and merging the second electric power data into a second data file; Detect and remove abnormal data in the first data file by using the quartile method, and detect and remove abnormal data in the second data file by using the quartile method; In the first data file, fill the data at the previous moment of the abnormal data into the position of the abnormal data; In the second data file, the data at a previous moment of the abnormal data is filled into the position of the abnormal data.

5. The operation identification method of the user-side energy storage device according to claim 1, characterized in that: The labeled data is input into a clustering algorithm, and clustering results of the energy storage device before and after it is put into operation are output, including: Dividing the labeled data into a plurality of time series, and inputting the time series into a clustering algorithm; Initialize the cluster to which the time series belongs, and initialize the central time series of each cluster; Iteratively updating the clustering division of the time series; When the clustering is stable or the maximum number of iterations is reached, the clustering results of the energy storage device before and after it is put into operation are output.

6. The operation identification method of the user-side energy storage device according to claim 5, characterized in that: The clustering division of the time series is iteratively updated, including: Calculate and update the central time series of the cluster according to the time series in each cluster under the current clustering division; Calculate the distance between each time series and each updated central time series; According to the distance calculation result, the time series is assigned to the cluster where the nearest central time series is located; The clustering division is updated according to the allocation result of the time series.

7. The operation identification method of the user-side energy storage device according to claim 6, characterized in that: Calculate and update the central time series of the cluster according to the time series in each cluster under the current clustering division, including: Multiplying the transpose of the time series matrix in the cluster by the time series matrix to obtain an autocorrelation matrix of the time series matrix; Obtaining a centering matrix according to the length of the time series; Multiplying the transpose of the centering matrix, the autocorrelation matrix, and the centering matrix to obtain a centered covariance matrix; Perform eigenvalue decomposition on the covariance matrix to obtain the maximum eigenvalue of the covariance matrix, and the eigenvector corresponding to the maximum eigenvalue is the updated central time series.

8. The operation identification method of the user-side energy storage device according to claim 6, characterized in that: Calculate the distance between each time series and each updated central time series, including: Calculating a cross-correlation sequence between the time series and the updated central time series; performing normalization processing on the cross-correlation sequence; The maximum value of the mutual correlation is calculated, and the distance between the time series and the updated central time series is obtained according to the maximum value of the mutual correlation.

9. The operation identification method of the user-side energy storage device according to claim 1, characterized in that: Obtaining the identification threshold of the control enterprise before and after the energy storage device is put into operation according to the clustering result, including: Dividing the time series of the labeled data into a number of data points at equal intervals; Dividing the time series of the labeled data into a charging period and a discharging period according to the segmented electricity price; Calculate the average power consumption of the data points in the charging period and the average power consumption of the data points in the discharging period according to the clustering result before the energy storage device is put into operation; Calculate the average power consumption of the data points in the charging period and the average power consumption of the data points in the discharging period according to the clustering result after the energy storage device is put into operation; The power consumption difference of the control enterprise is obtained according to the difference between the average power consumption of the energy storage device before and after it is put into operation during the charging period, and the difference between the average power consumption of the energy storage device before and after it is put into operation during the discharging period; The identification threshold is obtained by calculating the average value of the electricity usage difference; wherein, there are multiple reference enterprises, and each reference enterprise has one electricity usage difference.

10. The operation identification method of the user-side energy storage device according to claim 1, characterized in that: Identifying whether the target enterprise has put the energy storage device into operation according to the identification threshold and the data to be verified includes: The difference between the power consumption of the data to be verified after the target time and before the target time is used as the value to be verified of the target enterprise; When the value to be verified is greater than or equal to the identification threshold, the target enterprise has an energy storage device put into operation; When the value to be verified is less than the identification threshold, the target enterprise has not put the energy storage device into operation at the target time.

11. An electronic device, comprising: A processor, and a memory storing a program, wherein the program includes instructions, and when the instructions are executed by the processor, the processor executes the operation identification method of the user-side energy storage device according to any one of claims 1 to 10.

Images