Load Identification Method and Device Based on Variable Sliding Window Multi-Resolution Power Matching

Abstract

The present invention provides a load identification method and device based on variable sliding window multi-resolution power matching, which can be applied to the technical field of load monitoring. The method includes: detecting load events for the total power data to obtain initial load data; determining the load event type according to the length of the initial load data; in the case where the load event type is determined to be a long transient event type, determining a sliding window length range corresponding to the template power data to be matched according to the length of the template power data to be matched; determining C target section starting points according to the section starting point of the initial load data and the preset number of section starting points; for each target section starting point, dynamically intercepting the total power data according to the sliding window length range and each target section starting point to obtain a candidate load matrix; and determining a load identification result based on a multi-resolution waveform matching algorithm according to the candidate load matrix and the template power data to be matched.

Description

Technical Field

[0001] The present invention relates to the technical field of load monitoring, and particularly to a load identification method and device based on variable sliding window multi-resolution power matching. Background Art

[0002] Energy conservation has increasingly become an important issue. Feeding back the detailed power consumption information of different user electrical devices to the user can help the user adjust their power consumption plan to reduce unnecessary power consumption. Therefore, it is important to extract the load data of each different total electrical device from the power consumption. Existing load monitoring methods usually formulate rules or compare thresholds based on common sense and experience to determine whether it is a load event, and then extract load feature samples.

[0003] However, since the transient power waveforms generated during the working state conversion process of different electrical devices are not the same, and the state conversion process is easily affected by background noise, and the background noise levels of different load scenarios may be different. Therefore, for long transient type load events, existing methods are difficult to ensure that the start and end times of the same type of load event generated by the same electrical device are accurately located, that is, the accuracy of the complete detection of the load feature samples of the electrical device is low. Summary of the Invention

[0004] In view of the above problems, the present invention provides a load identification method and device based on variable sliding window multi-resolution power matching.

[0005] According to a first aspect of the present invention, there is provided a load identification method based on variable sliding window multi-resolution power matching, including: performing load event detection on the total power data to obtain initial load data; determining the load event type according to the length of the initial load data; in the case where the load event type is determined to be a long transient event type, determining a sliding window length range corresponding to the template power data to be matched according to the length of the template power data to be matched, wherein the length of the initial load data corresponding to the long transient event type is greater than or equal to a preset length threshold; determining C target section start points according to the section start point of the initial load data and a preset number of section start points, where C is a positive integer; for each of the C target section start points, dynamically intercepting the total power data according to the sliding window length range and each target section start point to obtain a candidate load matrix; based on a multi-resolution waveform matching algorithm, determining a load identification result according to the candidate load matrix and the template power data to be matched, and the load identification result includes target load data and a target electrical device corresponding to the target load data.

[0006] Optionally, based on the multi-resolution waveform matching algorithm, according to the candidate load matrix and the template power data to be matched, the load recognition result is obtained as follows: perform N downsampling processes on the candidate load matrix to obtain N downsampled candidate load matrices; perform N downsampling processes on the template power data to be matched to obtain N downsampled template power data to be matched; for the nth downsampling among the N downsamplings, according to the nth downsampled template power data to be matched and at least one downsampled candidate load data in the nth downsampled candidate load matrix, obtain the nth matching matrix, so as to obtain N matching matrices, where each matching matrix includes at least one matching result, and the matching result represents the distance value between the nth downsampled template power data to be matched and the nth downsampled candidate load data, N≥1, 1≤n≤N; determine the target matching result from at least one matching result, and when the target matching result meets the preset distance threshold range, determine the nth downsampled candidate load data corresponding to the target matching result as the target load data, and determine the electrical device corresponding to the template power data to be matched as the target electrical device corresponding to the target load data.

[0007] Optionally, determining the target matching result from at least one matching result includes: determining the minimum matching result among at least one matching result as the target matching result.

[0008] Optionally, the load recognition method based on variable sliding window multi-resolution power matching further includes: determining a first power difference according to the power values corresponding to the section start point and the section end point of the template power data to be matched respectively; determining a second power difference according to the power values corresponding to the section start point and the section end point of the target load data respectively; determining the similarity between the target load data and the template power data to be matched according to the first power difference and the second power difference; when the similarity is less than the preset similarity threshold, adding the target load data to the initial load data sample library to obtain the target load data sample library; determining the sample number of the sample load data in the target load data sample library; when the sample number is greater than the preset number threshold, updating the initial power data template library according to the target load data sample library, where the template power data to be matched is stored in the initial power data template library.

[0009] Optionally, the initial power data template library includes the template power data to be matched corresponding to each of the I types of electrical devices, and the template power data to be matched corresponding to the ith electrical device includes the central template power data, the average template power data, and the cluster template power data. The initial load data sample library includes multiple sample load data corresponding to the ith electrical device, i I, i, and I are positive integers; among them, the central template power data corresponding to the i-th electrical equipment is determined based on the following operations: calculating the distance between each two of multiple sample load data using the dynamic time warping distance algorithm to obtain a distance matrix; summing the column elements in the distance matrix to obtain multiple column element sums; and determining the sample load data corresponding to the smallest column element sum among the multiple column element sums as the central template power data.

[0010] Optionally, the average template power data corresponding to the i-th electrical equipment is determined based on the following operations: based on the dynamic time warping distance algorithm, calculating the warping paths between multiple sample load data and the central template power data respectively to obtain multiple warping paths; and processing the multiple warping paths using an average value calculation function to obtain the average template power data.

[0011] Optionally, the cluster template power data corresponding to the i-th electrical equipment is determined based on the following operations: determining a relationship judgment threshold according to the average value and standard deviation of the elements in the upper triangular region of the distance matrix, where the upper triangular region represents the region composed of all elements on and above the diagonal from the upper left corner to the lower right corner of the distance matrix; performing clustering processing on multiple sample load data based on the distance matrix and the relationship judgment threshold to obtain A clustering clusters, where A is a positive integer; and for each of the A clustering clusters, obtaining A cluster template power data according to the multiple sample load data in each clustering cluster.

[0012] Optionally, the load identification method based on variable sliding window multi-resolution power matching further includes: in the case where the load event type is a step event type, determining the power tolerance and length of the initial load data, where the length of the initial load data corresponding to the step event type is less than a preset length threshold; based on the power tolerance and length, matching multiple template power data to be matched and the initial load data to determine the target template power data corresponding to the initial load data, and determining the electrical equipment corresponding to the target template power data as the target electrical equipment corresponding to the initial load data.

[0013] Optionally, performing load event detection on the total power data to obtain the initial load data includes:

[0014] Intercept the section data of the total power data based on the first preset window length to obtain the first section power data, where the total power data represents the total data of the power consumption of different electrical devices; determine the third power difference according to the power values corresponding to the section start point and the section end point of the first section power data respectively; in the case where the third power difference is greater than or equal to the preset power threshold, intercept the section data of the first section power data based on the second preset window length to obtain the second section power data; determine the fourth power difference according to the power values corresponding to the section start point and the section end point of the second section power data respectively; in the case where the fourth power difference is greater than or equal to the preset power threshold and the length of the second section power data is within the preset length range, determine the second section power data as the initial load data.

[0015] The second aspect of the present invention provides a load recognition device based on variable sliding window multi-resolution power matching, including: a detection module for detecting load events in the total power data to obtain initial load data; a judgment module for determining the load event type according to the length of the initial load data; a first determination module for determining the sliding window length range corresponding to the template power data to be matched according to the length of the template power data to be matched in the case where the load event type is determined to be a long transient event type, where the length of the initial load data corresponding to the long transient event type is greater than or equal to the preset length threshold; a second determination module for determining C target section start points according to the section start point of the initial load data and the preset number of section start points; an interception module for dynamically intercepting the total power data for each of the C target section start points according to the sliding window length range and each target section start point to obtain a candidate load matrix; an identification module for obtaining a load recognition result based on a multi-resolution waveform matching algorithm according to the candidate load matrix and the template power data to be matched, where the load recognition result includes target load data and the target electrical device corresponding to the target load data.

[0016] According to the load identification method and device based on variable sliding window multi-resolution power matching provided by the present invention, by pre-applying the template power data corresponding to each personalized power-consuming device in the scenario to the target load data extraction stage, it is realized that the sliding window length range can be adjusted according to the length of the template power data to be matched in each matching process. Based on the initial load data, multiple candidate load data are dynamically intercepted within the sliding window length range, and then the candidate load data after being converted at multiple resolutions are matched with the template power data to be matched, and the target load data with high integrity among the template power data to be matched in the case of successful matching is selected, making full use of the template information to extract target load data with high integrity and high consistency, thereby improving the accuracy of load identification and solving the problems of poor integrity and poor accuracy in the extraction of load characteristic samples for long transient event types. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Through the following description of the embodiments of the present invention with reference to the drawings, the above and other objects, features and advantages of the present invention will become more clear.

[0018] Figure 1 The flowchart of the load identification method based on variable sliding window multi-resolution power matching according to an embodiment of the present invention is shown.

[0019] Figure 2 An example diagram of generating a candidate load matrix according to an embodiment of the present invention is shown.

[0020] Figure 3 The flowchart of the load identification process based on variable sliding window multi-resolution power matching according to an embodiment of the present invention is shown.

[0021] Figure 4 The structural block diagram of the load identification device based on variable sliding window multi-resolution power matching according to an embodiment of the present invention is shown. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0022] Hereinafter, embodiments of the present invention will be described with reference to the drawings. However, it should be understood that these descriptions are exemplary and are not intended to limit the scope of the present invention. In the following detailed description, for the sake of explanation, many specific details are set forth to provide a comprehensive understanding of the embodiments of the present invention. However, obviously, one or more embodiments can be implemented without these specific details. In addition, in the following description, descriptions of well-known structures and technologies are omitted to avoid unnecessarily confusing the concepts of the present invention.

[0023] The terms used herein are merely for describing specific embodiments and are not intended to limit the present invention. The terms "comprising", "including" and the like as used herein indicate the presence of features, steps, operations and / or components, but do not preclude the presence or addition of one or more other features, steps, operations or components.

[0024] All terms used herein (including technical and scientific terms) have the meanings commonly understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein should be interpreted as having a meaning consistent with the context of this specification, and should not be interpreted in an idealized or overly rigid manner.

[0025] In the case of using expressions such as "at least one of A, B, and C, etc.", generally, it should be interpreted according to the meaning commonly understood by those skilled in the art (for example, "a system having at least one of A, B, and C" should include, but is not limited to, a system having only A, only B, only C, having A and B, having A and C, having B and C, and / or having A, B, and C, etc.).

[0026] In view of this, embodiments of the present invention provide a load identification method and device based on variable sliding window multi-resolution power matching. The method includes: detecting load events in the total power data to obtain initial load data; determining the load event type according to the length of the initial load data; when it is determined that the load event type is a long transient event type, determining a sliding window length range corresponding to the template power data to be matched according to the length of the template power data to be matched; determining C target section starting points according to the section starting point of the initial load data and the preset number of section starting points; for each of the C target section starting points, dynamically intercepting the total power data according to the sliding window length range and each target section starting point to obtain a candidate load matrix; and obtaining a load identification result based on a multi-resolution waveform matching algorithm according to the candidate load matrix and the template power data to be matched.

[0027] In the technical solution of the present invention, the user information involved (including but not limited to user personal information, user image information, user device information, such as location information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) are all information and data authorized by the user or fully authorized by all parties. Moreover, the processing of relevant data, such as collection, storage, use, processing, transmission, provision, disclosure, and application, complies with relevant laws, regulations and standards, takes necessary confidentiality measures, does not violate public order and good customs, and provides corresponding operation entrances for users to choose to authorize or refuse.

[0028] It should be noted that the serial numbers of the respective operations in the following methods are only used as representations of the operations for description purposes and should not be regarded as indicating the execution order of the respective operations. Unless explicitly stated, the method does not need to be executed exactly in the order shown.

[0029] Figure 1 A flowchart of a load identification method based on variable sliding window multi-resolution power matching according to an embodiment of the present invention is shown.

[0030] As Figure 1 shown, the method 100 includes operations S110 to S160.

[0031] In operation S110, load event detection is performed on the total power data of electricity to obtain initial load data.

[0032] Optionally, the total power data of electricity is the total power time series change data directly collected from the power supply inlet of the electricity user, and the total power time series includes the time series power change data consumed by different electrical devices respectively. For example, the electrical devices can be air conditioners, refrigerators, etc.

[0033] Optionally, the median filtering algorithm is used to preprocess the total power data of electricity to obtain the filtered total active power data, and load event detection is performed on the filtered total active power data to obtain multiple initial load data.

[0034] Optionally, the initial load data is the power data change section during the process of an electrical device switching from a steady state to another steady state (i.e., the transient process), and the power change range of the initial load data is greater than or equal to a preset power threshold.

[0035] In operation S120, the load event type is determined according to the length of the initial load data.

[0036] Optionally, a sequence length calculation function is used to calculate the length of the initial load data, and the length of the initial load data can be detected to determine the load event type.

[0037] Optionally, the length of the initial load data is the time series length.

[0038] In operation S130, when it is determined that the load event type is the long transient event type, according to the length of the template power data to be matched, the sliding window length range corresponding to the template power data to be matched is determined.

[0039] Optionally, the length of the initial load data is calculated using a sequence length calculation function. When the length of the initial load data is greater than or equal to a preset length threshold, the load event type corresponding to the initial load data is determined as a long transient event type. A load event is an event in which power consumption is caused by an increase, decrease, or transfer of load data during the process of an electrical device changing its working state. The transient process duration of the load event corresponding to the long transient event type is relatively long and may reach several seconds or even several minutes.

[0040] Optionally, the initial power data template library stores template power data corresponding to different electrical devices respectively. The multiple template power data can be sorted based on the length of the template power data to obtain a matching order, and the currently to-be-matched template power data is determined based on the matching order. For example, the number of template power data belonging to the first electrical device is b. If the to-be-matched template power data is one of the b template power data corresponding to the first electrical device, then according to the standard deviation of the lengths of all the template power data belonging to this electrical device in the load data sample library and the length of the to-be-matched template power data , the sliding window length range is determined.

[0041] In operation S140, C target section start points are determined according to the section start point of the initial load data and the preset number of section start points.

[0042] Optionally, the initial load data is obtained by intercepting based on a preset window length. The initial load data is a time section data, and the time section data includes a section start point and a section end point. The sliding start point and the sliding end point of the window are respectively the section start point and the section end point of the initial load data, and the section difference between the section start point and the section end point is the preset window length.

[0043] Optionally, taking the section start point of the initial load data as a reference point, a time neighborhood with a width of r is determined according to the preset number of section start points, and sampling is performed within the time neighborhood of the reference point to obtain C target section start points. The target section start point is the sliding start point of the sliding window, and C is a positive integer.

[0044] In operation S150, for each of the C target section start points among the C target section start points, dynamic data interception is performed on the total power data according to the sliding window length range and each target section start point to obtain a candidate load matrix.

[0045] Optionally, for a certain target section start point, dynamic data interception is performed on the total power data according to the sliding window length range, thereby obtaining multiple candidate load data. The section start points among the multiple candidate load data are the same, and the section end points are different, and thus a one-dimensional candidate load sub-matrix corresponding to this target section start point is obtained. For example, the range of the section end point is 。

[0046] Optionally, for each starting point of the target section, a one-dimensional candidate load sub-matrix corresponding to each starting point of the target section is obtained based on the sliding window length range; then, the candidate load sub-matrices corresponding to each starting point of the target section are sorted in ascending order according to the position of the starting point of the target section to obtain a multi-dimensional candidate load matrix.

[0047] Optionally, the elements in the candidate load matrix represent the intercepted candidate load data, and the number of rows and columns of the candidate load matrix characterize the number of starting points and the number of ending points of the intercepted candidate load data sections.

[0048] Figure 2 FIG. shows an example diagram of generating a candidate load matrix according to an embodiment of the present invention.

[0049] As Figure 2 shown, according to the length of the template power data to be matched , the sliding window length range is determined ; taking the starting point of the section of the initial load data as the reference point G0, a time neighborhood with a width of r is determined according to the preset number of starting points of the section, and sampling is performed within the time neighborhood of the reference point G0 to obtain C target section starting points. For the target section starting point G1, dynamic data interception is performed on the total power data according to the sliding window length range to obtain a plurality of candidate load data. Among them, the candidate load data Q1 is obtained by intercepting data based on the target section starting point G1 and the sliding window length ; for the target section starting point G2, dynamic data interception is performed on the total power data according to the sliding window length range to obtain a plurality of candidate load data. Among them, the candidate load data Q2 is obtained by intercepting data based on the target section starting point G2 and the sliding window length ; for each target section starting point among the C target section starting points, a candidate load matrix is obtained according to the multiple candidate load data corresponding to each target section starting point.

[0050] In operation S160, based on the multi-resolution waveform matching algorithm, the load recognition result is determined according to the candidate load matrix and the template power data to be matched.

[0051] Optionally, the load recognition result includes the target load data and the target electrical device corresponding to the target load data.

[0052] Optionally, perform downsampling on the candidate load matrix and the template power data to be matched at the same frequency to obtain the downsampled candidate load matrix and the template power data to be matched. Then, match the downsampled template power data to be matched with the candidate load data in the candidate load matrix. If the match is successful, determine the target load data from multiple candidate load data.

[0053] Optionally, determine the electrical equipment corresponding to the template power data to be matched as the target electrical equipment.

[0054] Optionally, the target load data represents the power data with high integrity corresponding to the state transition process of the target electrical equipment.

[0055] Optionally, if the match fails, determine the template power data to be matched in the next match process according to the match order, re-determine the sliding window length range and the candidate load matrix, and then match the template power data to be matched with the candidate load matrix until the target load data is matched or all the template power data in the initial power data template library fail to match.

[0056] Optionally, since the template power data corresponding to each personalized electrical equipment in the scenario is pre-applied to the target load data extraction stage, the sliding window length range can be adjusted according to the length of the template power data to be matched in each match process. Based on the sliding window length range, multiple candidate load data are dynamically intercepted from the initial load data, and then the multiple candidate load data after resolution conversion are matched with the template power data to be matched, so as to fully utilize the template information to extract the target load data with high integrity and high consistency, thereby improving the accuracy of target load data identification.

[0057] Optionally, perform load event detection on the total power data to obtain the initial load data, including: intercepting the section data of the total power data based on the first preset window length to obtain the first section power data, where the total power data represents the total data of the power consumption of different electrical equipment; determining the third power difference according to the power values corresponding to the section start point and the section end point of the first section power data; if the third power difference is greater than or equal to the preset power threshold, intercept the section data of the first section power data based on the second preset window length to obtain the second section power data; determining the fourth power difference according to the power values corresponding to the section start point and the section end point of the second section power data; if the fourth power difference is greater than or equal to the preset power threshold and the length of the second section power data is within the preset length range, determine the second section power data as the initial load data.

[0058] Optionally, a third power difference is obtained based on the difference between the power value at the end point of the first section power data and the power value at the start point of the section.

[0059] Optionally, if the third power difference is greater than or equal to a preset power threshold, it indicates that the first section power data is an event section, and the first section power data is retained; if the third power difference is less than the preset power threshold, it indicates that the first section power data is a steady state section, and the first section power data is discarded. An event section is a section where the power change range is large, and a steady state section is a section where the power change range is small.

[0060] In one embodiment, the section type determination is as shown in formula (1):

[0061] (1); where indicates that the section where the first section power data is located is an event section, indicates that the section where the first section power data is located is a steady state section, indicates the preset power threshold, indicates the power value at the end point of the section of the first section power data, indicates the power value at the start point of the section of the first section power data.

[0062] Optionally, when the third power difference is greater than or equal to the preset power threshold, section data interception is performed on the first section power data based on the second preset window length to obtain second section power data.

[0063] Optionally, a fourth power difference is obtained based on the difference between the power value at the end point of the second section power data and the power value at the start point of the section.

[0064] Optionally, when the fourth power difference is greater than or equal to the preset power threshold, the first section power data is retained, and it continues to be determined whether the event section is a load event; when the length of the second section power data is within the preset length range, it is determined that this event section is a load event, and thus the second section power data is determined as the initial load data.

[0065] Optionally, when the fourth power difference is less than the preset power threshold or the length of the second section power data is not within the preset length range, the second section power data is discarded.

[0066] In one embodiment, the load event determination is as shown in formula (2):

[0067] (2); where indicates that the event section where the second section power data is located is a load event, Characterize the power data of the second section as a non-load event, Characterize the preset power threshold, Characterize the power value at the end point of the section of the power data of the second section, Characterize the power value at the starting point of the section of the power data of the second section, Characterize the length of the power data of the second section, and the preset length range is .

[0068] Optionally, the initial power data template library includes the template power data to be matched corresponding to each of the I types of electrical equipment. The template power data to be matched corresponding to the i-th electrical equipment includes the central template power data, the average template power data, and the cluster template power data. The initial load data sample library includes multiple sample load data corresponding to the i-th electrical equipment, where i I, i, and I are positive integers; among them, the central template power data corresponding to the i-th electrical equipment is determined based on the following operations: calculating the distance between every two sample load data in the multiple sample load data by using the dynamic time warping distance algorithm to obtain a distance matrix; summing the column elements in the distance matrix to obtain multiple column element sums; and determining the sample load data corresponding to the smallest column element sum among the multiple column element sums as the central template power data.

[0069] Optionally, the initial load data sample library includes multiple sample load data corresponding to each of the I types of electrical equipment. The central template power data, the average template power data, and the cluster template power data corresponding to the i-th electrical equipment in the initial power data template library are generated based on the multiple sample load data corresponding to the i-th electrical equipment.

[0070] For example, the initial load data sample library includes S sample load data corresponding to the i-th electrical equipment. The dynamic time warping distance algorithm (Dynamic Time Warping, DTW) is used to calculate the distance between every two sample load data in the multiple sample load data to obtain an S×S distance matrix. Each element in the distance matrix represents the distance between two sample load data.

[0071] Optionally, for each column element in the distance matrix, the column elements are summed to obtain multiple column element sums, and the sample load data corresponding to the smallest column element sum among the multiple column element sums is determined as the central template power data.

[0072] For example, the initial load data sample library includes 3 sample load data corresponding to the i-th electrical equipment. The distance between every two sample load data is calculated to obtain a 3-row and 3-column distance matrix. The sum of the column elements in the second column is the smallest column element sum, so the second sample load data is determined as the central template power data corresponding to the i-th electrical equipment.

[0073] Optionally, the average template power data corresponding to the i-th electrical device is determined based on the following operations: Based on the dynamic time warping distance algorithm, the warping paths between multiple sample load data and the central template power data are calculated respectively to obtain multiple warping paths; the average template power data is obtained by processing the multiple warping paths using an average value calculation function.

[0074] Optionally, the dynamic time warping distance algorithm is used to calculate the warping paths between each sample load data and the central template power data, obtaining multiple warping paths.

[0075] Optionally, the warping path is the optimal path found from the first point of the sample load data to the last point of the central template power data.

[0076] Optionally, first use the dynamic time warping distance algorithm to calculate the distance matrix between each sample load data and the central template power data, then calculate the minimum cumulative distance from the first point of the sample load data to the last point of the central template power data through the dynamic programming method to form a cumulative distance matrix. Starting from the last point of the central template power data in the cumulative distance matrix, trace back to the first point of the sample load data to find the path with the minimum cumulative distance, obtaining the warping path. The warping path is the optimal alignment path found when measuring the similarity between the sample load data and the central template power data.

[0077] In one embodiment, the warping path is as shown in formula (3):

[0078] (3); where represents that the -th point of the central template power data corresponds to the v-th point of the sample load data, represents the warping path between the multiple sample load data sample load data x and the central template power data u.

[0079] In one embodiment, the average value calculation function mean() is as shown in formula (4):

[0080] (4);

[0081] where represents the average result of the points corresponding to the k-th point of the central template power data u, represents the set of points corresponding to the k-th point of the central template power data u respectively in the multiple sample load data.

[0082] Optionally, based on multiple distortion paths, the points in the multiple sample load data corresponding to the points of the central template power data are averaged using an average value calculation function to obtain average template power data. Set the number of iterations IT, and repeat the calculation of the average template power data each time. By continuously calculating the distance matrix between each sample load data and the average template power data, the average template power data is gradually updated to gradually tend to reflect the overall morphology of all sample load data, and finally the optimal average template power data after IT iterations is obtained.

[0083] Optionally, the cluster template power data corresponding to the i-th electrical device is determined based on the following operations: Determine a relationship judgment threshold according to the average value and standard deviation of the elements in the upper triangular region of the distance matrix, where the upper triangular region represents the region composed of all elements on and above the diagonal from the upper left corner to the lower right corner of the distance matrix; Based on the distance matrix and the relationship judgment threshold, perform clustering processing on the multiple sample load data to obtain A clustering clusters, where A is a positive integer; For each of the A clustering clusters, according to the multiple sample load data in each clustering cluster, obtain A cluster template power data.

[0084] In one embodiment, the clustering process is shown in formula (5):

[0085] (5); where represents the distance value between the sample load data and the sample load data in the distance matrix D, represents the relationship judgment threshold, represents the average value of the elements in the upper triangular region of the distance matrix, represents the standard deviation of the elements in the upper triangular region of the distance matrix, being 0 indicates that the sample load data and the sample load data are not in the same clustering cluster, and being 1 indicates that the sample load data and the sample load data are in the same clustering cluster.

[0086] Optionally, based on the magnitude relationship between each element in the distance matrix and the relationship judgment threshold, determine the similarity relationship between every two sample load data, thereby performing clustering processing on the multiple sample load data to obtain A clustering clusters.

[0087] Optionally, for each of the A clusters, the central template power data corresponding to each cluster can be obtained based on the multiple sample load data in each cluster, so as to determine the central template power data corresponding to this cluster as the cluster template power data corresponding to this cluster, and thus obtain A cluster template power data.

[0088] Optionally, the initial power data template library stores the central template power data, average template power data, and A cluster template power data corresponding to the i-th electrical equipment.

[0089] Optionally, generate the central template power data, average template power data, and cluster template power data with high representativeness of the original waveform based on the multiple sample load data, so as to make full use of the template power information to extract more complete and better-consistent target load data, and help users better complete the load status identification.

[0090] Optionally, based on the multi-resolution waveform matching algorithm, according to the candidate load matrix and the template power data to be matched, the load recognition result is obtained as follows: perform N frequency downsampling processes on the candidate load matrix to obtain N downsampled candidate load matrices; perform N frequency downsampling processes on the template power data to be matched to obtain N downsampled template power data to be matched; for the n-th frequency downsampling among the N frequency downsamplings, according to the n-th downsampled template power data to be matched and at least one downsampled candidate load data in the n-th downsampled candidate load matrix, obtain the n-th matching matrix, and obtain N matching matrices, where each matching matrix includes at least one matching result, and the matching result represents the distance value between the downsampled template power data to be matched and the downsampled candidate load data, N≥1, 1≤n≤N; determine the target matching result from at least one matching result, and when the target matching result satisfies the preset distance threshold range, determine the downsampled candidate load data corresponding to the target matching result as the target load data, and determine the electrical equipment corresponding to the template power data to be matched as the target electrical equipment corresponding to the target load data.

[0091] Optionally, perform resampling on each candidate load data in the candidate load matrix to generate multiple waveform features at N time resolutions, and obtain N downsampled candidate load matrices. For example, obtain candidate load matrices H1, H2, H3, H4, H5, where H5 is the candidate load matrix after the original-resolution candidate load data is downsampled by 5 times.

[0092] Optionally, perform the same number of frequency downsampling processes on the template power data to be matched to obtain multiple downsampled template power data to be matched, such as Y1, Y2, Y3, Y4, Y5.

[0093] Optionally, the frequency of the nth template power data to be matched after downscaling is the same as that of the nth candidate load matrix after downscaling.

[0094] Optionally, use the dynamic time warping distance algorithm to calculate the distance between the nth template power data to be matched after downscaling and each downscaled candidate load data in the nth candidate load matrix after downscaling, to obtain the nth matching matrix.

[0095] Optionally, each matching matrix includes at least one matching result. Determine the target matching result from at least one matching result among the N matching matrices. When the target matching result satisfies the preset distance threshold range, determine the downscaled candidate load data corresponding to the target matching result as the target load data, and determine the electrical device corresponding to the template power data to be matched as the target electrical device corresponding to the target load data.

[0096] Optionally, determining the target matching result from at least one matching result includes: determining the smallest matching result among at least one matching result as the target matching result.

[0097] Optionally, the preset distance threshold range can be determined according to the average value and standard deviation of the elements in the upper triangular region of the distance matrix.

[0098] In one embodiment, the matching process for the long transient event type is shown in formula (6):

[0099] (6);

[0100] Wherein, represents the target matching result, represents the preset distance threshold range, represents the average value of the elements in the upper triangular region of the distance matrix, represents the standard deviation of the elements in the upper triangular region of the distance matrix. Sample being True represents successful matching, and Sample being True represents failed matching.

[0101] Optionally, the target matching result satisfying the preset distance threshold range means that the downscaled candidate load data corresponding to the target matching result and the template power data to be matched belong to the power conversion process of the same type of electrical device.

[0102] Optionally, determine the downscaled candidate load data corresponding to the target matching result as the target load data; determine the electrical device corresponding to the template power data to be matched as the target electrical device corresponding to the target load data.

[0103] Optionally, in the case of a matching failure, determine the template power data to be matched in the next matching process according to the matching order, re-determine the sliding window length range and the candidate load matrix, and then match the template power data to be matched and the candidate load matrix until the target load data is matched or all the template power data in the initial power data template library fail to match.

[0104] Optionally, the matching order may be to sort the multiple template power data for the same electrical device in descending order according to the length, and sequentially select the template power data to be matched next from the first position. If all the multiple template power data for the same electrical device fail to match, then select the multiple template power data for the next electrical device for matching.

[0105] Optionally, the load identification method further includes: determining a first power difference according to the power values corresponding to the section start point and the section end point of the template power data to be matched respectively; determining a second power difference according to the power values corresponding to the section start point and the section end point of the target load data respectively; determining the similarity between the target load data and the template power data to be matched according to the first power difference and the second power difference; in the case where the similarity is less than a preset similarity threshold, adding the target load data to the initial load data sample library to obtain a target load data sample library; determining the sample quantity of the sample load data in the target load data sample library; in the case where the sample quantity is greater than a preset quantity threshold, updating the initial power data template library according to the target load data sample library, wherein the template power data to be matched is stored in the initial power data template library.

[0106] Optionally, in the case of a successful match, perform a second verification process on the template power data to be matched and the target load data to judge the validity of the match.

[0107] In one embodiment, the similarity As shown in formula (7):

[0108] (7); where represents the power value corresponding to the section end point of the template power data to be matched, represents the power value corresponding to the section start point of the template power data to be matched, represents the power value corresponding to the section end point of the template power data to be matched, represents the power value corresponding to the section start point of the template power data to be matched.

[0109] Optionally, a similarity less than a preset similarity threshold indicates that the matching is valid, and the target load data is added to the target load data sample library; otherwise, the matching is valid, the target load data is recorded as an unknown event, and it is stored in the unknown event list. An unknown event refers to a load event type not included in the initial load data sample library, which may be a load event that has not occurred for a known electrical device before, a load event generated by a newly added electrical device, or an aliased load event. An aliased load event refers to a transient process in which the load power corresponding to the detected load event contains multiple different electrical devices during an unstable period.

[0110] Optionally, perform a quantity statistics on the target load data sample library to determine the sample quantity of the sample load data in the target load data sample library; if the sample quantity is greater than a preset quantity threshold, indicating that the batch processing scale is reached, update the template power data of each type corresponding to different electrical devices in the initial power data template library with the sample load data in the target load data sample library, and then obtain an updated power data template library for the next matching.

[0111] Optionally, since the latest template power data corresponding to each personalized electrical device in the scenario is pre-applied to the target load data extraction stage, the problem of low accuracy in matching the load data extracted based on the inherent parameters with the template information is avoided.

[0112] Optionally, the load identification method further includes: in the case where the load event type is a step event type, determine the power tolerance and length of the initial load data, where the length of the initial load data corresponding to the step event type is less than a preset length threshold; based on the power tolerance and length, match multiple template power data to be matched with the initial load data to determine the target template power data corresponding to the initial load data, and determine the electrical device corresponding to the target template power data as the target electrical device corresponding to the initial load data.

[0113] Optionally, in the case where the length of the initial load data is less than a preset length threshold, determine the type of the event section where the initial load data is located as the step event type.

[0114] Optionally, the preset length threshold can be , where is the dataset sampling frequency, is a preset parameter with a value of , and is the length of the longest template power data in the real scenario.

[0115] Optionally, the power tolerance of the initial load data represents the difference between the maximum power value and the minimum power value in the initial load data.

[0116] In one embodiment, the matching process for the step event type is shown in Equation (8):

[0117] (8);

[0118] Wherein, represents the tolerance coefficient, represents the power tolerance of the template power data to be matched, represents the length of the template power data to be matched, represents the power tolerance of the initial load data, represents the length of the initial load data, Sample being True indicates successful matching, and Sample being False indicates failed matching.

[0119] Optionally, the template power data is sequentially selected from the initial power data template library to be matched with the initial load data. In the case of successful matching, the template power data to be matched is determined as the target template power data corresponding to the initial load data, and the electrical equipment corresponding to the target template power data is determined as the target electrical equipment corresponding to the initial load data.

[0120] Optionally, a non-intrusive load monitoring framework (Non-Intrusive Load Monitoring, NILM) is introduced. In the non-intrusive load monitoring framework, load events are divided into step events and long transient events, and different load data extraction and recognition strategies are set according to the load event type, thereby overcoming the problems of poor consistency of load data extracted by conventional event detection algorithms and low recognition accuracy.

[0121] Figure 3 shows a flowchart of the load recognition process based on variable sliding window multi-resolution power matching according to an embodiment of the present invention.

[0122] As Figure 3 shown, the load recognition process includes steps S301 to S311.

[0123] In step S301, an initial power data template library is generated. Go to step S302.

[0124] In step S302, the total power data of electricity is collected and preprocessed. Go to step S303.

[0125] In step S303, load event detection is performed. Go to step S304.

[0126] In step S304, it is determined whether the load event type is a step event type. In the case of a step event type, go to step S305, otherwise go to step S306.

[0127] In step S305, perform matching based on the power tolerance to obtain the load identification result. Proceed to step S307.

[0128] In step S306, obtain the candidate load matrix based on the sliding window length range and the starting point of the target section; then perform matching based on the multi-resolution waveform matching algorithm to obtain the load identification result. Proceed to step S307.

[0129] In step S307, determine whether the load identification result passes the verification. If the verification is successful, proceed to step S309; otherwise, proceed to step S308.

[0130] In step S308, store the target load data in the unknown event list.

[0131] In step S309, add the target load data to the initial load data sample library. Proceed to step S310.

[0132] In step S310, determine whether the number of sample load data in the target load data sample library is greater than the preset number threshold. If so, proceed to step S311; otherwise, proceed to step S302.

[0133] In step S311, update the initial power data template library according to the target load data sample library. Proceed to step S301.

[0134] Optionally, the present invention selects a measured data set with a sampling frequency of 1 Hz and a time span of 7 days. The data set includes the total power data of different electrical appliances. Analyze and identify the data set according to the load identification method of the present invention and the existing load detection method. Calculate the recognition accuracy rate, recall rate, and precision rate according to the number of correctly identified load data samples or load events, the number of misidentified load data samples or load events, and the number of samples or events that are not successfully identified among all real load data samples or events.

[0135] Table 1 shows the comparison effect of load identification based on the method of the present invention and the existing method.

[0136] Table 1 Comparison effect

[0137]

[0138] Optionally, as can be seen from Table 1, compared with the existing method, the present invention has higher accuracy rate and precision rate for identifying the extracted target load data. At the same time, it represents that the present invention extracts relatively complete target load data, reflects a higher load decomposition ability, helps users better understand the power consumption status of each load in the family, so as to achieve the purpose of energy saving.

[0139] Based on the above load identification method, the present invention further provides a load identification device based on variable sliding window multi-resolution power matching. A detailed description of this device will be given in conjunction with Figure 4 and will be described in detail below.

[0140] Figure 4 Fig. shows a structural block diagram of a load identification device based on variable sliding window multi-resolution power matching according to an embodiment of the present invention.

[0141] As Figure 4 shown, the load identification device 400 of this embodiment includes a detection module 410, a judgment module 420, a first determination module 430, a second determination module 440, an interception module 450, and an identification module 460.

[0142] The detection module 410 is configured to perform load event detection on the total power data of the power grid to obtain initial load data. In one embodiment, the detection module 410 may be configured to execute the operation S110 described above, which will not be elaborated here.

[0143] The judgment module 420 is configured to determine the type of load event according to the length of the initial load data. In one embodiment, the judgment module 420 may be configured to execute the operation S120 described above, which will not be elaborated here

[0144] The first determination module 430 is configured to determine a sliding window length range corresponding to the template power data to be matched according to the length of the template power data to be matched when it is determined that the type of load event is a long transient event type, where the length of the initial load data corresponding to the long transient event type is greater than or equal to a preset length threshold. In one embodiment, the first determination module 430 may be configured to execute the operation S130 described above, which will not be elaborated here.

[0145] The second determination module 440 is configured to determine C target section start points according to the start point of the initial load data section and the preset number of section start points, where C is a positive integer. In one embodiment, the second determination module 440 may be configured to execute the operation S140 described above, which will not be elaborated here.

[0146] The interception module 450 is configured to perform dynamic data interception on the total power data of the power grid for each of the C target section start points according to the sliding window length range and each target section start point to obtain a candidate load matrix. In one embodiment, the interception module 450 may be configured to execute the operation S150 described above, which will not be elaborated here.

[0147] An identification module 460 is configured to determine a load identification result based on a multi-resolution waveform matching algorithm according to a candidate load matrix and template power data to be matched. The load identification result includes target load data and a target electrical device corresponding to the target load data. In one embodiment, the identification module 460 may be configured to perform the operation S160 described above, which will not be elaborated herein.

[0148] Optionally, the identification module 460 includes a first identification sub-module, a second identification sub-module, a third identification sub-module, and a fourth identification sub-module.

[0149] The first identification sub-module is configured to perform N downsampling processes on the candidate load matrix to obtain N downsampled candidate load matrices.

[0150] The second identification sub-module is configured to perform N downsampling processes on the template power data to be matched to obtain N downsampled template power data to be matched.

[0151] The third identification sub-module is configured to, for the nth downsampling among the N downsamplings, determine an nth matching matrix according to at least one downsampled candidate load data in the nth downsampled template power data to be matched and the nth downsampled candidate load matrix, so as to obtain N matching matrices, where each matching matrix includes at least one matching result, and the matching result represents a distance value between the downsampled template power data to be matched and the downsampled candidate load data, N≥1, 1≤n≤N.

[0152] The fourth identification sub-module is configured to determine a target matching result from at least one matching result. When the target matching result meets a preset distance threshold range, the downsampled candidate load data corresponding to the target matching result is determined as the target load data, and the electrical device corresponding to the template power data to be matched is determined as the target electrical device corresponding to the target load data.

[0153] Optionally, the fourth identification sub-module includes a first identification unit.

[0154] The first identification unit is configured to determine the minimum matching result among at least one matching result as the target matching result.

[0155] Optionally, the load device 400 further includes a third determination module, a fourth determination module, a fifth determination module, a first update module, a sixth determination module, and a second update module.

[0156] The third determination module is configured to determine a first power difference according to the power values corresponding to the section start point and the section end point of the template power data to be matched respectively.

[0157] The fourth determination module is configured to determine a second power difference according to the power values corresponding to the section start point and the section end point of the target load data.

[0158] The fifth determination module is configured to determine the similarity between the target load data and the template power data to be matched according to the first power difference and the second power difference.

[0159] The first update module is configured to add the target load data to the initial load data sample library to obtain a target load data sample library when the similarity is less than a preset similarity threshold.

[0160] The sixth determination module is configured to determine the sample quantity of the sample load data in the target load data sample library.

[0161] The second update module is configured to update the initial power data template library according to the target load data sample library when the sample quantity is greater than a preset quantity threshold, wherein the template power data to be matched is stored in the initial power data template library.

[0162] Optionally, the load device 400 further includes a first generation module, a second generation module, and a third generation module.

[0163] The first generation module is configured to calculate the distance between each two of the multiple sample load data by using the dynamic time warping distance algorithm to obtain a distance matrix.

[0164] The second generation module is configured to sum the column elements in the distance matrix to obtain a plurality of column element sums.

[0165] The third generation module is configured to determine the sample load data corresponding to the minimum column element sum among the multiple column element sums as the central template power data.

[0166] Optionally, the load device 400 further includes a fourth generation module and a fifth generation module.

[0167] The fourth generation module is configured to calculate the warping paths between the multiple sample load data and the central template power data respectively based on the dynamic time warping distance algorithm to obtain a plurality of warping paths.

[0168] The fifth generation module is configured to process the multiple warping paths by using an average value calculation function to obtain an average template power data.

[0169] Optionally, the load device 400 further includes a sixth generation module, a seventh generation module, and an eighth generation module.

[0170] The sixth generation module is used to determine a relationship judgment threshold according to the average value and standard deviation of the elements in the upper triangular region of the distance matrix, where the upper triangular region represents the region composed of all the elements on and above the diagonal from the upper left corner to the lower right corner of the distance matrix.

[0171] The seventh generation module is used to perform clustering processing on multiple sample load data based on the distance matrix and the relationship judgment threshold, and obtain A clustering clusters, where A is a positive integer.

[0172] The eighth generation module is used to obtain A cluster template power data for each of the A clustering clusters according to the multiple sample load data in each clustering cluster.

[0173] Optionally, the load device 400 further includes a seventh determination module and a matching module.

[0174] The seventh determination module is used to determine the power tolerance and length of the initial load data when the load event type is a step event type, where the length of the initial load data corresponding to the step event type is less than a preset length threshold.

[0175] The matching module is used to match multiple template power data to be matched and the initial load data based on the power tolerance and length, determine the target template power data corresponding to the initial load data, and determine the electrical device corresponding to the target template power data as the target electrical device corresponding to the initial load data.

[0176] Optionally, the detection module 410 includes a first detection sub-module, a second detection sub-module, a third detection sub-module, a fourth detection sub-module, and a fifth detection sub-module.

[0177] The first detection sub-module is used to intercept section data of the total power data based on a first preset window length to obtain first section power data, where the total power data represents the total data of the power consumption of different electrical devices.

[0178] The second detection sub-module is used to determine a third power difference according to the power values corresponding to the section start point and the section end point of the first section power data.

[0179] The third detection sub-module is used to intercept section data of the first section power data based on a second preset window length to obtain second section power data when the third power difference is greater than or equal to a preset power threshold.

[0180] The fourth detection sub-module is used to determine a fourth power difference according to the power values corresponding to the section start point and the section end point of the second section power data.

[0181] A fifth detection sub-module, configured to determine the second-segment power data as initial load data when the fourth power difference is greater than or equal to a preset power threshold and the length of the second-segment power data is within a preset length range.

[0182] Optionally, any multiple of the detection module 410, the judgment module 420, the first determination module 430, the second determination module 440, the interception module 450, and the recognition module 460 can be combined and implemented in one module, or any one of them can be split into multiple modules. Alternatively, at least part of the functions of one or more of these modules can be combined with at least part of the functions of other modules and implemented in one module. Optionally, at least one of the detection module 410, the judgment module 420, the first determination module 430, the second determination module 440, the interception module 450, and the recognition module 460 can be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array (PLA), a system on chip, a system on substrate, a system on package, an application specific integrated circuit (ASIC), or can be implemented by any other reasonable means such as integrating or packaging circuits, etc., in hardware or firmware, or implemented in any one of the three implementation manners of software, hardware, and firmware, or in an appropriate combination of any several of them. Alternatively, at least one of the detection module 410, the judgment module 420, the first determination module 430, the second determination module 440, the interception module 450, and the recognition module 460 can be at least partially implemented as a computer program module, and when the computer program module is run, the corresponding functions can be executed.

[0183] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagram may represent a module, a segment of a program, or a portion of code that contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions noted in the blocks may occur in a different order than that noted in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, or they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram or flowchart, and combinations of blocks in the block diagram or flowchart, can be implemented by a dedicated hardware-based system that performs the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions. Those skilled in the art will understand that the features described in the various embodiments of the present invention can be combined and / or combined in various ways, even if such combinations or combinations are not explicitly described in the present invention. In particular, without departing from the spirit and teachings of the present invention, the features described in the various embodiments of the present invention can be combined and / or combined in various ways. All such combinations and / or combinations fall within the scope of the present invention.

[0184] The embodiments of the present invention have been described above. However, these embodiments are for illustrative purposes only and are not intended to limit the scope of the present invention. Although the embodiments have been described separately above, this does not mean that the measures in each embodiment cannot be used advantageously in combination. Without departing from the scope of the present invention, those skilled in the art can make various substitutions and modifications, and all such substitutions and modifications should fall within the scope of the present invention.

Claims

1. A load identification method based on variable sliding window multi-resolution power matching, characterized in that: The method comprises: Perform load event detection on the total power data to obtain initial load data, wherein the total power data is the total power time series change data directly collected from the power supply entrance of the power user, the total power time series includes the time series power change data consumed by different power-consuming devices, the initial load data is the power data change section of the process of the power-consuming device switching from the first steady state to the second steady state, the power data change section includes the section start point and the section end point, and the process of switching from the first steady state to the second steady state is a transient process; determining a load event type according to the length of the initial load data; In the case where it is determined that the load event type is a long transient event type, determining a sliding window length range corresponding to the template power data to be matched according to the length of the template power data to be matched, wherein the length of the initial load data corresponding to the long transient event type is greater than or equal to a preset length threshold; Determine C target section starting points according to the section starting point of the initial load data and the number of preset section starting points, where C is a positive integer; For each of the C target section starting points, dynamically intercept the total power data according to the sliding window length range and each of the target section starting points to obtain a candidate load matrix; Based on a multi-resolution waveform matching algorithm, a load identification result is determined according to the candidate load matrix and the template power data to be matched, and the load identification result includes target load data and target electrical equipment corresponding to the target load data.

2. The method according to claim 1, characterized in that The method of determining the load identification result based on the multi-resolution waveform matching algorithm according to the candidate load matrix and the template power data to be matched includes: Performing N frequency reduction processing on the candidate load matrix to obtain N frequency reduced candidate load matrices; Performing N frequency reduction processing on the template power data to be matched to obtain N frequency reduced template power data to be matched; For the nth frequency reduction in N frequency reductions, determine the nth matching matrix according to the template power data to be matched after the nth frequency reduction and at least one candidate load data after the frequency reduction in the candidate load matrix after the nth frequency reduction, so as to obtain N matching matrices, wherein each of the matching matrices includes at least one matching result, and the matching result represents the distance value between the template power data to be matched after the frequency reduction and the candidate load data after the frequency reduction, N≥1, 1≤n≤N; A target matching result is determined from at least one of the matching results. When the target matching result satisfies a preset distance threshold range, the down-converted candidate load data corresponding to the target matching result is determined as the target load data, and the electrical equipment corresponding to the template power data to be matched is determined as the target electrical equipment corresponding to the target load data.

3. The method according to claim 2, characterized in that Determining a target matching result from at least one of the matching results includes: The minimum matching result among at least one of the matching results is determined as the target matching result.

4. The method according to claim 1, characterized in that: The method further comprises: Determine a first power difference value according to power values ​​corresponding to a segment start point and a segment end point of the template power data to be matched; Determine a second power difference value according to power values ​​corresponding to a section start point and a section end point of the target load data; Determining the similarity between the target load data and the template power data to be matched according to the first power difference and the second power difference; When the similarity is less than a preset similarity threshold, the target load data is added to an initial load data sample library to obtain a target load data sample library; Determining the number of samples of the sample load data in the target load data sample library; When the number of samples is greater than a preset number threshold, the initial power data template library is updated according to the target load data sample library, wherein the template power data to be matched is stored in the initial power data template library.

5. The method according to claim 4, characterized in that The initial power data template library includes template power data to be matched corresponding to each of the I types of electrical equipment, the template power data to be matched corresponding to the i-th electrical equipment includes central template power data, average template power data, and cluster template power data, and the initial load data sample library includes multiple sample load data corresponding to the i-th electrical equipment, i I, i, I are positive integers; The central template power data corresponding to the i-th electrical equipment is determined based on the following operations: Calculate the distance between every two of the sample load data in the plurality of sample load data using a dynamic time warping distance algorithm to obtain a distance matrix; Summing the column elements in the distance matrix to obtain a plurality of column element sums; The minimum column element and the corresponding sample load data among the plurality of the column elements and are determined as the central template power data.

6. The method according to claim 5, characterized in that The average template power data corresponding to the i-th electrical device is determined based on the following operations: Based on a dynamic time warping distance algorithm, respectively calculating the distortion paths between the plurality of sample load data and the central template power data to obtain a plurality of distortion paths; The plurality of twisted paths are processed using an average value calculation function to obtain the average template power data.

7. The method according to claim 5, characterized in that The cluster template power data corresponding to the i-th electrical device is determined based on the following operations: Determine the relationship judgment threshold according to the average value and standard deviation of the elements in the upper triangular area of ​​the distance matrix, wherein the upper triangular area represents the area consisting of the diagonal line from the upper left corner to the lower right corner of the distance matrix and all the elements above it; Based on the distance matrix and the relationship judgment threshold, clustering is performed on the plurality of sample load data to obtain A clusters, where A is a positive integer; For each of the A clusters, A cluster template power data are obtained according to a plurality of the sample load data in each cluster.

8. The method according to claim 1, characterized in that The method further comprises: In the case where the load event type is a step event type, determining a power tolerance and a length of the initial load data, wherein the length of the initial load data corresponding to the step event type is less than the preset length threshold; Based on the power tolerance and the length, the multiple template power data to be matched are matched with the initial load data, the target template power data corresponding to the initial load data is determined, and the electrical equipment corresponding to the target template power data is determined as the target electrical equipment corresponding to the initial load data.

9. The method according to claim 1, characterized in that: Perform load event detection on the total power data to obtain the initial load data including: Based on a first preset window length, segment data interception is performed on the total power data to obtain first segment power data, wherein the total power data represents total data of power consumption of different electrical devices; Determine a third power difference value according to power values ​​corresponding to a segment start point and a segment end point of the first segment power data; When the third power difference is greater than or equal to a preset power threshold, segment data interception is performed on the first segment power data based on a second preset window length to obtain second segment power data; Determine a fourth power difference value according to power values ​​corresponding to a segment start point and a segment end point of the second segment power data; When the fourth power difference is greater than or equal to the preset power threshold and the length of the second section power data is within a preset length range, the second section power data is determined as initial load data.

10. A load identification device based on variable sliding window multi-resolution power matching, characterized in that: The device comprises: A detection module is used to perform load event detection on the total power data to obtain initial load data, wherein the total power data is the total power time series change data directly collected from the power supply entrance of the power user, the total power time series includes the time series power change data consumed by different power-consuming devices, the initial load data is the power data change section of the process of the power-consuming device switching from a first steady state to a second steady state, the power data change section includes a section start point and a section end point, and the process of switching from the first steady state to the second steady state is a transient process; A judgment module, used for determining the load event type according to the length of the initial load data; A first determination module is used to determine, when determining that the load event type is a long transient event type, a sliding window length range corresponding to the template power data to be matched according to the length of the template power data to be matched, wherein the length of the initial load data corresponding to the long transient event type is greater than or equal to a preset length threshold; A second determination module is used to determine C target section starting points according to the section starting point of the initial load data and the number of preset section starting points, where C is a positive integer; An interception module is used for dynamically intercepting the total power data for each of the C target section starting points according to the sliding window length range and each of the target section starting points to obtain a candidate load matrix; The identification module is used to determine the load identification result based on the multi-resolution waveform matching algorithm according to the candidate load matrix and the template power data to be matched, and the load identification result includes the target load data and the target electrical equipment corresponding to the target load data.

Images