Low-voltage transformer area monitoring data calibration method and device based on multi-source information

Abstract

The invention provides a low-voltage transformer area monitoring data calibration method and device based on multi-source information. According to the method, a three-phase current value at the head end of a distribution transformer is acquired as correction comparison data, and user-side time sequence data is acquired through an intelligent electric meter to obtain to-be-corrected data. And analyzing deviation and identifying abnormal data in combination with a low-voltage topological line-user connection relationship. And correcting the abnormality by using the historical time sequence data, and generating target power consumption data. According to the method, deviation analysis and historical data correction are implemented by using the three-phase current value of the head end of the distribution transformer, the user-side intelligent electric meter data and the low-voltage topological line-user connection relationship, abnormal data are effectively identified and corrected, accurate target power consumption data are obtained, and the accuracy of the target power consumption data is improved. The problems that in the prior art, a data calibration method depends on hardware upgrading, cost is high, algorithm complexity is high, and applicability is poor are solved.

Description

Technical Field

[0001] The present invention relates to the technical field of low-voltage substation data quality improvement, and in particular to a low-voltage substation monitoring data calibration method based on multi-source information, a low-voltage substation monitoring data calibration device based on multi-source information, a computer-readable storage medium and a distribution network. Background Art

[0002] Smart meters are core components in low-voltage distribution networks. They can collect and record massive amounts of user electricity consumption data, which are the basis for realizing advanced applications such as low-voltage area topology identification, line loss analysis, and power quality management. However, in actual operation, smart meters are easily affected by problems such as excessive metering errors and equipment aging, resulting in noise in the data. At the same time, metering anomalies such as flyaway and reverse travel will further cause data anomalies. These problems significantly reduce the accuracy of the data and directly affect the effects of various advanced applications based on low-voltage distribution network data.

[0003] In order to improve data accuracy, it is usually necessary to identify and correct data noise and data anomalies. Traditional methods mainly rely on hardware upgrades of intelligent measurement systems, such as replacing smart meters with higher measurement accuracy, but such solutions often have high investment costs and complex engineering implementation. Algorithm optimization methods based on data analysis are gradually emerging, providing new ideas for solving data quality problems at a low cost. However, these methods also have certain limitations.

[0004] Although the existing abnormal data detection and repair methods based on deep neural networks can achieve high accuracy in experimental environments, they require a large amount of complete data for training, and the model design is complex. Retraining is required to adapt to new scenarios, which increases time and computing costs. In addition, although the matrix repair method based on optimization theory can repair data missing and anomalies at the same time, the model complexity is high, parameter tuning is difficult, and the computational overhead increases significantly with the expansion of the substation scale. In general, the existing technology has not yet achieved an ideal balance between cost, applicability and computational efficiency. It is urgent to explore a low-cost, high-efficiency method for improving the accuracy of low-voltage substation data to meet the needs of actual engineering. Summary of the invention

[0005] The main purpose of the present application is to provide a low-voltage substation monitoring data calibration method based on multi-source information, a low-voltage substation monitoring data calibration device based on multi-source information, a computer-readable storage medium and a distribution network, so as to solve the problems that the low-voltage substation data calibration method in at least the prior art relies on high hardware upgrade costs, high algorithm complexity and poor applicability.

[0006] In order to achieve the above-mentioned purpose, according to one aspect of the present application, a low-voltage substation monitoring data calibration method based on multi-source information is provided, including: obtaining the three-phase current value at the head end of the low-voltage distribution transformer to obtain correction comparison data; obtaining the current, voltage and power timing data on the user side through the smart meter to obtain the data to be corrected; obtaining the low-voltage topology line-user connection relationship, the low-voltage topology line-user connection relationship includes the connection relationship between the primary branch line of the low-voltage substation and the smart meter on the user side, and the primary branch line is connected to the low-voltage distribution transformer; based on the low-voltage topology line-user connection relationship, the correction comparison data and the data to be corrected are analyzed for deviations, and when the deviation is greater than a preset value, the corresponding data to be corrected is determined as abnormal data; obtaining the current, voltage and power timing data on the user side at a recording time before the data to be corrected to obtain historical correction data, and correcting the data to be corrected at least based on the historical correction data to obtain target power consumption data.

[0007] Optionally, a deviation analysis is performed on the correction comparison data and the data to be corrected based on the low-voltage topology line-user connection relationship, and when the deviation is greater than a preset value, the corresponding data to be corrected is determined as abnormal data, including: performing a deviation analysis based on the three-phase current value in the correction comparison data and the current in the data to be corrected, and performing an abnormality diagnosis based on the deviation and a first threshold; when the abnormality diagnosis fails, clustering is performed based on the voltage in the data to be corrected, and sorting is performed based on the voltages in the same clustering cluster, and when the deviation of the sorting result is greater than a second threshold, the corresponding data to be corrected is determined as abnormal data.

[0008] Optionally, a deviation analysis is performed based on the three-phase current values ​​in the correction comparison data and the current in the data to be corrected, and an abnormality diagnosis is performed based on the deviation and a first threshold, including: calculating the difference between the three-phase current values ​​in the correction comparison data and the sum of the currents in the data to be corrected to obtain a target deviation; when the target deviation is greater than or equal to the first threshold, determining that the abnormal data exists in the data to be corrected at the corresponding moment.

[0009] Optionally, deviation analysis is performed based on the voltage in the data to be corrected, and clustering is performed based on the voltages of different smart meters, and sorting is performed based on the voltages in the same clustering cluster. When the deviation of the sorting result is greater than a second threshold, the corresponding data to be corrected is determined as abnormal data, including: clustering based on the correlation coefficient between the voltage curves of the voltage to obtain multiple target clusters, wherein the correlation coefficient of the voltage in the same clustering cluster is greater than or equal to a third threshold; sorting the smart meters corresponding to the voltage in each of the target clusters according to the time when the abnormal data exists and the time when the abnormal data does not exist, to obtain a first target sequence and a second target sequence; when the sorting deviation of the voltage corresponding to the smart meter in the first target sequence and the second target sequence is greater than the second threshold, the data to be corrected corresponding to the smart meter is determined as the abnormal data.

[0010] Optionally, clustering is performed based on the correlation coefficient between the voltage curves of the voltage to obtain a plurality of target clusters, and the method further comprises: calculating the correlation coefficient based on the voltages of any two user sides: Among them, τ mv is the correlation coefficient between smart meter m and smart meter v, u m,t and u v,t are the voltage values ​​of the smart meter m and the smart meter v at time t, respectively, t=1, 2, ..., T, T is the total number of metering time sections; clustering is performed based on the correlation coefficient to obtain the target cluster: in, is the correlation coefficient threshold of the y-th cluster, Ω cla (y) represents the yth target cluster.

[0011] Optionally, calculating the difference between the three-phase current value in the corrected comparison data and the sum of the currents in the data to be corrected to obtain a target deviation includes: substituting the three-phase current value in the corrected comparison data and the current in the data to be corrected into a target formula to obtain the target deviation: in, is the target deviation, is the three-phase current value of the j-th primary branch line at time t, represents the current value of the smart meter b at time t, t=1, 2, ..., T, T is the total number of measurement time sections, ψ j is the set of smart meters connected to the jth primary branch line, and L is the set of primary branch lines.

[0012] Optionally, the data to be corrected is corrected at least based on the historical correction data to obtain target power consumption data, including: obtaining the current in the historical data that is separated from the abnormal data by a first preset time length and a second preset time length to obtain a first target current and a second target current, calculating the average of the first target current and the second target current and replacing the current in the abnormal data; obtaining a first target power and a second target power based on the power in the historical data that is separated from the abnormal data by the first preset time length and the second preset time length, calculating the average of the first target power and the second target power and replacing the power in the abnormal data; obtaining the voltage of the smart meter adjacent to the number of the smart meter corresponding to the abnormal data in the data to be corrected to obtain a first target voltage and a second target voltage, calculating the average of the first target voltage and the second target voltage and replacing the power in the abnormal data.

[0013] According to another aspect of the present application, a low-voltage substation monitoring data calibration device based on multi-source information is provided, the device comprising: a first acquisition unit, used to acquire the three-phase current value of the head end of the low-voltage distribution transformer to obtain correction comparison data; a second acquisition unit, used to acquire the current, voltage and power timing data on the user side through the smart meter to obtain the data to be corrected; a third acquisition unit, used to acquire the low-voltage topology line-user connection relationship, the low-voltage topology line-user connection relationship includes the connection relationship between the primary branch line of the low-voltage substation and the smart meter on the user side, and the primary branch line is connected to the low-voltage distribution transformer; a determination unit, used to perform deviation analysis on the correction comparison data and the data to be corrected based on the low-voltage topology line-user connection relationship, and when the deviation is greater than a preset value, the corresponding data to be corrected is determined as abnormal data; a correction unit, used to acquire the current, voltage and power timing data on the user side before the recording time of the data to be corrected, obtain historical correction data, and correct the data to be corrected at least based on the historical correction data to obtain target power consumption data.

[0014] According to another aspect of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute any one of the methods described.

[0015] According to another aspect of the present application, a distribution network is provided, comprising: one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by the one or more processors, and the one or more programs include methods for executing any one of the methods described.

[0016] By applying the technical solution of the present application, the three-phase current value at the head end of the low-voltage distribution transformer is first obtained to obtain correction comparison data; the current, voltage and power timing data on the user side are obtained through the smart meter to obtain the data to be corrected; then the low-voltage topology line-user connection relationship is obtained, and the low-voltage topology line-user connection relationship includes the connection relationship between the primary branch line of the low-voltage substation and the smart meter on the user side, and the primary branch line is connected to the low-voltage distribution transformer; then, based on the low-voltage topology line-user connection relationship, the correction comparison data and the data to be corrected are analyzed for deviations, and when the deviation is greater than a preset value, the corresponding data to be corrected is determined as abnormal data; finally, the current, voltage and power timing data on the user side at a recording time before the data to be corrected are obtained to obtain historical correction data, and the data to be corrected is corrected at least based on the historical correction data to obtain target power consumption data. This application implements deviation analysis and historical data correction by comprehensively utilizing the three-phase current value at the head end of the distribution transformer, the smart meter data on the user side, and the low-voltage topology line-user connection relationship, effectively identifies and corrects abnormal data, and obtains accurate target electricity consumption data, thereby solving the problems in the prior art that the data calibration method relies on high hardware upgrade costs, high algorithm complexity, and poor applicability. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 A hardware structure block diagram of a mobile terminal for calibrating low-voltage area monitoring data based on multi-source information provided in an embodiment of the present application is shown;

[0018] Figure 2 A schematic flow chart of a method for calibrating low-voltage area monitoring data based on multi-source information provided according to an embodiment of the present application is shown;

[0019] Figure 3 A structural block diagram of a low-voltage area monitoring data calibration device based on multi-source information provided according to an embodiment of the present application is shown.

[0020] The above drawings include the following reference numerals:

[0021] 102, processor; 104, memory; 106, transmission device; 108, input and output devices. DETAILED DESCRIPTION

[0022] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0023] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0024] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present application described here. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0025] As introduced in the background technology, the methods for improving the accuracy of low-voltage area data in the prior art mainly include hardware upgrades and algorithm optimization. Hardware upgrades are costly and complex to implement; algorithm methods require a large amount of data training, have high computational complexity, poor applicability, and are difficult to balance cost and efficiency. In order to solve the problem that the low-voltage area data calibration method in the prior art relies on high hardware upgrade costs, high algorithm complexity, and poor applicability, the embodiments of the present application provide a low-voltage area monitoring data calibration method based on multi-source information, a low-voltage area monitoring data calibration device based on multi-source information, a computer-readable storage medium, and a distribution network.

[0026] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0027] The method embodiments provided in the embodiments of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Taking running on a mobile terminal as an example, Figure 1 1 is a hardware structure block diagram of a mobile terminal for a low voltage area monitoring data calibration method based on multi-source information according to an embodiment of the present invention. Figure 1 As shown, the mobile terminal may include one or more ( Figure 1Only one is shown in the figure) a processor 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing data, wherein the mobile terminal may also include a transmission device 106 and an input / output device 108 for communication functions. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the mobile terminal. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations are shown.

[0028] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the low-voltage area monitoring data calibration method based on multi-source information in the embodiment of the present invention. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, the above method is realized. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories can be connected to the mobile terminal via a network. Examples of the above-mentioned network include but are not limited to the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof. The transmission device 106 is used to receive or send data via a network. The above-mentioned network specific example may include a wireless network provided by a communication provider of the mobile terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0029] In this embodiment, a low-voltage substation monitoring data calibration method based on multi-source information is provided, which runs on a mobile terminal, a computer terminal or a similar computing device. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0030] Figure 2 1 is a flow chart of a method for calibrating low voltage area monitoring data based on multi-source information according to an embodiment of the present application. Figure 2As shown, the method comprises the following steps:

[0031] Step S201, obtaining the three-phase current value of the head end of the low-voltage distribution transformer to obtain correction comparison data;

[0032] Specifically, by obtaining the three-phase current value at the head end of the low-voltage distribution transformer, a reliable benchmark data is provided as calibration comparison data. These current data reflect the actual load conditions of the main power supply points in the distribution network, and can be compared with the smart meter data on the user side to help identify whether there are any abnormalities.

[0033] Step S202, obtaining the current, voltage and power time series data of the user side through the smart meter to obtain the data to be corrected;

[0034] Specifically, the current, voltage and power time series data on the user side reflect the actual power consumption of the user, and they show certain spatiotemporal characteristics over time. During the data correction process, the real-time data provided by the smart meter can be used to identify possible anomalies, such as metering errors, power fluctuations, etc., providing key data support for subsequent data correction.

[0035] Step S203, obtaining a low-voltage topology line-user connection relationship, where the low-voltage topology line-user connection relationship includes a connection relationship between a primary branch line in a low-voltage area and a smart meter on the user side, where the primary branch line is connected to a low-voltage distribution transformer;

[0036] Specifically, the low-voltage topology line-user connection relationship not only describes the power flow path, but also includes how the power consumption data of each user's meter is connected to the distribution transformer. This information is the basis for data deviation analysis and anomaly detection, which helps to accurately identify the time and location of data anomalies.

[0037] Step S204, performing deviation analysis on the correction comparison data and the data to be corrected based on the low-voltage topology line-user connection relationship, and determining the corresponding data to be corrected as abnormal data when the deviation is greater than a preset value;

[0038] Specifically, by calculating the difference between the current at the head end of the first-level branch line in the low-voltage area and the sum of the currents of the smart meter on the user side connected to the branch line, it can be determined whether the data is abnormal. When the difference exceeds the preset threshold, the corresponding data to be corrected can be determined as abnormal data. This method can accurately locate the moment when the data anomaly occurs, ensuring the accuracy and efficiency of data analysis.

[0039] Step S205, obtaining the current, voltage and power time series data of the user side recorded before the data to be corrected, obtaining historical correction data, correcting the data to be corrected at least based on the historical correction data, and obtaining target power consumption data.

[0040] Specifically, the historical current, voltage and power time series data before the data to be corrected are obtained as the basis for correction. Using these historical data, the data to be corrected can be reasonably corrected to ensure its accuracy. For voltage data, the spatial correlation between nodes can be considered; for current and power data, corrections are made based on the cycle law of user electricity consumption, and finally the target electricity consumption data is generated.

[0041] Through this embodiment, the present application provides a method for improving the accuracy of low-voltage area data based on multi-source information, which makes full use of multi-source data such as low-voltage distribution transformers, user-side smart meters, and low-voltage topology line-user connection relationships, and combines spatiotemporal characteristics and deviation analysis to effectively improve the accuracy of data correction. This method does not require additional equipment installation, and can achieve data correction using the data of the existing distribution network system, saving investment costs. Through precise deviation analysis and historical data correction, abnormal data can be effectively identified and corrected, thereby generating high-precision target electricity consumption data. In addition, this method has a small amount of calculation, does not require complex model training or optimization, has strong engineering adaptability, can be widely used in smart meter data calibration in low-voltage areas, and improves the operating efficiency of the distribution network system and the credibility of the data. It solves the problem that the data calibration method in the prior art relies on high hardware upgrade costs, high algorithm complexity, and poor applicability.

[0042] As a possible implementation method, based on the low-voltage topology line-user connection relationship, the correction comparison data and the data to be corrected are analyzed for deviations. When the deviation is greater than a preset value, the corresponding data to be corrected is determined as abnormal data, including:

[0043] Step S301, performing deviation analysis based on the three-phase current values ​​in the correction comparison data and the current in the data to be corrected, and performing abnormality diagnosis based on the deviation and the first threshold;

[0044] Specifically, the three-phase current value at the head end of the low-voltage distribution transformer is first used as a benchmark, and compared with the current value collected in the smart meter on the user side hour by hour, and the deviation is evaluated by calculating the difference between the two. If the difference exceeds the preset first threshold, the data is considered abnormal. This diagnostic method utilizes the stability and consistency of the three-phase current and effectively captures the abnormal characteristics of the current value deviation.

[0045] Step S302, when the abnormality diagnosis fails, clustering is performed based on the voltage in the data to be corrected, and sorting is performed based on the voltage in the same clustering cluster. When the deviation of the sorting result is greater than a second threshold, the corresponding data to be corrected is determined as abnormal data.

[0046] Specifically, when the abnormal diagnosis of step S301 fails, the voltage in the data to be corrected is further subjected to adaptive cluster analysis. Based on the similarity of the voltage curve (such as the correlation coefficient), the user's electric meter is assigned to different clusters according to its voltage characteristics. In each cluster, the voltage values ​​are sorted and compared with the sorting results of normal data. When the sorting deviation exceeds the second threshold, the corresponding data to be corrected can be confirmed as abnormal.

[0047] As a possible implementation, a deviation analysis is performed based on the three-phase current values ​​in the correction comparison data and the current in the data to be corrected, and an abnormality diagnosis is performed based on the deviation and the first threshold, including:

[0048] Step S401, calculating the difference between the three-phase current values ​​in the correction comparison data and the sum of the currents in the data to be corrected, and obtaining the target deviation;

[0049] Specifically, the three-phase current value at the head end of the low-voltage distribution transformer is used as the correction comparison data, and then added to all the user-side current data collected by the smart meter for comparison. By calculating the target deviation, the current anomaly in the low-voltage area can be quickly located, directly reflecting whether there is an anomaly in the overall data.

[0050] Step S402: when the target deviation is greater than or equal to the first threshold, determining whether abnormal data exists in the data to be corrected at the corresponding moment.

[0051] Specifically, the calculated target deviation value is compared with the first threshold. When the target deviation exceeds or equals the preset first threshold, it is judged that the data to be corrected at that moment is abnormal. The setting of the first threshold is based on the national electric energy meter error standard (such as the error of household electric energy meters is 2%), and is adjusted in combination with specific application scenarios. By comparing with the first threshold, abnormal data moments can be quickly screened out to avoid misjudgment of normal data.

[0052] As a possible implementation method, deviation analysis is performed based on the voltage in the data to be corrected, and the voltages of different smart meters are clustered, and the voltages in the same cluster are sorted. When the deviation of the sorting result is greater than the second threshold, the corresponding data to be corrected is determined as abnormal data, including:

[0053] Step S501, clustering is performed based on the correlation coefficient between voltage curves to obtain a plurality of target clusters, wherein the correlation coefficient of the voltage in the same cluster is greater than or equal to a third threshold;

[0054] Specifically, the voltage curves of the user-side smart meters are subjected to correlation analysis, and the correlation coefficients (CCVP, Correlation Coefficient of Voltage Profiles) between the meters are calculated. The correlation threshold (third threshold) is set, and the meters with higher correlation are clustered into a cluster. Clustering based on the correlation of voltage curves can effectively distinguish the voltage characteristics of different devices in the low-voltage area. This method fully considers the spatiotemporal correlation characteristics of voltage data, which helps to narrow the scope of abnormal data identification and improve the efficiency of abnormal location.

[0055] Step S502, sorting the smart meters corresponding to the voltage in each target cluster according to the time when abnormal data exists and when abnormal data does not exist, to obtain a first target sequence and a second target sequence;

[0056] Specifically, for each target cluster, the voltage values ​​of the meter at different times are sorted. The first target sequence corresponds to the voltage sorting at the time when abnormal data exists, and the second target sequence corresponds to the voltage sorting at normal times. The sorting is based on the size of the voltage value, and two sequences are generated to compare the behavior characteristics of the meter in different scenarios.

[0057] Step S503: when the order deviation of the voltage corresponding to the smart meter in the first target sequence and the second target sequence is greater than a second threshold, the to-be-corrected data corresponding to the smart meter is determined as abnormal data.

[0058] Specifically, the meter ranking positions in the first target sequence and the second target sequence are compared one by one, and the ranking deviation of each meter is calculated. If the ranking deviation of a meter exceeds the second threshold, the corresponding data to be corrected is determined to be abnormal data. The setting of the second threshold is based on the national electric energy meter error standard of 2%-4%, which can be adjusted in combination with specific scenarios.

[0059] It can be seen that by clustering and sorting deviation analysis based on the correlation coefficient of the voltage curve, abnormal meters and their data in the low-voltage area can be efficiently identified. The correlation clustering method makes full use of the spatiotemporal characteristics of voltage to classify and process meters with consistent characteristics, thereby improving the pertinence of anomaly detection. Sorting deviation analysis further verifies the significant changes in meters at abnormal times and enhances the accuracy of abnormal data judgment. This method combines clustering and sorting deviation analysis, does not require complex model training or additional equipment support, has the advantages of low computational complexity and strong adaptability, can significantly improve the accuracy of low-voltage area data and reduce the cost of project implementation.

[0060] As a possible implementation manner, clustering is performed based on the correlation coefficient between voltage curves to obtain multiple target clusters. The method further includes:

[0061] Step S601, calculating the correlation coefficient based on the voltages of any two user sides:

[0062]

[0063] Among them, τ mv is the correlation coefficient between smart meter m and smart meter v, u m,t and u v,t are the voltage values ​​of smart meter m and smart meter v at time t, respectively, t = 1, 2, ..., T, T is the total number of measurement time sections;

[0064] Specifically, this formula uses the Pearson correlation coefficient method to measure the correlation between the voltage curves of the two meters, with a value range of [-1,1], τ mv =1 means that the voltage curves of the two meters are completely positively correlated; τ mv =-1 means that the voltage curves of the two meters are completely negatively correlated; τ mv =0 means that the voltage curves of the two meters are not related. By calculating the correlation coefficient, the similarity of the voltage changes of the smart meters on the user side can be effectively quantified, which is convenient for further cluster analysis. This method does not require complex calculations and is suitable for large-scale low-voltage area data processing.

[0065] Step S602: clustering based on the correlation coefficient to obtain the target cluster:

[0066]

[0067] in, is the correlation coefficient threshold of the y-th cluster, Ω cla (y) represents the y-th target cluster.

[0068] Specifically, Indicates the degree of refinement of clustering division; clustering methods can use adaptive algorithms to automatically adjust The clustering accuracy and complexity are balanced to ensure that the voltage curves of the meters within the cluster are highly similar and the differences between clusters are significant. Clustering based on the correlation coefficient can group smart meters with similar voltage characteristics, reducing the complexity of subsequent analysis.

[0069] As a possible implementation method, the difference between the three-phase current values ​​in the correction comparison data and the sum of the currents of the data to be corrected is calculated to obtain the target deviation, including:

[0070] Substitute the three-phase current values ​​in the correction comparison data and the current in the data to be corrected into the target formula to obtain the target deviation:

[0071]

[0072] in, is the target deviation, is the three-phase current value of the j-th primary branch line at time t, represents the current value of the smart meter at time t, t = 1, 2, ..., T, T is the total number of measurement time sections, ψ j is the set of smart meters connected to the jth primary branch line, and L is the set of primary branch lines.

[0073] Specifically, the formula quantifies the consistency of the branch line current by calculating the deviation between the current value at the head end of the branch line and the sum of the current values ​​of its subordinate smart meters, and can intuitively reflect the matching degree between the overall load of the branch line and the measurement data of the smart meter. If the value is too large, it indicates that there may be data anomalies.

[0074] As a possible implementation manner, the data to be corrected is corrected at least based on the historical correction data to obtain the target power consumption data, including:

[0075] Step S701, obtaining the current in the historical data separated from the abnormal data by a first preset time length and a second preset time length, obtaining the first target current and the second target current, calculating the average of the first target current and the second target current, and replacing the current in the abnormal data;

[0076] Step S702, obtaining a first target power and a second target power based on the power in the historical data separated by a first preset time length and a second preset time length from the power in the abnormal data, calculating the average of the first target power and the second target power, and replacing the power in the abnormal data;

[0077] Specifically, the current and power data are determined by the user's electricity consumption characteristics and have no spatial correlation, but the user's electricity consumption has a daily and seasonal time cycle. Therefore, the current and power values ​​at the same time two days before the abnormal data was recorded are extracted from the historical records, and the average values ​​of the current and power at the same time of the previous two days are calculated to replace the corresponding abnormal data.

[0078] Step S703, obtaining the voltage of the smart meter adjacent to the smart meter corresponding to the abnormal data in the data to be corrected, obtaining the first target voltage and the second target voltage, calculating the average of the first target voltage and the second target voltage, and replacing the power in the abnormal data.

[0079] Specifically, voltage data has significant spatial correlation between nodes in low-voltage areas, that is, the voltage values ​​of adjacent meters are usually close, so the voltage anomaly data is replaced by the average voltage value of the two user nodes before and after the user node.

[0080] It can be seen that the use of historical correction data to correct abnormal data item by item ensures the integrity and accuracy of current, power and voltage. At the same time, combined with the periodic characteristics in time and the voltage correlation characteristics in space, the correction results are more in line with the actual power consumption. By replacing abnormal data, the system errors caused by equipment abnormalities or transmission errors are effectively reduced, and the accuracy of the target power consumption data is improved. In summary, this method improves the reliability and engineering applicability of power consumption data by independently correcting current, power and voltage.

[0081] The embodiment of the present application also provides a low-voltage area monitoring data calibration device based on multi-source information. It should be noted that the low-voltage area monitoring data calibration device based on multi-source information in the embodiment of the present application can be used to execute the low-voltage area monitoring data calibration method based on multi-source information provided in the embodiment of the present application. The device is used to implement the above-mentioned embodiments and preferred implementation modes, and those that have been described will not be repeated. As used below, the term "module" can implement a combination of software and / or hardware for a predetermined function. Although the device described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceived.

[0082] The following introduces the low-voltage area monitoring data calibration device based on multi-source information provided in an embodiment of the present application.

[0083] Figure 3 1 is a structural block diagram of a low voltage area monitoring data calibration device based on multi-source information according to an embodiment of the present application. Figure 3 As shown, the device includes: a first acquisition unit 10, a second acquisition unit 20, a third acquisition unit 30, a determination unit 40 and a correction unit 50.

[0084] The first acquisition unit 10 is used to acquire the three-phase current value of the head end of the low-voltage distribution transformer to obtain correction comparison data;

[0085] Specifically, by obtaining the three-phase current value at the head end of the low-voltage distribution transformer, a reliable benchmark data is provided as calibration comparison data. These current data reflect the actual load conditions of the main power supply points in the distribution network, and can be compared with the smart meter data on the user side to help identify whether there are any abnormalities.

[0086] The second acquisition unit 20 is used to acquire the current, voltage and power time series data of the user side through the smart meter to obtain the data to be corrected;

[0087] Specifically, the current, voltage and power time series data on the user side reflect the actual power consumption of the user, and they show certain spatiotemporal characteristics over time. During the data correction process, the real-time data provided by the smart meter can be used to identify possible anomalies, such as metering errors, power fluctuations, etc., providing key data support for subsequent data correction.

[0088] The third acquisition unit 30 is used to acquire a low-voltage topology line-user connection relationship, where the low-voltage topology line-user connection relationship includes a connection relationship between a primary branch line in a low-voltage area and a smart meter on a user side, where the primary branch line is connected to a low-voltage distribution transformer;

[0089] Specifically, the low-voltage topology line-user connection relationship not only describes the power flow path, but also includes how the power consumption data of each user's meter is connected to the distribution transformer. This information is the basis for data deviation analysis and anomaly detection, which helps to accurately identify the time and location of data anomalies.

[0090] A determination unit 40 is used to perform deviation analysis on the correction comparison data and the data to be corrected based on the low voltage topology line-user connection relationship, and when the deviation is greater than a preset value, the corresponding data to be corrected is determined as abnormal data;

[0091] Specifically, by calculating the difference between the current at the head end of the first-level branch line of the low-voltage substation and the sum of the currents of the smart meter on the user side connected to the branch line, it can be determined whether the data is abnormal. When the difference exceeds the preset threshold, the corresponding data to be corrected can be determined as abnormal data. The unit can accurately locate the moment when the data anomaly occurs, ensuring the accuracy and efficiency of data analysis.

[0092] The correction unit 50 is used to obtain the current, voltage and power time series data of the user side before the data to be corrected is recorded, obtain the historical correction data, correct the data to be corrected at least based on the historical correction data, and obtain the target power consumption data.

[0093] Specifically, the historical current, voltage and power time series data before the data to be corrected are obtained as the basis for correction. Using these historical data, the data to be corrected can be reasonably corrected to ensure its accuracy. For voltage data, the spatial correlation between nodes can be considered; for current and power data, corrections are made based on the cycle law of user electricity consumption, and finally the target electricity consumption data is generated.

[0094] Through this embodiment, the present application provides a low-voltage area monitoring data calibration device based on multi-source information, the device includes: a first acquisition unit, a second acquisition unit, a third acquisition unit, a determination unit and a correction unit. The first acquisition unit is used to obtain the three-phase current value at the head end of the low-voltage distribution transformer to obtain the correction comparison data; the second acquisition unit is used to obtain the current, voltage and power timing data on the user side through the smart meter to obtain the data to be corrected; the third acquisition unit is used to obtain the low-voltage topology line-user connection relationship, the low-voltage topology line-user connection relationship includes the connection relationship between the first-level branch line of the low-voltage area and the smart meter on the user side, and the first-level branch line is connected to the low-voltage distribution transformer; the determination unit is used to perform deviation analysis on the correction comparison data and the data to be corrected based on the low-voltage topology line-user connection relationship, and when the deviation is greater than the preset value, the corresponding data to be corrected is determined as abnormal data; the correction unit is used to obtain the current, voltage and power timing data on the user side before the data to be corrected at the recording time, obtain the historical correction data, at least based on the historical correction data to correct the data to be corrected, and obtain the target power consumption data. The device implements deviation analysis and historical data correction by utilizing the three-phase current value at the head end of the distribution transformer, the smart meter data on the user side, and the low-voltage topology line-user connection relationship, effectively identifying and correcting abnormal data to obtain accurate target electricity consumption data, solving the problems of data calibration methods in the existing technology that rely on high hardware upgrade costs, high algorithm complexity, and poor applicability.

[0095] As a possible implementation manner, the determination unit includes: an abnormality diagnosis module and an abnormality determination module.

[0096] An abnormality diagnosis module, used for performing deviation analysis based on the three-phase current values ​​in the correction comparison data and the current in the data to be corrected, and performing abnormality diagnosis based on the deviation and the first threshold value;

[0097] Specifically, the three-phase current value at the head end of the low-voltage distribution transformer is first used as a benchmark, and compared with the current value collected in the smart meter on the user side hour by hour, and the deviation is evaluated by calculating the difference between the two. If the difference exceeds the preset first threshold, the data is considered abnormal. This diagnostic method utilizes the stability and consistency of the three-phase current and effectively captures the abnormal characteristics of the current value deviation.

[0098] The abnormality determination module is used to cluster the voltages in the data to be corrected and sort the voltages in the same cluster clusters when the abnormality diagnosis fails, and to determine the corresponding data to be corrected as abnormal data when the deviation of the sorting result is greater than a second threshold.

[0099] Specifically, when the abnormal diagnosis fails, the voltage in the data to be corrected is further subjected to adaptive cluster analysis. Based on the similarity of the voltage curve (such as the correlation coefficient), the user's electric meter is assigned to different clusters according to its voltage characteristics. In each cluster, the voltage values ​​are sorted and compared with the sorting results of normal data. When the sorting deviation exceeds the second threshold, the corresponding data to be corrected can be confirmed as abnormal.

[0100] As a possible implementation, the abnormality diagnosis module includes: a target deviation submodule and an abnormality existence submodule.

[0101] The target deviation submodule is used to calculate the difference between the three-phase current value in the correction comparison data and the sum of the currents of the data to be corrected to obtain the target deviation;

[0102] Specifically, the three-phase current value at the head end of the low-voltage distribution transformer is used as the correction comparison data, and then added to all the user-side current data collected by the smart meter for comparison. By calculating the target deviation, the current anomaly in the low-voltage area can be quickly located, directly reflecting whether there is an anomaly in the overall data.

[0103] The abnormality existence submodule is used to determine whether abnormal data exists in the data to be corrected at the corresponding moment when the target deviation is greater than or equal to the first threshold.

[0104] Specifically, the calculated target deviation value is compared with the first threshold. When the target deviation exceeds or equals the preset first threshold, it is judged that the data to be corrected at that moment is abnormal. The setting of the first threshold is based on the national electric energy meter error standard (such as the error of household electric energy meters is 2%), and is adjusted in combination with specific application scenarios. By comparing with the first threshold, abnormal data moments can be quickly screened out to avoid misjudgment of normal data.

[0105] As a possible implementation manner, the abnormality determination module includes: a clustering submodule, a sorting submodule and an abnormality determination submodule.

[0106] A clustering submodule, configured to perform clustering based on the correlation coefficient between voltage curves of the voltage to obtain a plurality of target clusters, wherein the correlation coefficient of the voltage in the same cluster is greater than or equal to a third threshold;

[0107] Specifically, the voltage curves of the user-side smart meters are subjected to correlation analysis, and the correlation coefficients (CCVP, Correlation Coefficient of Voltage Profiles) between the meters are calculated. The correlation threshold (third threshold) is set, and the meters with higher correlation are clustered into a cluster. Clustering based on the correlation of voltage curves can effectively distinguish the voltage characteristics of different devices in the low-voltage area. The device fully considers the spatiotemporal correlation characteristics of voltage data, which helps to narrow the scope of abnormal data identification and improve the efficiency of abnormal location.

[0108] A sorting submodule, used to sort the smart meters corresponding to the voltage in each target cluster according to the time when abnormal data exists and when abnormal data does not exist, to obtain a first target sequence and a second target sequence;

[0109] Specifically, for each target cluster, the voltage values ​​of the meter at different times are sorted. The first target sequence corresponds to the voltage sorting at the time when abnormal data exists, and the second target sequence corresponds to the voltage sorting at normal times. The sorting is based on the size of the voltage value, and two sequences are generated to compare the behavior characteristics of the meter in different scenarios.

[0110] The abnormality determination submodule is used to determine the to-be-corrected data corresponding to the smart meter as abnormal data when the order deviation of the voltage corresponding to the smart meter in the first target sequence and the second target sequence is greater than a second threshold.

[0111] Specifically, the meter ranking positions in the first target sequence and the second target sequence are compared one by one, and the ranking deviation of each meter is calculated. If the ranking deviation of a meter exceeds the second threshold, the corresponding data to be corrected is determined to be abnormal data. The setting of the second threshold is based on the national electric energy meter error standard of 2%-4%, which can be adjusted in combination with specific scenarios.

[0112] It can be seen that through clustering and sorting deviation analysis based on the correlation coefficient of the voltage curve, abnormal meters and their data in the low-voltage area can be efficiently identified. The correlation clustering method makes full use of the spatiotemporal characteristics of voltage to classify and process meters with consistent characteristics, thereby improving the pertinence of anomaly detection. Sorting deviation analysis further verifies the significant changes in meters at abnormal times and enhances the accuracy of abnormal data judgment. The device combines clustering and sorting deviation analysis, does not require complex model training or additional equipment support, has the advantages of low computational complexity and strong adaptability, can significantly improve the accuracy of low-voltage area data and reduce project implementation costs.

[0113] As a possible implementation manner, the clustering submodule includes: a calculation submodule and a target clustering submodule.

[0114] The calculation submodule is used to calculate the correlation coefficient based on the voltages of any two user sides:

[0115]

[0116] Among them, τ mv is the correlation coefficient between smart meter m and smart meter v, u m,t and u v,t are the voltage values ​​of smart meter m and smart meter v at time t, respectively, t = 1, 2, ..., T, T is the total number of measurement time sections;

[0117] Specifically, this formula uses the Pearson correlation coefficient method to measure the correlation between the voltage curves of the two meters, with a value range of [-1,1], τ mv =1 means that the voltage curves of the two meters are completely positively correlated; τ mv =-1 means that the voltage curves of the two meters are completely negatively correlated; τ mv =0 means that the voltage curves of the two meters are not related. By calculating the correlation coefficient, the similarity of the voltage changes of the smart meters on the user side can be effectively quantified, which is convenient for further cluster analysis. This method does not require complex calculations and is suitable for large-scale low-voltage area data processing.

[0118] The target clustering submodule is used to perform clustering based on the correlation coefficient to obtain the target clustering clusters:

[0119]

[0120] in, is the correlation coefficient threshold of the y-th cluster, Ω cla (y) represents the y-th target cluster.

[0121] Specifically, Indicates the degree of refinement of clustering division; clustering methods can use adaptive algorithms to automatically adjust The clustering accuracy and complexity are balanced to ensure that the voltage curves of the meters within the cluster are highly similar and the differences between clusters are significant. Clustering based on the correlation coefficient can group smart meters with similar voltage characteristics, reducing the complexity of subsequent analysis.

[0122] As a possible implementation manner, the target deviation submodule includes: a target deviation calculation submodule.

[0123] The target deviation calculation submodule is used to substitute the three-phase current values ​​in the correction comparison data and the current in the data to be corrected into the target formula to obtain the target deviation:

[0124]

[0125] in, is the target deviation, is the three-phase current value of the j-th primary branch line at time t, represents the current value of the smart meter at time t, t = 1, 2, ..., T, T is the total number of measurement time sections, ψ j is the set of smart meters connected to the jth primary branch line, and L is the set of primary branch lines.

[0126] Specifically, the formula quantifies the consistency of the branch line current by calculating the deviation between the current value at the head end of the branch line and the sum of the current values ​​of its subordinate smart meters, and can intuitively reflect the matching degree between the overall load of the branch line and the measurement data of the smart meter. If the value is too large, it indicates that there may be data anomalies.

[0127] As a possible implementation manner, the correction unit includes: a current replacement module, a power replacement module and a voltage replacement module.

[0128] A current replacement module, used to obtain the current in the historical data separated from the abnormal data by a first preset time length and a second preset time length, obtain the first target current and the second target current, calculate the average of the first target current and the second target current, and replace the current in the abnormal data;

[0129] A power replacement module, used to obtain a first target power and a second target power based on the power in the historical data separated by a first preset time length and a second preset time length from the power in the abnormal data, calculate the average of the first target power and the second target power, and replace the power in the abnormal data;

[0130] Specifically, the current and power data are determined by the user's electricity consumption characteristics and have no spatial correlation, but the user's electricity consumption has a daily and seasonal time cycle. Therefore, the current and power values ​​at the same time two days before the abnormal data was recorded are extracted from the historical records, and the average values ​​of the current and power at the same time of the previous two days are calculated to replace the corresponding abnormal data.

[0131] The voltage replacement module is used to obtain the voltage of the smart meter whose number is adjacent to the smart meter corresponding to the abnormal data in the data to be corrected, obtain the first target voltage and the second target voltage, calculate the average of the first target voltage and the second target voltage, and replace the power in the abnormal data.

[0132] Specifically, voltage data has significant spatial correlation between nodes in low-voltage areas, that is, the voltage values ​​of adjacent meters are usually close, so the voltage anomaly data is replaced by the average voltage value of the two user nodes before and after the user node.

[0133] It can be seen that the use of historical correction data to correct abnormal data item by item ensures the integrity and accuracy of current, power and voltage. At the same time, combined with the periodic characteristics in time and the voltage correlation characteristics in space, the correction results are more in line with the actual power consumption. By replacing abnormal data, the system error caused by equipment abnormality or transmission error is effectively reduced, and the accuracy of the target power consumption data is improved. In summary, the device improves the reliability and engineering applicability of power consumption data by independently correcting current, power and voltage.

[0134] The low-voltage area monitoring data calibration device based on multi-source information includes a processor and a memory. The first acquisition unit, the second acquisition unit, the third acquisition unit, the determination unit and the correction unit are all stored in the memory as program units, and the processor executes the program units stored in the memory to implement corresponding functions. The above modules are all located in the same processor; or, the above modules are located in different processors in any combination.

[0135] The processor includes a kernel, which calls the corresponding program unit from the memory. One or more kernels can be set, and the communication efficiency can be improved by adjusting the kernel parameters.

[0136] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0137] An embodiment of the present invention provides a computer-readable storage medium, which includes a stored program, wherein when the program is running, the device where the computer-readable storage medium is located is controlled to execute the low-voltage substation monitoring data calibration method based on multi-source information.

[0138] An embodiment of the present invention provides a distribution network, comprising: one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by the one or more processors, and the one or more programs include methods for executing the above-mentioned low-voltage substation monitoring data calibration method based on multi-source information.

[0139] Obviously, those skilled in the art should understand that the above modules or steps of the present invention can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in a different order than here, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.

[0140] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0141] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0142] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0143] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0144] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0145] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0146] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0147] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0148] From the above description, it can be seen that the above embodiments of the present application achieve the following technical effects:

[0149] 1) The low-voltage area monitoring data calibration method based on multi-source information of the present application makes full use of multi-source data such as low-voltage distribution transformers, user-side smart meters, and low-voltage topology line-user connection relationships, combined with spatiotemporal characteristics and deviation analysis, to effectively improve the accuracy of data correction. This method does not require additional equipment installation, and can achieve data correction using the data of the existing distribution network system, saving investment costs. Through precise deviation analysis and historical data correction, abnormal data can be effectively identified and corrected, thereby generating high-precision target electricity consumption data. In addition, this method has a small amount of calculation, does not require complex model training or optimization, has strong engineering adaptability, can be widely used in smart meter data calibration in low-voltage areas, and improves the operating efficiency of the distribution network system and the credibility of the data. It solves the problems of data calibration methods in the prior art that rely on high hardware upgrade costs, high algorithm complexity, and poor applicability.

[0150] 2) The low-voltage area monitoring data calibration device based on multi-source information of the present application includes: a first acquisition unit, a second acquisition unit, a third acquisition unit, a determination unit and a correction unit. The first acquisition unit is used to obtain the three-phase current value at the head end of the low-voltage distribution transformer to obtain the correction comparison data; the second acquisition unit is used to obtain the current, voltage and power timing data on the user side through the smart meter to obtain the data to be corrected; the third acquisition unit is used to obtain the low-voltage topology line-user connection relationship, and the low-voltage topology line-user connection relationship includes the connection relationship between the primary branch line of the low-voltage area and the smart meter on the user side, and the primary branch line is connected to the low-voltage distribution transformer; the determination unit is used to perform deviation analysis on the correction comparison data and the data to be corrected based on the low-voltage topology line-user connection relationship, and when the deviation is greater than the preset value, the corresponding data to be corrected is determined as abnormal data; the correction unit is used to obtain the current, voltage and power timing data on the user side at the time of recording before the data to be corrected, and obtain historical correction data, and correct the data to be corrected at least based on the historical correction data to obtain the target power consumption data. The device implements deviation analysis and historical data correction by utilizing the three-phase current value at the head end of the distribution transformer, the smart meter data on the user side, and the low-voltage topology line-user connection relationship, effectively identifying and correcting abnormal data to obtain accurate target electricity consumption data, solving the problems of data calibration methods in the existing technology that rely on high hardware upgrade costs, high algorithm complexity, and poor applicability.

[0151] The above are only preferred embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A method for calibrating low-voltage area monitoring data based on multi-source information, characterized in that: include: Obtain the three-phase current value at the head end of the low-voltage distribution transformer to obtain correction comparison data; The current, voltage and power time series data on the user side are obtained through the smart meter to obtain the data to be corrected; Acquire a low-voltage topology line-user connection relationship, wherein the low-voltage topology line-user connection relationship includes a connection relationship between a primary branch line of a low-voltage station area and the smart meter on the user side, wherein the primary branch line is connected to the low-voltage distribution transformer; Based on the low-voltage topology line-user connection relationship, the correction comparison data and the data to be corrected are analyzed for deviations, and when the deviation is greater than a preset value, the corresponding data to be corrected is determined as abnormal data; The current, voltage and power timing data of the user side recorded before the data to be corrected are obtained to obtain historical correction data, and the data to be corrected is corrected at least based on the historical correction data to obtain target power consumption data.

2. The method according to claim 1, characterized in that Based on the low-voltage topology line-user connection relationship, the correction comparison data and the data to be corrected are analyzed for deviations, and when the deviation is greater than a preset value, the corresponding data to be corrected is determined as abnormal data, including: Performing deviation analysis based on the three-phase current values ​​in the correction comparison data and the current in the data to be corrected, and performing abnormality diagnosis based on the deviation and a first threshold; When the abnormality diagnosis fails, clustering is performed based on the voltages in the data to be corrected, and the voltages in the same cluster are sorted. When the deviation of the sorting result is greater than a second threshold, the corresponding data to be corrected is determined as abnormal data.

3. The method according to claim 2, characterized in that Performing deviation analysis based on the three-phase current values ​​in the correction comparison data and the current in the data to be corrected, and performing abnormality diagnosis based on the deviation and a first threshold, including: Calculating the difference between the three-phase current value in the correction comparison data and the sum of the currents of the data to be corrected to obtain a target deviation; When the target deviation is greater than or equal to the first threshold, it is determined that the abnormal data exists in the data to be corrected at the corresponding moment.

4. The method according to claim 2, characterized in that: The method comprises: performing deviation analysis based on the voltage in the data to be corrected, clustering based on the voltages of different smart meters, and sorting based on the voltages in the same cluster, and determining the corresponding data to be corrected as abnormal data when the deviation of the sorting result is greater than a second threshold value, including: Clustering is performed based on the correlation coefficients between the voltage curves of the voltages to obtain a plurality of target clusters, wherein the correlation coefficients of the voltages in the same cluster are greater than or equal to a third threshold; The smart meters corresponding to the voltage in each of the target clusters are sorted according to the time when the abnormal data exists and the time when the abnormal data does not exist, to obtain a first target sequence and a second target sequence; When the order deviation of the voltage corresponding to the smart meter in the first target sequence and the second target sequence is greater than the second threshold, the to-be-corrected data corresponding to the smart meter is determined as the abnormal data.

5. The method according to claim 4, characterized in that Clustering is performed based on the correlation coefficient between the voltage curves of the voltage to obtain a plurality of target clusters, and the method further includes: The correlation coefficient is calculated based on the voltages of any two user sides: Among them, τ mv is the correlation coefficient between smart meter m and smart meter v, u m,t and u v,t are the voltage values ​​of the smart meter m and the smart meter v at time t, respectively, t=1, 2, ..., T, T is the total number of measurement time sections; Clustering is performed based on the correlation coefficient to obtain the target cluster: in, is the correlation coefficient threshold of the y-th cluster, Ω cla (y) represents the yth target cluster.

6. The method according to claim 3, characterized in that Calculating the difference between the three-phase current value in the correction comparison data and the sum of the currents of the data to be corrected to obtain a target deviation includes: Substitute the three-phase current values ​​in the correction comparison data and the current in the data to be corrected into the target formula to obtain the target deviation: in, is the target deviation, is the three-phase current value of the j-th primary branch line at time t, represents the current value of the smart meter b at time t, t=1, 2, ..., T, T is the total number of measurement time sections, ψ j is the set of smart meters connected to the jth primary branch line, and L is the set of primary branch lines.

7. The method according to claim 1, characterized in that Correcting the data to be corrected based at least on the historical correction data to obtain target power consumption data includes: Acquire the current in the historical data separated from the abnormal data by a first preset time length and a second preset time length, obtain a first target current and a second target current, calculate the average of the first target current and the second target current, and replace the current in the abnormal data; Based on the power in the historical data that is separated from the power in the abnormal data by the first preset time length and the second preset time length, a first target power and a second target power are obtained, an average of the first target power and the second target power is calculated, and the power in the abnormal data is replaced; Obtain the voltage of the smart meter adjacent to the number of the smart meter corresponding to the abnormal data in the data to be corrected, obtain the first target voltage and the second target voltage, calculate the average of the first target voltage and the second target voltage, and replace the power in the abnormal data.

8. A low voltage area monitoring data calibration device based on multi-source information, characterized in that: The device comprises: A first acquisition unit is used to acquire the three-phase current value of the head end of the low-voltage distribution transformer to obtain correction comparison data; The second acquisition unit is used to acquire the current, voltage and power time series data of the user side through the smart meter to obtain the data to be corrected; A third acquisition unit is used to acquire a low-voltage topology line-user connection relationship, wherein the low-voltage topology line-user connection relationship includes a connection relationship between a primary branch line of a low-voltage station area and the smart meter on the user side, wherein the primary branch line is connected to the low-voltage distribution transformer; A determination unit, configured to perform deviation analysis on the correction comparison data and the data to be corrected based on the low-voltage topology line-user connection relationship, and determine the corresponding data to be corrected as abnormal data when the deviation is greater than a preset value; A correction unit is used to obtain the current, voltage and power timing data on the user side before the data to be corrected is recorded, obtain historical correction data, correct the data to be corrected at least based on the historical correction data, and obtain target power consumption data.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute the method according to any one of claims 1 to 7.

10. A distribution network, characterized in that: include: One or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by the one or more processors, and the one or more programs include methods for executing any one of claims 1 to 7.

Images