A power distribution network abnormal data determination method, device, equipment, medium and product

Abstract

The application discloses a power distribution network abnormal data determination method, device, equipment, medium and product. The method comprises the following steps: acquiring current operation data collected by each data collection device in a power distribution network; performing time sequence checking on the current operation data to obtain a first abnormal data judgment result; performing spatial distribution checking on the current operation data to obtain a second abnormal data judgment result; and determining abnormal data according to the first abnormal data judgment result and the second abnormal data judgment result. The technical scheme of the application can improve the accuracy and reliability of abnormal data detection by bidirectional data checking, complementary and consistency of multi-source data.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of power system data processing technology, and in particular to a method, apparatus, equipment, medium and product for determining abnormal data in a distribution network. Background Technology

[0002] As a crucial component of the power system, the accuracy and reliability of data from the distribution network are paramount. However, due to data acquisition equipment malfunctions, communication problems, and other factors, distribution network data may exhibit anomalies. Failure to detect and address these anomalies in a timely manner can impact the normal operation of the distribution network and decision support. Existing anomaly detection methods often rely on one-way data verification, failing to fully leverage the complementarity of multi-source data, resulting in insufficient accuracy and timeliness in anomaly labeling. Summary of the Invention

[0003] This invention provides a method, apparatus, device, medium, and product for determining abnormal data in a power distribution network, thereby improving the accuracy and reliability of abnormal data detection.

[0004] According to one aspect of the present invention, a method for determining abnormal data in a power distribution network is provided, comprising:

[0005] Acquire the current operating data collected by each data acquisition device in the power distribution network;

[0006] The current running data is subjected to time series verification to obtain the first abnormal data judgment result;

[0007] The spatial distribution of the current running data is checked to obtain the second abnormal data judgment result;

[0008] Abnormal data is determined based on the first abnormal data judgment result and the second abnormal data judgment result.

[0009] According to another aspect of the present invention, a distribution network anomaly data determination device is provided, the device comprising:

[0010] The acquisition module is used to acquire the current operating data collected by each data acquisition device in the power distribution network;

[0011] The first verification module is used to perform time series verification on the current running data to obtain the first abnormal data judgment result;

[0012] The second verification module is used to perform spatial distribution verification on the current running data to obtain the second abnormal data judgment result;

[0013] The determination module is used to determine abnormal data based on the first abnormal data judgment result and the second abnormal data judgment result.

[0014] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0015] At least one processor; and

[0016] A memory communicatively connected to the at least one processor; wherein,

[0017] 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 power distribution network anomaly data determination method according to any embodiment of the present invention.

[0018] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions, the computer instructions being configured to cause a processor to execute and implement the distribution network anomaly data determination method according to any embodiment of the present invention.

[0019] According to another aspect of the present invention, embodiments of the present invention also provide a computer program product, the computer program product including a computer program, which, when executed by a processor, implements the distribution network abnormal data determination method described in any embodiment of the present invention.

[0020] This invention acquires current operating data from each data acquisition device in the power distribution network, performs time-series verification on the current operating data to obtain a first anomaly judgment result, performs spatial distribution verification on the current operating data to obtain a second anomaly judgment result, and determines the anomaly data based on the first and second anomaly judgment results. The technical solution of this invention, through bidirectional data verification, utilizes the complementarity and consistency of multi-source data to improve the accuracy and reliability of anomaly data detection.

[0021] 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

[0022] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0023] Figure 1 This is a flowchart of a method for determining abnormal data in a power distribution network according to an embodiment of the present invention;

[0024] Figure 2 This is a schematic diagram of the structure of a power distribution network anomaly data determination device according to an embodiment of the present invention;

[0025] Figure 3 This is a schematic diagram of the structure of an electronic device that implements the distribution network abnormal data determination method according to an embodiment 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 their derivatives, are intended to cover 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] It is understood that before using the technical solutions disclosed in the various embodiments of this disclosure, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in this disclosure in an appropriate manner in accordance with relevant laws and regulations, and user authorization should be obtained.

[0029] Example 1

[0030] Figure 1 This is a flowchart of a method for determining abnormal data in a distribution network according to an embodiment of the present invention. This embodiment is applicable to the determination of abnormal data in a distribution network. The method can be executed by the distribution network abnormal data determination device in this embodiment of the present invention. This device can be implemented in software and / or hardware, such as... Figure 1 As shown, the method specifically includes the following steps:

[0031] S101. Obtain the current operating data collected by each data acquisition device in the power distribution network.

[0032] In this embodiment, the data acquisition device can be a device used in the power distribution network to collect and measure various types of data. For example, the data acquisition device can be various sensors, smart meters, etc. The current operating data can be various operating data detected in the power distribution network at the current moment, such as parameter data like voltage, current, power, and frequency.

[0033] Specifically, real-time operating data is acquired from various data acquisition devices in the power distribution network (such as sensors and smart meters), and the acquired current operating data is preprocessed, including data cleaning, noise reduction, and completion, to ensure the accuracy and completeness of the data.

[0034] S102. Perform time series verification on the current running data to obtain the first abnormal data judgment result.

[0035] It should be noted that time series verification can be performed from the time series dimension of the data. Specifically, the first abnormal data judgment result can be derived from the data verification of the currently running data's time series dimension, determining whether the data contains anomalies. For example, the first abnormal data judgment result may indicate the presence of abnormal data; in other embodiments, the first abnormal data judgment result may also indicate the absence of abnormal data.

[0036] In practice, the main purpose of time series verification is to detect outliers or unreasonable changes by comparing historical and current data. The core of this process lies in using time series models to predict or smooth current data and comparing it with actual observed data to identify potential anomalies. Specifically, data verification from the time series perspective of current operating data can be further refined as follows: using historical operating data corresponding to the current operating data for time series analysis to detect deviations between the current and historical operating data, and determining whether the data is abnormal.

[0037] S103. Perform spatial distribution verification on the current running data to obtain the second abnormal data judgment result.

[0038] It should be noted that spatial distribution verification can be performed from the spatial distribution dimension of the data. Specifically, the second abnormal data judgment result can be derived from the data verification based on the spatial distribution dimension of the currently running data, determining whether the data is abnormal. For example, the second abnormal data judgment result may indicate the presence of abnormal data; in other embodiments, the second abnormal data judgment result may also indicate the absence of abnormal data.

[0039] In practice, data verification from the spatial distribution dimension of current operating data can be further refined as follows: using the current operating data of each node in the distribution network, analyze the consistency of current operating data between nodes, and detect whether there is any abnormal data.

[0040] S104. Determine the abnormal data based on the judgment results of the first abnormal data and the judgment results of the second abnormal data.

[0041] Here, abnormal data can be identified by verifying the data from both the time series and spatial distribution dimensions of the current operating data. For example, this abnormal data may be caused by data acquisition equipment failure, communication problems, or other factors.

[0042] Specifically, abnormal data is identified based on the two-way verification results and marked. The marking information can include the type of abnormality, its severity, and the time of occurrence. The marked abnormal data can then be stored in a pre-defined database, supporting subsequent queries and analysis. For example, the marked abnormal data can be further processed, including issuing alarms, data repair, and generating anomaly reports.

[0043] This invention acquires current operating data from each data acquisition device in the power distribution network, performs time-series verification on the current operating data to obtain a first anomaly judgment result, performs spatial distribution verification on the current operating data to obtain a second anomaly judgment result, and determines the anomaly data based on the first and second anomaly judgment results. The technical solution of this invention, through bidirectional data verification, utilizes the complementarity and consistency of multi-source data to improve the accuracy and reliability of anomaly data detection.

[0044] Optionally, perform time series verification on the current running data to obtain the first abnormal data judgment result, including:

[0045] Acquire historical operational data collected by various data acquisition devices in the power distribution network.

[0046] Historical operating data can be various operating data of the distribution network detected at historical times, such as parameters like voltage, current, power, and frequency. In this embodiment, the historical time is not limited and can be set according to actual needs. For example, the historical time can be the previous day, the previous week, or the previous month, etc. Correspondingly, the current time can be the current day, the current week, or the current month, etc.

[0047] Specifically, this involves acquiring historical operational data from various data acquisition devices in the power distribution network (such as sensors and smart meters). In practice, the acquired historical operational data can be preprocessed, including data cleaning, noise reduction, and data completion, to ensure the accuracy and completeness of the data.

[0048] An initial time series model is trained based on historical operational data to obtain a target prediction model.

[0049] In practice, traditional time series verification methods may be based on simple smoothing, regression, or moving average methods. However, these methods may not perform well when dealing with nonlinear or non-stationary data. Therefore, this invention introduces more advanced time series modeling and prediction algorithms, such as the ARIMA (Auto Regressive Integrated Moving Average) model and the SARIMA (Seasonal Auto Regressive Integrated Moving Average) model. These models perform well in handling non-stationary time series data and are suitable for distribution network operation data with trend and seasonal characteristics. By introducing these advanced modeling and prediction methods, the accuracy of anomaly detection in time series verification can be improved.

[0050] The initial time series model can be an initial, untrained ARIMA model or a SARIMA model, and the target prediction model can be a trained ARIMA model or a SARIMA model.

[0051] Specifically, by analyzing the trends of historical operating data, a predictive model for current operating data is established, such as time series models like ARIMA and SARIMA. The time series model is then trained based on historical operating data to obtain the target predictive model.

[0052] Obtain the prediction data output by the target prediction model.

[0053] It should be noted that the predicted operating data can be the current operating data predicted by the target prediction model based on historical operating data.

[0054] Specifically, a time series model is trained based on historical operational data to obtain the predicted operational data output by the target prediction model.

[0055] If the residual between the current running data and the predicted running data is greater than or equal to the preset residual threshold, then abnormal data is determined to exist.

[0056] The preset residual threshold can be a pre-set threshold for the difference between the actual value (i.e., the current running data) and the predicted value (i.e., the predicted running data). This embodiment does not limit the specific value of the preset residual threshold. In practical applications, the preset residual threshold can be set through statistical analysis (such as the 3-standard deviation method) or empirical values.

[0057] Specifically, if the residual between the current running data (actual value) and the predicted running data (predicted value) is less than the preset residual threshold, it is determined that there is no abnormal data; if the residual between the current running data (actual value) and the predicted running data (predicted value) is greater than or equal to the preset residual threshold, it is determined that there is abnormal data.

[0058] Optionally, the first outlier judgment result is determined based on the time series data, including:

[0059] Time series data is generated based on the current running data.

[0060] Time series data can be generated by sorting the currently observed operational data according to time series.

[0061] Identify abrupt changes in time series data.

[0062] It's important to explain that a mutation point can be understood as a data point in a time series where the value changes dramatically. For example, in a time series data set, the voltage values ​​for the vast majority of values ​​are between 0 and 100V, but there is a data point with a voltage value of 150V. This data point can be considered a mutation point.

[0063] Specifically, the CUSUM (Cumulative SUM Control Chart) variation detection method can be used to identify abrupt changes in time series data.

[0064] Obtain the mutation magnitude corresponding to the mutation point.

[0065] It should be noted that the mutation magnitude can be the difference between the mutation point and the data adjacent to the mutation point in the time series data.

[0066] Specifically, after identifying the mutation point in the time series data, the data adjacent to the mutation point can be obtained separately, and then the mutation magnitude corresponding to the mutation point can be calculated.

[0067] If the magnitude of the mutation is greater than or equal to the preset magnitude threshold, then abnormal data is determined to exist.

[0068] The preset amplitude threshold can be a threshold for the difference in data values ​​in time series data that is preset according to actual needs. In this embodiment, the specific value of the preset amplitude threshold is not limited.

[0069] In practice, the operating data of the power distribution network should typically be continuous and gradually changing; any sudden, large-scale changes may indicate potential anomalies. By detecting abrupt changes in the time series, further analysis of the data before and after the abrupt change can be conducted to analyze the magnitude and frequency of the changes and determine if any anomalies exist. It is necessary to determine whether the abrupt change was caused by an actual event (such as equipment switching or a fault). If it was not caused by an actual event, further investigation of the data source or system status is required.

[0070] Optionally, the first outlier judgment result is determined based on the time series data, including:

[0071] The target frequency fluctuation range is determined based on historical operating data.

[0072] The target frequency fluctuation range can be the normal fluctuation range of voltage frequency in the distribution network determined by statistical analysis of historical operating data.

[0073] Specifically, after obtaining historical operating data, the historical voltage frequency data in the historical operating data is statistically analyzed to determine the normal voltage frequency fluctuation range.

[0074] The current frequency fluctuation range is determined based on the current operating data.

[0075] The current frequency fluctuation range can be the actual fluctuation range of voltage frequency in the distribution network determined by statistical analysis based on current operating data.

[0076] Specifically, after obtaining the current operating data, the current voltage frequency data in the current operating data is statistically analyzed to determine the actual voltage frequency fluctuation range.

[0077] If the frequency fluctuation tolerance between the current frequency fluctuation range and the target frequency fluctuation range is greater than or equal to the preset fluctuation tolerance threshold, then abnormal data is determined to exist.

[0078] The preset fluctuation tolerance threshold can be a voltage frequency fluctuation tolerance threshold preset according to actual needs. In this embodiment, the specific value of the preset fluctuation tolerance threshold is not limited.

[0079] In power distribution networks, voltage and frequency stability is a critical parameter. Drastic frequency fluctuations within a short period may indicate data anomalies or system failures. Therefore, voltage and frequency fluctuations must be within a certain range; otherwise, they are considered abnormal. By statistically analyzing historical frequency data, a normal fluctuation range is determined, a fluctuation tolerance threshold is set, and frequency data is monitored in real time. If the fluctuation exceeds this range, an alarm is triggered. Combined analysis with other time-series data (such as voltage and current) helps eliminate false alarms caused by data acquisition or transmission errors.

[0080] In power distribution network data, anomalies can occur at different time scales. Therefore, multi-scale analysis methods, such as wavelet analysis or HHT (Hilbert-Huang Transform), can be used to decompose and analyze time series data at multiple scales to detect anomalies at different scales.

[0081] Distribution network data often comes from multiple sensors or different monitoring points. Fusing data from different sources can improve the accuracy of time series verification. Several methods can be used for data fusion: Kalman filter: suitable for state estimation of dynamic systems, it can provide more accurate anomaly detection results by fusing time series data from multiple sensors. Bayesian method: a time series verification method based on Bayesian statistics, which can introduce prior knowledge into data fusion, thereby improving the accuracy of anomaly detection.

[0082] In practice, spatial distribution verification mainly involves analyzing the data consistency and spatial rationality between nodes in the distribution network to determine the correctness of the data. Due to the complex topology of the distribution network, the electrical and spatial connections between nodes need to meet specific physical and logical rules.

[0083] Optionally, spatial distribution verification is performed on the current running data to obtain the second abnormal data judgment result, including:

[0084] Build a topology diagram based on the current running data.

[0085] In this embodiment, the topology diagram can be constructed by mapping the current operating data to the positions of each node in the distribution network according to the physical connection topology between each node in the distribution network.

[0086] Specifically, after obtaining the operating data of each node, a topology diagram can be constructed from the current operating data based on the physical topology between the nodes in the distribution network.

[0087] In a distribution network, nodes typically represent physical or logical connection points in the power system. These nodes can be substations, distribution transformers, feeder segments (distribution lines), switching equipment, etc. Node data in a distribution network is usually obtained through direct measurement and calculation. In spatial distribution verification, current operating data can be electrical parameters or other relevant information collected at these nodes, such as voltage, current, power, and frequency. In some cases, node data may require comprehensive calculations based on data from multiple measurement points.

[0088] If there are nodes that are not connected in the topology graph, then abnormal data is identified.

[0089] The topology of a power distribution network requires all electrical nodes to be physically connected. If the status data (such as voltage and current) of a node is inconsistent with that of other nodes, it may indicate a data anomaly or a system fault. A topology graph of the power distribution network can be constructed, and connectivity algorithms based on graph theory, such as DFS (Depth-First Search) and BFS (Breadth-First Search), can be used to check whether all nodes in the network are connected. The electrical status data of each node is checked to ensure that the voltage and current data of all connected nodes are consistent within reasonable ranges. For any inconsistencies detected, further analysis of the operating status and geographical location of the power distribution equipment is conducted to confirm whether the inconsistencies are caused by equipment failure, sensor malfunction, or data transmission errors.

[0090] Optionally, spatial distribution verification is performed on the current running data to obtain the second abnormal data judgment result, including:

[0091] Obtain the location information corresponding to each data acquisition device.

[0092] In this embodiment, the location information can be the actual geographical location where the data acquisition device is installed.

[0093] Specifically, the location information of each data acquisition device is collected in real time. Furthermore, the location information of each data acquisition device can be the actual geographic coordinates of each data acquisition device.

[0094] The database is queried to obtain the geographic coordinates of each data acquisition device.

[0095] Among them, the geographic coordinate information can be the geographic coordinate information that each data acquisition device should be installed according to the design specifications, which is stored in the database.

[0096] Specifically, the geographical coordinates of the equipment are acquired and recorded during installation to form a standard database.

[0097] The location information and geographic coordinate information corresponding to each data acquisition device are compared. If the deviation between the location information and geographic coordinate information is greater than or equal to the preset deviation range, it is determined that there is an anomaly in the data acquisition device.

[0098] The preset deviation range can be a coordinate deviation range threshold set in advance according to actual needs. In this embodiment, the specific value of the preset deviation threshold is not limited.

[0099] Specifically, equipment in the power distribution network (such as transformers and switches) should be installed at specific geographical coordinates according to design specifications. If the equipment location data deviates significantly from its expected location, it may indicate data errors or improper actual equipment placement. Geographic coordinate information should be acquired and recorded during equipment installation to form a standard database. Equipment location information should be collected in real time and compared with the coordinates in the standard database; if the deviation exceeds the allowable range, it is considered abnormal. For deviations, further investigation should be conducted to determine if they are caused by equipment movement, incorrect installation, or GPS positioning errors; on-site inspection may be necessary.

[0100] Optionally, spatial distribution verification is performed on the current running data to obtain the second abnormal data judgment result, including:

[0101] Determine the set of adjacent node pairs based on the topology diagram.

[0102] In this embodiment, the set of adjacent node pairs includes several adjacent node pairs. It should be noted that an adjacent node pair can be a pair of nodes that are in adjacent positions in the topology graph.

[0103] Specifically, each pair of adjacent nodes in the topology graph is considered as an adjacent node pair, and the set of adjacent node pairs is determined based on the topology graph.

[0104] Obtain the difference in runtime data for each pair of adjacent nodes.

[0105] It should be noted that the difference in operating data can be the difference in each type of operating data between two adjacent nodes in an adjacent node pair, such as voltage difference, current difference, etc.

[0106] Specifically, calculate the difference in running data between every two adjacent nodes in each pair of adjacent nodes.

[0107] If the difference in the running data is greater than or equal to the preset tolerance range, then abnormal data is determined to exist.

[0108] The preset tolerance range can be the range of operating data differences between two adjacent nodes that are preset according to actual needs. In this embodiment, the specific value of the preset tolerance range is not limited.

[0109] In practice, data (such as voltage, current, and power) between adjacent nodes should have high consistency, especially in the branch networks of the distribution network. Significant differences in data between adjacent nodes may indicate an anomaly in a particular node or data link. The distribution network topology is analyzed to determine the set of adjacent node pairs. Key parameters (such as voltage and current differences) between adjacent nodes are compared, and a reasonable tolerance range is set. Any node pair exceeding the tolerance range is marked as an anomaly, and the status of the power equipment and data acquisition system in that area are further examined.

[0110] Optionally, spatial distribution verification is performed on the current running data to obtain the second abnormal data judgment result, including:

[0111] Based on the topology diagram and equipment rated parameters, determine the power flow distribution data.

[0112] In this embodiment, the device's rated parameters can be the rated parameters of each data acquisition device, such as rated voltage, rated current, etc.

[0113] Among them, the power flow distribution data can be theoretical power flow distribution data calculated using the topology of the distribution network and the rated parameters of the equipment.

[0114] Specifically, based on the topology diagram and the rated parameters of the equipment, the theoretical power flow distribution data is calculated.

[0115] Obtain the power flow data for each node in the topology diagram.

[0116] The power flow data can be the power flow data that flows through each node.

[0117] Specifically, real-time power flow data for each node.

[0118] The power flow data for each branch is determined based on the power flow data of each node.

[0119] It should be noted that a branch can be formed by connecting every two nodes; that is, the connection between two nodes can be called a branch.

[0120] Specifically, the power flow data of each node is monitored in real time, and the actual power flow data of the branch formed by each pair of nodes is calculated based on the power flow data of each pair of nodes.

[0121] The power flow data and power flow distribution data of each branch are compared. If the difference between the power flow data and power flow distribution data of each branch is greater than or equal to the preset power flow threshold, then abnormal data is identified.

[0122] The preset power flow threshold can be a threshold value that is set in advance according to actual needs between the actual power flow (power flow data) and the theoretical value (power flow distribution data). This embodiment does not limit the specific value of the preset power flow threshold.

[0123] In a power distribution network, power flow must satisfy the law of conservation of power, and the difference between input and output power should be within a reasonable range (considering losses). An unreasonable power flow distribution may indicate data anomalies or system configuration errors. Using the distribution network topology and equipment rated parameters, the theoretical power flow distribution is calculated. Power flow data at each node is monitored in real time, and the actual power flow of each branch is calculated. The actual power flow is compared with the theoretical value; if the difference exceeds the allowable range, an anomaly alarm is triggered. Further analysis is conducted to determine the cause of the difference, investigating potential equipment failures, data errors, or unauthorized access.

[0124] Spatial distribution verification of a power distribution network involves not only the consistency of data at each node but also the overall network topology. Optimization can be achieved through the following methods: Graph theory and network analysis: Utilizing concepts such as shortest path, connectivity, and network flow in graph theory, the topology of the power distribution network can be analyzed, and anomaly detection can be performed in conjunction with node data. Spectral graph theory: By analyzing the Laplace matrix of the power distribution network, abnormal behaviors in the network can be detected, such as abnormal fluctuations at certain nodes or abnormal distributions of power flow.

[0125] In spatial distribution verification, data between nodes often exhibit spatial autocorrelation. The following methods can be used to optimize spatial distribution verification: Spatial clustering analysis: Using spatial clustering algorithms, such as DBSCAN (Density-Based Spatial Clustering of Applications with Noise, a density-based clustering algorithm that divides areas with sufficiently high density into clusters and treats low-density areas as noise or outliers) and K-means, areas with anomalous data in the distribution network can be identified. Through cluster analysis, spatially concentrated outliers can be discovered, allowing for targeted processing.

[0126] Spatial distribution verification of power distribution networks requires consideration of the multi-scale characteristics of the data. Verification algorithms can be optimized through multi-scale analysis: Multi-scale decomposition methods, such as wavelet transform or multi-scale pyramid methods, can decompose power distribution network data at multiple scales, analyzing spatial distribution characteristics at different scales to improve the accuracy of anomaly detection. Multi-resolution analysis: Combining GIS data and power distribution network operational data allows for spatial verification at different resolutions. For example, fine-grained spatial analysis can more accurately locate anomaly areas.

[0127] In spatial distribution verification, different nodes may collect different types of data (such as voltage, current, frequency, etc.). By fusing these multi-source data, the spatial verification effect can be optimized: Bayesian data fusion: Using Bayesian inference methods, spatial data from different nodes can be fused and combined with prior knowledge for anomaly detection.

[0128] Time-series verification and spatial distribution verification verify data from different dimensions. However, in practical applications, these two verification methods can complement each other to achieve more accurate and robust anomaly detection. 1. Time-space joint modeling: Dynamic Bayesian network: By combining the dynamic model in time-series verification with the spatial dependencies in spatial distribution verification, a dynamic Bayesian network model can be constructed for time-space joint verification. 2. Iterative verification mechanism: Multi-round verification and feedback mechanism: Time-series verification can be performed first, and after initial anomalies are detected, spatial distribution verification can be used for validation, and vice versa. Through iterative and feedback mechanisms, false positives and false negatives can be reduced, improving the overall reliability of the verification. In the bidirectional data verification of distribution network operation data, time-series verification and spatial distribution verification each have their unique advantages. Through algorithm optimization and improvement, the accuracy and real-time performance of anomaly detection can be significantly improved. Future research and applications can further explore the synergistic optimization of the two methods, and through time-space joint modeling, iterative verification, data fusion, and other means, achieve a more accurate and intelligent distribution network operation data verification system. This not only helps improve the stability and reliability of the distribution network, but also provides a solid data foundation for the development of smart grids.

[0129] The technical solution of this invention, through bidirectional verification of time series and spatial distribution, fully utilizes the complementarity of multi-source data to promptly detect and mark abnormal data in the distribution network, effectively improving the accuracy and reliability of abnormal data detection and ensuring the safe and stable operation of the distribution network. At the same time, by processing abnormal data in real time, it can promptly respond to and repair abnormal situations, providing strong support for the intelligent management of the distribution network.

[0130] Example 2

[0131] Figure 2 This is a schematic diagram of a distribution network anomaly data determination device according to an embodiment of the present invention. This embodiment is applicable to the determination of distribution network anomaly data. The device can be implemented using software and / or hardware, and can be integrated into any device that provides the function of determining distribution network anomaly data, such as… Figure 2 As shown, the power distribution network abnormal data determination device specifically includes: an acquisition module 201, a first verification module 202, a second verification module 203, and a determination module 204.

[0132] Among them, the acquisition module 201 is used to acquire the current operating data collected by each data acquisition device in the power distribution network;

[0133] The first verification module 202 is used to perform time series verification on the current running data to obtain the first abnormal data judgment result;

[0134] The second verification module 203 is used to perform spatial distribution verification on the current running data to obtain a second abnormal data judgment result;

[0135] The determination module 204 is used to determine abnormal data based on the first abnormal data judgment result and the second abnormal data judgment result.

[0136] Optionally, the first verification module 202 is specifically used for:

[0137] Acquire historical operating data collected by each data acquisition device in the power distribution network;

[0138] An initial time series model is trained based on the historical operational data to obtain the target prediction model;

[0139] Obtain the prediction execution data output by the target prediction model;

[0140] If the residual between the current running data and the predicted running data is greater than or equal to a preset residual threshold, then abnormal data is determined to exist.

[0141] Optionally, the first verification module 202 is specifically used for:

[0142] Generate time-series data based on the current operating data;

[0143] Identify abrupt changes in the time series data;

[0144] Obtain the mutation magnitude corresponding to the mutation point;

[0145] If the mutation magnitude is greater than or equal to a preset magnitude threshold, then abnormal data is determined to exist.

[0146] Optionally, the first verification module 202 is specifically used for:

[0147] The target frequency fluctuation range is determined based on the historical operating data.

[0148] Determine the current frequency fluctuation range based on the current operating data;

[0149] If the frequency fluctuation tolerance between the current frequency fluctuation range and the target frequency fluctuation range is greater than or equal to the preset fluctuation tolerance threshold, then abnormal data is determined to exist.

[0150] Optionally, the second verification module 203 is specifically used for:

[0151] Construct a topology diagram based on the current operating data;

[0152] If there are unconnected nodes in the topology graph, then abnormal data is determined to exist.

[0153] Optionally, the second verification module 203 is specifically used for:

[0154] Obtain the location information corresponding to each data acquisition device;

[0155] Query the database to obtain the geographic coordinates of each data acquisition device;

[0156] The location information and geographic coordinate information corresponding to each data acquisition device are compared. If the deviation between the location information and the geographic coordinate information is greater than or equal to a preset deviation range, it is determined that the data acquisition device is abnormal.

[0157] Optionally, the second verification module 203 is specifically used for:

[0158] Determine the set of adjacent node pairs based on the topology diagram;

[0159] Obtain the difference in runtime data for each pair of adjacent nodes;

[0160] If the difference in the running data is greater than or equal to the preset tolerance range, then abnormal data is determined to exist.

[0161] Optionally, the second verification module 203 is specifically used for:

[0162] Based on the aforementioned topology diagram and equipment rated parameters, determine the power flow distribution data;

[0163] Obtain the power flow data of each node in the topology diagram;

[0164] The power flow data for each branch is determined based on the power flow data of each node;

[0165] The power flow data of each branch is compared with the power flow distribution data. If the difference between the power flow data of each branch and the power flow distribution data is greater than or equal to a preset power flow threshold, then abnormal data is determined to exist.

[0166] The above-mentioned products can execute the distribution network abnormal data determination method provided in any embodiment of the present invention, and have the corresponding functional modules and beneficial effects of the execution method.

[0167] Example 3

[0168] Figure 3A schematic diagram of an electronic device 30 that can be used to implement embodiments of the present invention 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 (e.g., 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.

[0169] like Figure 3 As shown, the electronic device 30 includes at least one processor 31 and a memory, such as a read-only memory (ROM) 32 or a random access memory (RAM) 33, communicatively connected to the at least one processor 31. The memory stores computer programs executable by the at least one processor. The processor 31 can perform various appropriate actions and processes based on the computer program stored in the ROM 32 or loaded from storage unit 38 into the RAM 33. The RAM 33 can also store various programs and data required for the operation of the electronic device 30. The processor 31, ROM 32, and RAM 33 are interconnected via a bus 34. An input / output (I / O) interface 35 is also connected to the bus 34.

[0170] Multiple components in electronic device 30 are connected to I / O interface 35, including: input unit 36, such as keyboard, mouse, etc.; output unit 37, such as various types of monitors, speakers, etc.; storage unit 38, such as disk, optical disk, etc.; and communication unit 39, such as network card, modem, wireless transceiver, etc. Communication unit 39 allows electronic device 30 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0171] Processor 31 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 31 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 31 performs the various methods and processes described above, such as the distribution network anomaly data determination method:

[0172] Acquire the current operating data collected by each data acquisition device in the power distribution network;

[0173] The current running data is subjected to time series verification to obtain the first abnormal data judgment result;

[0174] The spatial distribution of the current running data is checked to obtain the second abnormal data judgment result;

[0175] Abnormal data is determined based on the first abnormal data judgment result and the second abnormal data judgment result.

[0176] In some embodiments, the distribution network anomaly data determination method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 38. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 30 via ROM 32 and / or communication unit 39. When the computer program is loaded into RAM 33 and executed by processor 31, one or more steps of the distribution network anomaly data determination method described above may be performed. Alternatively, in other embodiments, processor 31 may be configured to perform the distribution network anomaly data determination method by any other suitable means (e.g., by means of firmware).

[0177] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-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.

[0178] 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.

[0179] 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.

[0180] 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).

[0181] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include 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.

[0182] 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 created 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 within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0183] In one embodiment, the present invention further includes a computer program product, which includes a computer program that, when executed by a processor, implements the distribution network anomaly data determination method of any embodiment of the present invention.

[0184] In implementing the computer program product, computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof. Programming languages ​​include object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0185] 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.

[0186] 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 determining abnormal data in a power distribution network, characterized in that, include: Acquire the current operating data collected by each data acquisition device in the power distribution network; The current running data is subjected to time series verification to obtain the first abnormal data judgment result; The spatial distribution of the current running data is checked to obtain the second abnormal data judgment result; The abnormal data is determined based on the first abnormal data judgment result and the second abnormal data judgment result; The step of performing time-series verification on the current running data to obtain the first abnormal data judgment result includes: Acquire historical operating data collected by each data acquisition device in the power distribution network; An initial time series model is trained based on the historical operating data to obtain a target prediction model; wherein, the initial time series model includes an untrained autoregressive integral moving average model and a seasonal autoregressive integral moving average model; the target prediction model includes a trained autoregressive integral moving average model and a seasonal autoregressive integral moving average model. Obtain the predicted running data output by the target prediction model, wherein the predicted running data is the current running data predicted by the target prediction model based on the historical running data; If the residual between the current running data and the predicted running data is greater than or equal to a preset residual threshold, then abnormal data is determined to exist; or, Generate time-series data based on the current operating data; Identify abrupt changes in the time series data; Analyze the mutation amplitude and frequency corresponding to the mutation points to determine whether there is abnormal data based on the mutation amplitude and frequency; The step of performing spatial distribution verification on the current running data to obtain the second abnormal data judgment result includes: A topology diagram is constructed based on the current operating data; wherein, the topology diagram is constructed by corresponding the current operating data to the positions of each node in the distribution network according to the physical connection topology between each node in the distribution network. If any nodes in the topology graph are not connected, then abnormal data is determined to exist; or, Based on the aforementioned topology diagram and equipment rated parameters, determine the power flow distribution data; Obtain the power flow data of each node in the topology diagram; The power flow data for each branch is determined based on the power flow data of each node; The power flow data of each branch is compared with the power flow distribution data. If the difference between the power flow data of each branch and the power flow distribution data is greater than or equal to a preset power flow threshold, then abnormal data is determined to exist.

2. The method according to claim 1, characterized in that, Determining the first abnormal data judgment result based on the time series data includes: Generate time-series data based on the current operating data; Identify abrupt changes in the time series data; Obtain the mutation magnitude corresponding to the mutation point; If the mutation magnitude is greater than or equal to a preset magnitude threshold, then abnormal data is determined to exist.

3. The method according to claim 1, characterized in that, Determining the first abnormal data judgment result based on the time series data includes: The target frequency fluctuation range is determined based on the historical operating data. Determine the current frequency fluctuation range based on the current operating data; If the frequency fluctuation tolerance between the current frequency fluctuation range and the target frequency fluctuation range is greater than or equal to the preset fluctuation tolerance threshold, then abnormal data is determined to exist.

4. The method according to claim 1, characterized in that, The spatial distribution of the current running data is checked to obtain a second abnormal data judgment result, which also includes: Obtain the location information corresponding to each data acquisition device; Query the database to obtain the geographic coordinates of each data acquisition device; The location information and geographic coordinate information corresponding to each data acquisition device are compared. If the deviation between the location information and the geographic coordinate information is greater than or equal to a preset deviation range, it is determined that the data acquisition device is abnormal.

5. The method according to claim 1, characterized in that, The spatial distribution of the current running data is checked to obtain a second abnormal data judgment result, which also includes: Determine the set of adjacent node pairs based on the topology diagram; Obtain the difference in runtime data for each pair of adjacent nodes; If the difference in the running data is greater than or equal to the preset tolerance range, then abnormal data is determined to exist.

6. A device for determining abnormal data in a power distribution network, characterized in that, include: The acquisition module is used to acquire the current operating data collected by each data acquisition device in the power distribution network; The first verification module is used to perform time series verification on the current running data to obtain the first abnormal data judgment result; The second verification module is used to perform spatial distribution verification on the current running data to obtain the second abnormal data judgment result; The determination module is used to determine abnormal data based on the first abnormal data judgment result and the second abnormal data judgment result; Specifically, the first verification module is used to acquire historical operating data collected by each data acquisition device in the distribution network; train an initial time series model based on the historical operating data to obtain a target prediction model; wherein the initial time series model includes an untrained autoregressive integral moving average model and a seasonal autoregressive integral moving average model; the target prediction model includes a trained autoregressive integral moving average model and a seasonal autoregressive integral moving average model; acquire the predicted operating data output by the target prediction model, wherein the predicted operating data is the current operating data predicted by the target prediction model based on the historical operating data; if the residual between the current operating data and the predicted operating data is greater than or equal to a preset residual threshold, it is determined that there is abnormal data; or, generate time series data based on the current operating data; identify abrupt change points in the time series data; analyze the abrupt change amplitude and frequency corresponding to the abrupt change points, so as to determine whether there is abnormal data based on the abrupt change amplitude and the frequency; Specifically, the second verification module is used to construct a topology diagram based on the current operating data. The topology diagram is constructed by mapping the current operating data to the positions of each node in the distribution network according to the physical connection topology between nodes. If any node in the topology diagram is not connected, abnormal data is determined. Alternatively, based on the topology diagram and equipment rated parameters, power flow distribution data is determined. Power flow data for each node in the topology diagram is obtained. Power flow data for each branch is determined based on the power flow data of each node. The power flow data of each branch is compared with the power flow distribution data. If the difference between the power flow data of each branch and the power flow distribution data is greater than or equal to a preset power flow threshold, abnormal data is determined.

7. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the distribution network anomaly data determination method according to any one of claims 1-5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that, when executed by a processor, implement the distribution network anomaly data determination method according to any one of claims 1-5.

9. A computer program product comprising a computer program that, when executed by a processor, implements the method for determining abnormal data in a power distribution network according to any one of claims 1-5.

Images