A load switching detection method, device, equipment and medium of a composite sliding window

Abstract

The application discloses a kind of composite sliding window load switching detection method, device, equipment and medium, by periodically obtaining the current, voltage analog value of intelligent electric energy meter, conversion is the to-be-detected data containing current, voltage and active power effective value;It is input to improved least square model, and the active power trend coefficient is calculated;Based on the mean and standard deviation of the trend coefficient calculated by the preset sliding window, the suspicious load input and cut-out event point is identified according to the determination condition;Extract the current instantaneous value of the period before and after the event point, calculate the normalized cross-correlation function to obtain the waveform similarity, use the decision threshold to screen out abnormal data points, and determine the real event point;Finally, the current waveform corresponding to the real event point is uniquely matched by the Pearson similarity coefficient, and the load switching event recognition is completed.The application effectively solves the problem of large amount of calculation, high miss detection and false detection rate of traditional algorithm under complex working conditions, and improves the detection efficiency and accuracy by improving the model.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a method, apparatus, equipment and medium for detecting load switching of a composite sliding window. Background Technology

[0002] With the development of smart grids and smart homes, users' demands for refined electricity consumption sensing and energy efficiency management are increasing. Non-intrusive load monitoring (NILM) technology, which only requires the installation of data acquisition equipment at the power inlet to identify the operating status of internal appliances, has become a research hotspot in this field due to its significant advantages such as low cost, easy deployment, and non-infringement of user privacy. NILM systems typically include two key components: load event detection and load identification. Among these, the accurate detection of load switching events is the foundation of the entire technology chain, and its performance directly determines the accuracy of subsequent feature extraction and load identification.

[0003] In the process of realizing this invention, the inventors discovered the following defects in the prior art: When dealing with the complex working conditions of frequent switching of multiple electrical appliances and superimposed load changes common in residential users, the existing detection methods not only have a large amount of calculation, but also generally lead to frequent missed detections and false detections, making it difficult to meet the requirements of high precision and low calculation in practical applications. Summary of the Invention

[0004] This invention provides a load switching detection device, equipment, and medium for a composite sliding window, in order to solve the technical problems of large computational load and frequent missed and false detections in existing load switching detection algorithms under complex working conditions with frequent switching of multiple electrical appliances and superimposed load changes.

[0005] According to one aspect of the present invention, a method for detecting load switching of a composite sliding window is provided, comprising:

[0006] The instantaneous simulated values ​​of current and voltage of the target smart energy meter are periodically acquired, and the power load data to be detected is obtained through a specific conversion formula; wherein, the power load data to be detected includes the effective value of current, the effective value of voltage, and the effective value of active power;

[0007] The power load data to be detected is input into the improved least squares model, and the sliding window and historical power sliding window are calculated based on the trend coefficient to obtain the active power trend coefficient corresponding to the power load data to be detected.

[0008] Based on a preset trend coefficient statistical sliding window, the mean and standard deviation of the active power trend coefficient are obtained. Based on the preset judgment conditions for suspicious load switching event points, suspicious load switching event points and suspicious load switching event points are output. The instantaneous simulated value of the periodic current before the event point and the instantaneous simulated value of the periodic current after the event point are extracted. The maximum absolute value of the periodic current before the event point is output as the waveform similarity according to the normalized cross-correlation function. Using a preset judgment threshold, abnormal data points of the suspicious load switching event points and suspicious load switching event points are screened out to obtain the real load switching event points and real load switching event points.

[0009] The instantaneous simulated values ​​of the periodic current corresponding to the actual load switching event point and the actual load disconnection event point are input into the Pearson similarity coefficient formula for unique matching to obtain the complete load switching event.

[0010] According to another aspect of the present invention, a load switching detection device for a composite sliding window is provided, comprising:

[0011] The data acquisition and conversion module is used to periodically acquire the instantaneous analog values ​​of current and voltage of the target smart energy meter, and obtain the power load data to be detected through a specific conversion formula; wherein, the power load data to be detected includes the effective value of current, the effective value of voltage, and the effective value of active power;

[0012] The trend screening module is used to input the power load data to be detected into the improved least squares model, calculate the sliding window and historical power sliding window based on the trend coefficient, and obtain the active power trend coefficient corresponding to the power load data to be detected.

[0013] The waveform verification module is used to obtain the mean and standard deviation of the active power trend coefficient based on a preset trend coefficient statistical sliding window, and output the suspected load input event point and suspected load cut-off event point according to the preset judgment conditions of the suspected load switching event point. It extracts the instantaneous simulated value of the periodic current before the event point and the instantaneous simulated value of the periodic current after the event point, and outputs its maximum absolute value as the waveform similarity according to the normalized cross-correlation function. Using a preset judgment threshold, it filters out the abnormal data points of the suspected load input event point and suspected load cut-off event point to obtain the real load input event point and real load cut-off event point.

[0014] The complete event matching module is used to input the instantaneous simulated values ​​of the periodic current corresponding to the actual load switching event point and the actual load switching event point into the Pearson similarity coefficient formula for unique matching, so as to obtain the complete load switching event.

[0015] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0016] At least one processor; and The memory connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform the load switching event detection method according to any embodiment of the present invention.

[0017] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the load switching event detection method according to any embodiment of the present invention.

[0018] The technical solution of this invention involves periodically acquiring instantaneous simulated current and voltage values ​​from a target smart energy meter, and obtaining power load data to be detected through a specific conversion formula. This power load data includes RMS current, RMS voltage, and RMS active power. The power load data is input into an improved least squares model, and a sliding window and historical power sliding window are calculated based on a trend coefficient to obtain the active power trend coefficient corresponding to the power load data. Then, the sliding window is statistically analyzed based on the preset trend coefficient to obtain the mean and standard deviation of the active power trend coefficient. Finally, based on a preset negative value... The judgment criteria for load switching events output suspicious load input and output event points. The instantaneous simulated values ​​of the periodic current before and after the event point are extracted. The maximum absolute value of these values ​​is output as waveform similarity based on the normalized cross-correlation function. Using a preset decision threshold, abnormal data points from the suspicious load input and output event points are filtered out to obtain the true load input and output event points. Finally, the instantaneous simulated values ​​of the periodic current corresponding to the true load input and output event points are input into the Pearson similarity coefficient formula for unique matching to obtain the complete load switching event. This solves the technical problems of high computational load and frequent false negatives and missed detections in existing load switching detection algorithms under complex operating conditions with frequent switching of multiple electrical appliances and superimposed load changes. By constructing an improved least squares model, load switching event detection can be performed more quickly and effectively, improving the accuracy of load switching event detection and reducing the computational load.

[0019] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0020] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the accompanying drawings involved in the embodiments are now briefly described. Obviously, the drawings in the following description are merely illustrative of some embodiments of the present invention. For those skilled in the art, other forms of drawings can be constructed based on these drawings without creative effort.

[0021] Figure 1 This is a flowchart of a load switching detection method for a composite sliding window provided in Embodiment 1 of the present invention;

[0022] Figure 2 This is a schematic diagram of the results of S130 in the load switching detection method of a composite sliding window provided in Embodiment 1 of the present invention;

[0023] Figure 3 This is a graph showing the results of successfully matched load switching event pairs in a composite sliding window load switching detection method provided in Embodiment 1 of the present invention.

[0024] Figure 4 This is a schematic diagram of the load switching detection device for a composite sliding window provided in Embodiment 2 of the present invention;

[0025] Figure 5 This is a schematic diagram of the structure of an electronic device provided in Embodiment 3 of the present invention; Detailed Implementation

[0026] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0027] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0028] Example 1

[0029] Figure 1 This is a flowchart of a load switching detection method for a composite sliding window according to this application. This embodiment is applicable to detecting load switching events. The method can be executed by a load switching detection device for a composite sliding window, which can be implemented in hardware and / or software and can be configured in an electronic device. Figure 1 As shown, the method includes:

[0030] S110. Periodically acquire the instantaneous simulated current and voltage values ​​of the target smart energy meter, and obtain the power load data to be detected through a specific conversion formula;

[0031] The power load data to be detected includes the effective value of current, the effective value of voltage, and the effective value of active power;

[0032] For example, the target smart meter could be a smart meter for a specific user in a specific building within a residential community. The specific conversion formula could refer to a pre-defined conversion formula.

[0033] Optionally, if a specific conversion formula is: , , ,but It can refer to the effective value of the current over one cycle. It can refer to the effective value of the voltage over one cycle. It can refer to the effective value of active power over one cycle. It can refer to the instantaneous simulated current value at the nth sampling point within the mth period. It can refer to the instantaneous simulated voltage value at the nth sampling point within the mth period; It can refer to the number of sampling points for the instantaneous analog values ​​of current, voltage, and active power in the m-th cycle.

[0034] S120. Input the power load data to be detected into the improved least squares model, calculate the sliding window and historical power sliding window based on the trend coefficient, and obtain the active power trend coefficient corresponding to the power load data to be detected.

[0035] The improved least squares model can refer to a pre-defined least squares model. The trend coefficient calculation sliding window is located after the current active power RMS value sampling point, and its length is a first preset length; the historical power sliding window is located before the current active power RMS value sampling point, and its length is a second preset length. For example, the first preset length can be 25, and the second preset length can be 10.

[0036] Specifically, if the preset improvement yields a least squares model, it can be:

[0037] but Trend coefficient Refers to the first preset length. Refers to the index of the j-th sampling point. This refers to the effective value of active power at the corresponding index. This refers to the moving average of power. Specifically, the moving average of power... use express, Refers to the second preset length. It updates in real time as the data to be detected is input, representing the index of the sampling point at the end of the current calculation window, where k refers to the index of the starting sampling point of the calculation window. use express, express, use express.

[0038] S130. Based on the preset trend coefficient statistical sliding window, the mean and standard deviation of the active power trend coefficient are obtained. Based on the preset judgment conditions for suspicious load switching event points, suspicious load input event points and suspicious load disconnection event points are output. The instantaneous simulated value of the periodic current before the event point and the instantaneous simulated value of the periodic current after the event point are extracted. The maximum absolute value of the periodic current is output as the waveform similarity according to the normalized cross-correlation function. Using the preset judgment threshold, the abnormal data points of the suspicious load input event points and suspicious load disconnection event points are screened out to obtain the real load input event points and real load disconnection event points.

[0039] The trend coefficient calculation sliding window is located after the current active power trend coefficient sampling point, and its length is a third preset length. It is understood that this sliding window is used to slide along the trend coefficient sequence to calculate local statistical characteristics. For example, the third preset length can be 25.

[0040] Optionally, the step of outputting suspicious load input event points and suspicious load cut-off event points based on preset judgment conditions for suspicious load switching event points specifically includes: calculating the mean value of the trend coefficient within the trend coefficient statistical sliding window. and trend coefficient standard deviation .in, The trend coefficient is calculated at the j-th position within the trend coefficient statistical sliding window. It can refer to the third preset length.

[0041] In this embodiment, sequence N is set to indicate suspicious load input event points, and sequence F is set to indicate suspicious load cut-off event points. It is understood that if the trend coefficient at a certain location... If the load is significantly higher than the average level of the current window, it indicates that there is a possibility of load being added; conversely, if it is significantly lower, it indicates that there is a possibility of load being cut off.

[0042] Optionally, the criteria for determining the suspicious load switching event point can be expressed as follows: .in, The preset load input threshold, This is the preset load cut-off threshold. When the condition is met, the load at position m will be cut off. or Marked as 1 otherwise, marked as 0. For example, 1 could represent "yes" or "occurred". For example, a preset load input threshold. It can be 1.25, the preset load cut-off threshold. It can be 0.8.

[0043] Furthermore, the extraction of instantaneous simulated values ​​of periodic current before and after the event point can specifically refer to: for each position m marked as a suspicious event point in sequence N or F, extracting the original current sequence of the g-th power frequency cycle before that point. and the original current sequence of the g-th power frequency cycle after that point .

[0044] For example, its extraction method can be defined as: , Where N is the number of sampling points in one power frequency cycle; g is the set number of cycles. For example, the number of sampling points N in one power frequency cycle can be 128 or 256. The number of cycles g can range from 15 to 200.

[0045] In this embodiment, the step of using the maximum absolute value of the normalized cross-correlation function as the waveform similarity specifically involves calculating... and Normalized cross-correlation function .in, and These are sequences and The mean, This is the time delay. Subsequently, the maximum absolute value of this function is taken as the measure of waveform similarity. .

[0046] Understandable, The value range is the absolute value of [-1, 1]. The closer the value is to 0, the greater the difference in the current waveform before and after the event point, and the more real the load switching event. Conversely, the closer the value is to 1, the more the waveform basically does not change, and the event point may be a misjudgment.

[0047] Among them, the use of a preset decision threshold By filtering out abnormal data points, the actual load input event points and actual load output event points are obtained. The specific implementation method is as follows:

[0048] Set sequence Store the actual load delivery event points, in sequence. Store the actual load cut-off event points.

[0049] For each suspicious load input event point in sequence N, if its corresponding If the point is determined to be a real load input event, it will be added to the sequence. ;like If the value is zero, it means that no actual load has been applied at that point, and it should be removed from the list.

[0050] Similarly, for each suspected load cut-off event point in sequence F, if its corresponding If the point is determined to be the actual load shedding event point, it will be added to the sequence. ;like If the result is negative, it indicates that no actual load shedding has occurred at that point, and it should be removed from the list.

[0051] Optional, decision threshold The value can range from 0.65 to 0.98. For example, A value of 0.75 can be used. Through the above steps, secondary verification of suspicious event points is achieved, effectively improving the accuracy of load event detection.

[0052] In an optional embodiment, the number of sampling points N in one power frequency cycle is 128, and the number of cycles g can be 100. It can take the value 0.9. Calculate. and The normalized cross-correlation function is used, and the maximum absolute value of the function is taken as the measure of waveform similarity. . It is understandable that the suspicious load input event point is the actual load input event point. Figure 2 This is a schematic diagram of the results of S130 in a load switching detection method for a composite sliding window provided in Embodiment 1 of this application. Figure 2 The comparison of current waveforms and normalized cross-correlation function similarity before and after the suspected load switching event point m is shown. The horizontal axis represents the number of period sampling points, the vertical axis represents the original current value, and the upper left corner represents the normalized cross-correlation function similarity.

[0053] S140. Input the instantaneous simulated values ​​of the periodic current corresponding to the actual load switching event point and the actual load switching event point into the Pearson similarity coefficient formula for unique matching to obtain the complete load switching event.

[0054] The purpose of performing unique matching is to correctly pair the event points representing the same load being put into operation with the event points representing the same load being taken out of operation, thereby forming a complete load switching cycle.

[0055] Optionally, inputting the instantaneous simulated value of the periodic current into the Pearson similarity coefficient formula specifically involves calculating the Pearson correlation coefficient between the current sequence corresponding to a real load input event point and the current sequence corresponding to a real load output event point, including: using the formula... To calculate the Pearson correlation coefficient ,in, and These are sequences and The mean, Each event point that has been determined to be a real input event The original current sequence, It is each event point that has been determined to be a real cut-off point. The original current sequence.

[0056] Understandably, the Pearson correlation coefficient is used to measure the degree of linear correlation and shape similarity between two current waveforms. In this embodiment, the value range of this coefficient is [-1, 1]. The closer its value is to 1, the more similar the shape and trend of the two waveforms are, and the more likely they are to originate from the same load; the closer its value is to -1, the more opposite the trends of the two waveforms are; when its value is close to 0, it indicates that there is no linear correlation between the two waveforms, and they are unlikely to belong to the same load.

[0057] Optionally, the specific implementation strategy for the unique match includes the following steps:

[0058] 1. Traversal Calculation: For each event point in the sequence of actual load input events, traverse each event point in the sequence of actual load output events. Calculate the Pearson correlation coefficient of the current sequence corresponding to each possible input-output event point, thereby obtaining a set of similarity coefficients between each input event point and all output event points.

[0059] 2. Find the best candidate: For each input event point, find the cut-out event point corresponding to the largest coefficient from its similarity coefficient set, as its most likely matching object.

[0060] 3. Threshold Decision: A similarity threshold is set. This threshold is used to judge the quality of the match. Only when the maximum similarity coefficient found above is greater than this threshold is the match considered valid, thus forming a candidate complete load switching event pair.

[0061] 4. Ensure uniqueness: During the matching process, a single cutoff event point may be selected as the best match by multiple input event points. In this embodiment, to ensure one-to-one matching, when a conflict occurs, only the pair with the highest similarity coefficient is retained, while other pairs are considered invalid matches and discarded.

[0062] For example, the final output is a list of successfully matched load switching event pairs. Each element in this list, that is, a pairing of an input event point and an output event point, represents a complete identified load switching event.

[0063] In an optional embodiment, the unique matching is performed. Figure 3 This is a graph showing the results of successfully matched load switching events in a composite sliding window load switching detection method provided in Embodiment 1 of this application.

[0064] Example 2

[0065] Figure 4 This is a schematic diagram of a load switching detection device for a composite sliding window provided in Embodiment 2 of this application. The load switching detection device for a composite sliding window provided in this embodiment can be implemented by software and / or hardware, and can be configured in a terminal device or server to implement a load switching detection method for a composite sliding window according to an embodiment of the present invention. Figure 4 As shown, the device includes: a data acquisition and conversion module 210, a trend screening module 220, a waveform verification module 230, and a complete event matching module 240.

[0066] The data acquisition and conversion module 210 is used to periodically acquire the instantaneous analog values ​​of current and voltage of the target smart energy meter, and obtain the power load data to be detected through a specific conversion formula; wherein the power load data to be detected includes the effective value of current, the effective value of voltage, and the effective value of active power.

[0067] The trend screening module 220 is used to input the power load data to be detected into the improved least squares model, calculate the sliding window and historical power sliding window based on the trend coefficient, and obtain the active power trend coefficient corresponding to the power load data to be detected.

[0068] The waveform verification module 230 is used to obtain the mean and standard deviation of the active power trend coefficient according to the preset trend coefficient statistical sliding window, and output the suspected load input event point and suspected load cut-off event point according to the preset judgment conditions of the suspected load switching event point. It extracts the instantaneous simulated value of the periodic current before the event point and the instantaneous simulated value of the periodic current after the event point, outputs its maximum absolute value as the waveform similarity according to the normalized cross-correlation function, and uses the preset judgment threshold to filter out the abnormal data points of the suspected load input event point and suspected load cut-off event point to obtain the real load input event point and real load cut-off event point.

[0069] The complete event matching module 240 is used to input the instantaneous simulated values ​​of the periodic current corresponding to the actual load switching event point and the actual load switching event point into the Pearson similarity coefficient formula for unique matching, so as to obtain the complete load switching event.

[0070] The technical solution of this invention involves periodically acquiring instantaneous simulated current and voltage values ​​from a target smart energy meter, and obtaining power load data to be detected through a specific conversion formula. This power load data includes RMS current, RMS voltage, and RMS active power. The power load data is input into an improved least squares model, and a sliding window and historical power sliding window are calculated based on a trend coefficient to obtain the active power trend coefficient corresponding to the power load data. Then, the sliding window is statistically analyzed based on the preset trend coefficient to obtain the mean and standard deviation of the active power trend coefficient. Finally, based on a preset negative value... The judgment criteria for load switching events output suspicious load input and output event points. The instantaneous simulated values ​​of the periodic current before and after the event point are extracted. The maximum absolute value of these values ​​is output as waveform similarity based on the normalized cross-correlation function. Using a preset decision threshold, abnormal data points from the suspicious load input and output event points are filtered out to obtain the true load input and output event points. Finally, the instantaneous simulated values ​​of the periodic current corresponding to the true load input and output event points are input into the Pearson similarity coefficient formula for unique matching to obtain the complete load switching event. This solves the technical problems of high computational load and frequent false negatives and missed detections in existing load switching detection algorithms under complex operating conditions with frequent switching of multiple electrical appliances and superimposed load changes. By constructing an improved least squares model, load switching event detection can be performed more quickly and effectively, improving the accuracy of load switching event detection and reducing the computational load. By using cross-correlation function filtering and Pearson similarity coefficient unique matching, the problem of frequent missed and false detections of load switching events is effectively reduced.

[0071] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.

[0072] The aforementioned load switching detection device for a composite sliding window can execute the load switching detection method for a composite sliding window provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects for executing the load switching detection method for a composite sliding window.

[0073] Example 3

[0074] Figure 5 A schematic diagram of the electronic device 310 according to Embodiment 3 of this application is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0075] like Figure 5 As shown, the electronic device 310 includes at least one processor 320 and a memory, such as a read-only memory (ROM) 330 or a random access memory (RAM) 340, communicatively connected to the at least one processor 320. The memory stores computer programs executable by the at least one processor. The processor 320 can perform various appropriate actions and processes based on the computer program stored in the ROM 330 or loaded into the RAM 340 from storage unit 390. The RAM 340 may also store various programs and data required for the operation of the electronic device 310. The processor 320, ROM 330, and RAM 340 are interconnected via a bus 350. An input / output (I / O) interface 360 ​​is also connected to the bus 350.

[0076] Multiple components in electronic device 310 are connected to I / O interface 360, including: input unit 370, such as keyboard, mouse, etc.; output unit 380, such as various types of monitors, speakers, etc.; storage unit 390, such as disk, optical disk, etc.; and communication unit 3100, such as network card, modem, wireless transceiver, etc. Communication unit 3100 allows electronic device 310 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0077] Processor 320 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 320 include, but are not limited to, central processing unit (CPU), graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any suitable processor, controller, microcontroller, etc. Processor 320 performs the various methods and processes described above, such as a composite sliding window load switching detection method.

[0078] In some embodiments, a load switching detection method for a composite sliding window can be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 390. In some embodiments, the computer program can be received from an external device or network by communication unit 3100, stored in storage unit 390 and / or read-only memory (ROM) 330 after receipt, and then loaded and / or installed into random access memory (RAM) 340 for execution by processor 320. When the computer program is loaded into RAM 340 and executed by processor 320, one or more steps of the load switching detection method for a composite sliding window described above can be performed. In other embodiments, processor 320 can also be configured, via firmware or any other suitable means, to execute the load switching detection method for a composite sliding window.

[0079] The method includes: periodically acquiring instantaneous simulated current and voltage values ​​of a target smart energy meter, and obtaining power load data to be detected through a specific conversion formula; wherein, the power load data to be detected includes effective values ​​of current, voltage, and active power; inputting the power load data to be detected into an improved least squares model, calculating a sliding window and a historical power sliding window based on a trend coefficient to obtain the active power trend coefficient corresponding to the power load data to be detected, then statistically analyzing the sliding window based on the preset trend coefficient to obtain the mean and standard deviation of the active power trend coefficient, and finally, based on a preset suspicious load switching event... The system outputs suspicious load input and suspicious load output event points based on the judgment criteria. It extracts the instantaneous simulated values ​​of the periodic current before and after the event point, and outputs their maximum absolute values ​​as waveform similarity according to the normalized cross-correlation function. Using a preset decision threshold, it filters out abnormal data points of the suspicious load input and suspicious load output event points to obtain the true load input and true load output event points. Finally, it inputs the instantaneous simulated values ​​of the periodic current corresponding to the true load input and true load output event points into the Pearson similarity coefficient formula for unique matching to obtain the complete load input and output events.

[0080] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0081] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0082] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0083] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0084] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0085] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is established by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product in the cloud computing service system to solve the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0086] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0087] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

[0088] Example 4

[0089] Embodiment 4 of the present invention also provides a computer-readable storage medium, wherein the computer-readable instructions, when executed by a computer processor, are used to perform a load switching detection method with a composite sliding window. The method includes: acquiring periodically acquired instantaneous analog values ​​of current and voltage from a target smart energy meter, and obtaining power load data to be detected through a specific conversion formula; wherein the power load data to be detected includes effective values ​​of current, voltage, and active power; inputting the power load data to be detected into an improved least squares model; calculating a sliding window and a historical power sliding window based on a trend coefficient to obtain an active power trend coefficient corresponding to the power load data to be detected; and then statistically analyzing the sliding window based on a preset trend coefficient. The mean and standard deviation of the active power trend coefficient are obtained, and the suspected load switching event points and suspected load disconnection event points are output according to the preset judgment conditions of suspected load switching event points. The instantaneous simulated values ​​of the periodic current before and after the event point are extracted, and their maximum absolute values ​​are output as waveform similarity according to the normalized cross-correlation function. Using the preset judgment threshold, abnormal data points of the suspected load switching event points and suspected load disconnection event points are screened out to obtain the real load switching event points and real load disconnection event points. Finally, the instantaneous simulated values ​​of the periodic current corresponding to the real load switching event points and real load disconnection event points are input into the Pearson similarity coefficient formula for unique matching to obtain the complete load switching event.

[0090] Of course, the computer-executable instructions provided in the embodiments of the present invention, which include a computer-readable storage medium, are not limited to the method operations described above, but can also perform related operations in the load switching detection method of the composite sliding window provided in any embodiment of the present invention.

[0091] Based on the above description of the implementation methods, those skilled in the art can clearly understand that the present invention can be implemented using software and necessary general-purpose hardware, and of course, it can also be implemented using hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ROM), random access memory (RAM), flash memory, hard disk, or optical disk, etc., including several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0092] It is worth noting that in the embodiments of the load switching detection device for the composite sliding window described above, the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of each functional unit are only for easy differentiation and are not used to limit the scope of protection of the present invention.

[0093] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for detecting load switching of a composite sliding window, characterized in that, include: The instantaneous simulated values ​​of current and voltage of the target smart energy meter are periodically acquired, and the power load data to be detected is obtained through a conversion formula; wherein, the power load data to be detected includes the effective value of current, the effective value of voltage, and the effective value of active power; The power load data to be detected is input into the improved least squares model, and the active power trend coefficient corresponding to the power load data to be detected is obtained based on the sliding window used to calculate the trend coefficient and the historical power sliding window. In the improved least squares model, the sliding window used to calculate the trend coefficient is located after the current active power effective value sampling point, and its length is a first preset length; the historical power sliding window is located before the current active power effective value sampling point, and its length is a second preset length. The improved least squares model is as follows: but Trend coefficient Refers to the first preset length. Refers to the index of the j-th sampling point. This refers to the effective value of active power at the corresponding index. The moving average of power refers to the power moving average. use express, Refers to the second preset length. It updates in real time as the data to be detected is input, representing the index of the sampling point at the end of the current calculation window, where k refers to the index of the starting sampling point of the calculation window. use express, express, use express; Based on a preset sliding window for statistical trend coefficients, the mean and standard deviation of the active power trend coefficients are obtained. Based on the mean and standard deviation of the active power trend coefficients, judgment conditions for suspicious composite switching event points are set, and suspicious load input event points and suspicious load cut-off event points are output according to the judgment conditions. The instantaneous simulated value of the periodic current before the event point and the instantaneous simulated value of the periodic current after the event point are extracted. The maximum absolute value of the periodic current before the event point is output as the waveform similarity according to the normalized cross-correlation function. Using a preset decision threshold, abnormal data points of the suspicious load input event points and suspicious load cut-off event points are screened out to obtain the real load input event points and real load cut-off event points. The instantaneous simulated values ​​of the periodic current corresponding to the actual load switching event point and the actual load disconnection event point are input into the Pearson similarity coefficient formula for unique matching to obtain the complete load switching event.

2. The method according to claim 1, characterized in that, The waveform similarity assessment is achieved through a normalized cross-correlation function, and a preset decision threshold is used to complete the screening.

3. The method according to claim 2, characterized in that, The unique match is achieved by calculating the similarity coefficient between current waveforms.

4. A load switching detection device for a composite sliding window, characterized in that, The device is used to perform the load switching detection method for a composite sliding window as described in claim 1, and the device includes: The data acquisition and conversion module is used to periodically acquire the instantaneous analog values ​​of current and voltage of the target smart energy meter, and obtain the power load data to be detected through conversion formula; wherein, the power load data to be detected includes the effective value of current, the effective value of voltage, and the effective value of active power; The trend screening module is used to input the power load data to be detected into the improved least squares model, and obtain the active power trend coefficient corresponding to the power load data to be detected based on the sliding window used to calculate the trend coefficient and the historical power sliding window. The waveform verification module is used to obtain the mean and standard deviation of the active power trend coefficient based on a preset sliding window for statistical trend coefficients, and output suspicious load input event points and suspicious load cut-off event points according to preset judgment conditions for suspicious load switching event points. It extracts the instantaneous simulated value of the periodic current before the event point and the instantaneous simulated value of the periodic current after the event point, and outputs its maximum absolute value as waveform similarity according to the normalized cross-correlation function. Using a preset judgment threshold, it filters out abnormal data points of the suspicious load input event points and suspicious load cut-off event points to obtain the real load input event points and real load cut-off event points. The complete event matching module is used to input the instantaneous simulated values ​​of the periodic current corresponding to the actual load switching event point and the actual load switching event point into the Pearson similarity coefficient formula for unique matching, so as to obtain the complete load switching event.

5. An electronic device, characterized in that, The electronic device includes: 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, which is then executed by the at least one processor to enable the at least one processor to perform a load switching detection method for a composite sliding window according to any one of claims 1-3.

6. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute and implement the load switching detection method for a composite sliding window according to any one of claims 1-3.

Images