A power supply station business automation testing method and system based on digital employees

Abstract

The present invention relates to the technical field of power supply station power services, and in particular to a method and system for automatic testing of power supply station services based on digital employees, including extracting features from single-phase meter measurement data in the service area to be tested in the power supply station to obtain measurement misalignment feature data; determining the single-phase meter measurement misalignment level distribution data according to the single-phase meter measurement data deviation amplitude and the measurement misalignment feature data; establishing a correlation model with the single-phase meter measurement misalignment level distribution data as the independent variable and the key assessment index values of each distribution area as the dependent variable; combining the correlation model and using a long short-term memory neural network to predict the change trend of the key assessment indexes at the test points under different misalignment levels to obtain expected index data; generating a service test result according to the expected index data and the actual assessment index data. The present invention combines digital employee technology and machine learning algorithms, improves the accuracy and reliability of automatic testing of power supply station services, and reduces manual intervention and errors.

Description

Technical Field

[0001] The present invention relates to the technical field of power supply business, and in particular, to an automated test method and system for power supply business based on digital employees. Background Art

[0002] In modern power systems, power supply stations play an important role in delivering electrical energy from power plants to end-users. With the development of artificial intelligence technology, in the wave of digital transformation, digital employees based on artificial intelligence technology are gradually penetrating into power supply stations. Digital employees, with their powerful data processing capabilities and intelligent decision-making support, have brought unprecedented opportunities for the automation of power supply station operations. However, in practical applications, especially for issues such as inaccurate metering of single-phase electricity meters and deviations in substation assessment indicators, the testing methods for digital employees still face many technical bottlenecks and challenges. As the core equipment in power supply station operations, the accuracy and integrity of the metering data of single-phase electricity meters are directly related to the assessment of substation assessment indicators. However, due to various reasons such as equipment aging and environmental factors, single-phase electricity meters often exhibit inaccurate metering problems, which pose great challenges to the accuracy and fairness of substation assessment indicators. How to accurately test and identify the inaccurate metering problems of single-phase electricity meters is a major problem that urgently needs to be solved in the current testing of digital employees in power supply station operations.

[0003] Secondly, the analysis of the variation law of assessment indicators under different levels of inaccuracy needs to consider various factors, such as load type, power consumption time distribution, line parameters, etc. These factors have complex coupling relationships, which bring great difficulties to the testing process. For example, different types of loads have different degrees of influence on meter inaccuracy, and the unevenness of power consumption time distribution may exacerbate this influence. In addition, the impact of inaccurate metering of single-phase electricity meters on substation assessment indicators has a time cumulative effect. It may be difficult to detect in the short term, but may lead to a serious deviation of assessment indicators from the actual situation after long-term accumulation. How to quantify this time cumulative effect is a major problem. In actual operation, due to the lack of effective quantification methods, it is often difficult to accurately evaluate the long-term impact of meter inaccuracy on assessment indicators, which brings great uncertainty to the business management of power supply stations. Therefore, how to solve these problems and improve the accuracy and reliability of digital employees in power supply station operations is an issue that urgently needs to be studied and solved in the current power industry. Summary of the Invention

[0004] To solve the above technical problems, the present invention provides an automated test method and system for power supply business based on digital employees.

[0005] In a first aspect, the present invention provides an automated test method for power supply business based on digital employees, the method comprising the following steps:

[0006] Use digital employee technology to trigger the collection of single-phase meter measurement data in the business area to be tested in the power supply station, and extract features from the single-phase meter measurement data to obtain measurement misalignment feature data; the single-phase meter measurement data includes power data, voltage data, and current data;

[0007] Use a support vector machine to analyze the single-phase meter measurement data and calculate the key assessment index values for each substation area; the key assessment index values include the line loss rate and the electricity quantity difference rate for each substation area;

[0008] Determine the single-phase meter measurement misalignment level distribution data based on the single-phase meter measurement data deviation amplitude and the measurement misalignment feature data;

[0009] Take the single-phase meter measurement misalignment level distribution data as the independent variable and the key assessment index values for each substation area as the dependent variable to establish an association model between the misalignment degree and the key assessment indexes of the substation area;

[0010] Combine the association model and use a pre-constructed long short-term memory neural network to predict the change trend of the key assessment indexes at the test points under different misalignment levels to obtain the expected index data;

[0011] Generate a business test result based on the expected index data and the actual assessment index data.

[0012] In a further implementation, the step of extracting features from the single-phase meter measurement data to obtain measurement misalignment feature data includes:

[0013] Adopt a five-point linear interpolation method to fill in the breakpoints and missing points of the single-phase meter measurement data to obtain the single-phase meter measurement complemented data;

[0014] Perform filtering processing on the single-phase meter measurement complemented data through a seven-point sliding median filtering window to obtain the single-phase meter measurement filtered data;

[0015] Use Daubechies fourth-order wavelet to decompose the single-phase meter measurement filtered data into three layers to obtain high-frequency component data, and extract the amplitude mutation points from the high-frequency component data as feature points;

[0016] Construct a statistical period data window, and use the statistical period data window to extract the voltage feature group, current feature group, and power feature group at the feature points under a preset reference value;

[0017] Perform maximum and minimum normalization processing on the voltage feature group, the current feature group, and the power feature group respectively to obtain the corresponding standardized feature data;

[0018] Based on all the standardized feature data under the voltage feature dimension, current feature dimension, and power feature dimension, calculate the feature weight coefficients of each standardized feature data using the weighted average method;

[0019] Take the standardized feature data with the feature weight coefficients exceeding the preset misalignment threshold as the measurement misalignment feature data.

[0020] In a further embodiment, the voltage feature group includes the root mean square value of voltage, voltage crest factor, and voltage volatility;

[0021] The current feature group includes current peak factor and current distortion degree;

[0022] The power feature group includes power fluctuation degree and phase offset.

[0023] In a further embodiment, the steps of analyzing the single-phase meter measurement data using a support vector machine and calculating the key performance indicator values of each substation area include:

[0024] Use the principal component analysis algorithm to extract key feature points from the single-phase meter measurement data, and collect the historical load data of the key feature points;

[0025] Use the support vector regression algorithm to analyze the historical load data and identify the load distribution pattern of the key feature points;

[0026] According to the load distribution pattern of the key feature points, calculate the synchronous load mean value using statistical analysis methods;

[0027] Calculate the difference between the current power value of the key feature point and the synchronous load mean value, and calculate the power difference rate of the substation area;

[0028] Determine the benchmark value of the line loss rate, and calculate the transformer loss compensation value, conductor loss compensation value, and contact loss compensation value according to the single-phase meter measurement data;

[0029] Determine the line loss rate of the substation area according to the difference between the line loss rate benchmark value and the transformer loss compensation value, the conductor loss compensation value, and the contact loss compensation value, and integrate the line loss rate of the substation area and the power difference rate of the substation area to form the key performance indicator value of the substation area.

[0030] In a further embodiment, the steps of determining the single-phase meter measurement misalignment level distribution data according to the single-phase meter measurement data deviation range and measurement misalignment feature data include:

[0031] According to the measurement misalignment characteristic data and the single-phase meter measurement standard value, the deviation amplitude of the single-phase meter measurement data is obtained. The deviation amplitude of the single-phase meter measurement data includes the voltage deviation amplitude, current deviation amplitude, and power factor deviation amplitude of the single-phase meter measurement data;

[0032] Determine the moving data window, and perform statistical analysis on the deviation amplitude of the single-phase meter measurement data within the moving data window to obtain the measurement deviation amplitude characteristics;

[0033] Use the Gaussian Naive Bayes classifier to model the measurement deviation amplitude characteristics, and calculate the characteristic distribution probability values of each measurement deviation amplitude characteristic at different misalignment levels;

[0034] According to the characteristic distribution probability values and the preset characteristic misalignment level probability distribution interval, classify the measurement misalignment characteristic data to determine the single-phase meter measurement misalignment level distribution data.

[0035] In a further embodiment, the measurement deviation amplitude characteristics include the deviation mean, deviation standard deviation, and maximum deviation value of the deviation amplitude of the single-phase meter measurement data.

[0036] In a further embodiment, the steps of establishing an association model between the misalignment degree and the key assessment index of the substation area, with the single-phase meter measurement misalignment level distribution data as the independent variable and the key assessment index values of each substation area as the dependent variable, include:

[0037] Perform normalization processing on the single-phase meter measurement misalignment level distribution data to obtain the normalized misalignment level distribution data;

[0038] Use the random forest regressor to model the relationship between the normalized misalignment level distribution data and the key assessment index values of each substation area to obtain an association model between the misalignment degree and the key assessment index of the substation area.

[0039] In a further embodiment, the steps of combining the association model and using a pre-constructed long short-term memory neural network to predict the change trend of the key assessment index of the test point at different misalignment levels to obtain the expected index data include:

[0040] Perform linear interpolation on the characteristic misalignment level probability distribution interval to obtain test data points;

[0041] Calculate the confidence interval value of each test data point, and detect the validity of the test data point according to the confidence interval value, and filter out the valid test data points;

[0042] Obtain the single-phase meter measurement test data of the valid test data points, and obtain the corresponding key assessment index of the test point through the association model;

[0043] Input the key assessment indicators of the test points into a pre - constructed long - short - term memory neural network to predict the change trend of the key assessment indicators of the test points at different misalignment levels, and obtain the expected index data.

[0044] In a further implementation, the step of generating the business test result according to the expected index data and the actual assessment index data includes:

[0045] Compare the expected index data with the actual assessment index data. If the comparison result of the expected index data and the actual assessment index data is consistent, it is determined that the business test result is a pass; if the comparison result of the expected index data and the actual assessment index data is inconsistent, it is determined that the business test result is a failure.

[0046] In a second aspect, the present invention provides a power supply station business automation test system based on digital employees. The system includes:

[0047] A data acquisition module, which is used to trigger the acquisition of single - phase meter measurement data in the business area to be tested in the power supply station by using digital employee technology, and extract features from the single - phase meter measurement data to obtain measurement misalignment feature data; the single - phase meter measurement data includes power data, voltage data, and current data;

[0048] A data analysis module, which is used to analyze the single - phase meter measurement data by using a support vector machine and calculate the key assessment index values of each sub - station area; the key assessment index values include the line loss rate and the power quantity difference rate of each sub - station area;

[0049] A misalignment analysis module, which is used to determine the single - phase meter measurement misalignment level distribution data according to the deviation amplitude of the single - phase meter measurement data and the measurement misalignment feature data;

[0050] A model construction module, which is used to establish an association model between the misalignment degree and the key assessment indicators of the sub - station area with the single - phase meter measurement misalignment level distribution data as the independent variable and the key assessment index values of each sub - station area as the dependent variable;

[0051] An expected test module, which is used to combine the association model and use a pre - constructed long - short - term memory neural network to predict the change trend of the key assessment indicators of the test points at different misalignment levels and obtain the expected index data;

[0052] A test result generation module, which is used to generate a business test result according to the expected index data and the actual assessment index data.

[0053] The present invention provides a method and system for automatic testing of power supply station services based on digital employees. The method uses digital employee technology to trigger the collection of single-phase meter measurement data in the service area to be tested in the power supply station, and extracts features from the single-phase meter measurement data to obtain measurement misalignment feature data. It uses a support vector machine to analyze the single-phase meter measurement data and calculates the key assessment index values for each distribution transformer area. The key assessment index values include the line loss rate and the electricity quantity difference rate for each distribution transformer area. According to the deviation amplitude of the single-phase meter measurement data and the measurement misalignment feature data, the distribution data of the single-phase meter measurement misalignment level is determined. Taking the distribution data of the single-phase meter measurement misalignment level as the independent variable and the key assessment index values of each distribution transformer area as the dependent variable, an association model between the misalignment degree and the key assessment index of the distribution transformer area is established. Combining the association model, using a pre-constructed long short-term memory neural network to predict the change trend of the key assessment index of the test point under different misalignment levels, and obtaining the expected index data. According to the expected index data and the actual assessment index data, a service test result is generated. Compared with the prior art, this method can effectively identify the problem of single-phase meter measurement misalignment, predict the impact of misalignment on the assessment index of the distribution transformer area, thereby realizing the automatic management of power supply station services and improving the work efficiency and management level of the power supply station. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 is a schematic flow chart of a method for automatic testing of power supply station services based on digital employees provided by an embodiment of the present invention;

[0055] Figure 2 is a block diagram of a system for automatic testing of power supply station services based on digital employees provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0056] The following specifically illustrates the embodiments of the present invention in conjunction with the drawings. The given embodiments are only for illustrative purposes and should not be construed as a limitation of the present invention. The drawings are only for reference and illustration, and do not constitute a limitation on the scope of protection of the present invention's patent, because many changes can be made to the present invention without departing from the spirit and scope of the present invention.

[0057] Refer to Figure 1 , an embodiment of the present invention provides a method for automatic testing of power supply station services based on digital employees. As Figure 1 shown, the method includes the following steps:

[0058] S1. Use digital employee technology to trigger the collection of single-phase meter measurement data in the service area to be tested in the power supply station, and extract features from the single-phase meter measurement data to obtain measurement misalignment feature data; the single-phase meter measurement data includes power data, voltage data, and current data.

[0059] In this embodiment, the steps of extracting the characteristic data of the single-phase meter measurement data to obtain the measurement misalignment characteristic data include:

[0060] Adopt the five-point linear interpolation method to fill the breakpoints and missing points of the single-phase meter measurement data to obtain the single-phase meter measurement completed data;

[0061] Filter the single-phase meter measurement completed data through a seven-point sliding median filter window to obtain the single-phase meter measurement filtered data;

[0062] Use the Daubechies fourth-order wavelet to decompose the single-phase meter measurement filtered data into three layers to obtain high-frequency component data, and extract the amplitude mutation points from the high-frequency component data as feature points;

[0063] Construct a statistical period data window, and use the statistical period data window to extract the voltage characteristic group, current characteristic group, and power characteristic group at the feature points under a preset reference value;

[0064] Perform maximum-minimum normalization processing on the voltage characteristic group, the current characteristic group, and the power characteristic group respectively to obtain the corresponding standardized characteristic data; the standardized characteristic data includes standardized voltage characteristic data, standardized current characteristic data, and standardized power characteristic data;

[0065] According to all the standardized characteristic data under the voltage characteristic dimension, current characteristic dimension, and power characteristic dimension, use the weighted average method to calculate the characteristic weight coefficient of each standardized characteristic data;

[0066] Take the standardized characteristic data with the characteristic weight coefficient exceeding the preset misalignment threshold as the measurement misalignment characteristic data.

[0067] Specifically, the business data of the power supply station covers the measurement data of various types of electricity meters, including but not limited to single-phase meters, three-phase meters, etc. These data are an important part of the power management of the power supply station and involve multiple aspects such as the management, verification, rotation of electricity measurement devices, and the prevention and handling of faults and errors. The measurement data of single-phase meters can be used to test and evaluate multiple operations of the power supply station. As the executor or tool of automated testing, the digital employee instructs or triggers the data collection process of the data collection device through its program logic. In this embodiment, the digital employee technology is used to automatically trigger the data collection system to collect the measurement data of single-phase meters involved in the business area to be tested in the power supply station. This data contains key information such as voltage data, current data, and power data. For the breakpoint and missing data in the single-phase meter measurement time-series data, this embodiment uses the five-point linear interpolation method to fill in the breakpoints and missing points in the single-phase meter measurement data. For example, two valid data points before and after the breakpoint are selected, a total of five points, and the filled value at the breakpoint is calculated through the linear interpolation formula to obtain the filled data of the single-phase meter measurement. For the filled single-phase meter measurement data, this embodiment filters the filled data of the single-phase meter measurement through a seven-point sliding median filter window, that is, a window containing seven data points is slid on the data sequence, and the data in each window is sorted by amplitude, and the value at the middle position is taken as the filtering result of the window. At the same time, in the filtering result, the mean and standard deviation of voltage, current, and power factor are calculated, and the values outside the three times standard deviation range are regarded as outliers and removed to ensure the accuracy of the data, remove noise and outliers, and thus obtain the filtered data of the single-phase meter measurement. Then, this embodiment uses the Daubechies fourth-order wavelet (abbreviated as db4 wavelet) to decompose the filtered data of the single-phase meter measurement into three layers to obtain high-frequency component data. Amplitude mutation points are extracted from the high-frequency component data, and these mutation points are the feature points. Based on the feature points, a statistical period data window is constructed. For example, with a 10-minute period, the data within each period is statistically calculated to provide a basis for subsequent feature calculation.

[0068] According to the feature points and the statistical period data window, under the preset reference values (such as rated voltage, rated current, power factor, etc.), a voltage feature group, a current feature group, and a power feature group are respectively extracted. These feature groups contain feature values in their respective fields, such as voltage volatility, phase offset, crest factor, etc. Specifically, in this embodiment, the root mean square value of voltage, voltage crest-to-average ratio, and voltage volatility are used as the voltage feature group; the current crest factor and current distortion degree are used as the current feature group; the power fluctuation degree and phase offset are used as the power feature group; then, maximum-minimum normalization processing is respectively performed on the voltage feature group, the current feature group, and the power feature group to map the feature values into the interval from 0 to 1, obtaining the corresponding standardized voltage feature data, standardized current feature data, and standardized power feature data. According to all the standardized feature data (i.e., standardized voltage feature data, standardized current feature data, and standardized power feature data), the feature weight coefficients of each standardized feature data are calculated by using the weighted average method according to the voltage feature dimension, current feature dimension, and power feature dimension. The calculation of the feature weight coefficients is to evaluate the importance of each feature point in the overall dimensional features. The feature weight coefficients exceeding the preset threshold indicate that the feature point has a significant impact on the out-of-accuracy feature recognition, so the standardized feature data with the feature weight coefficients exceeding the preset out-of-accuracy threshold are marked as measurement out-of-accuracy feature data.

[0069] S2. Analyze the single-phase meter measurement data by using a support vector machine and calculate the key assessment index values of each substation area.

[0070] In this embodiment, the steps of analyzing the single-phase meter measurement data by using a support vector machine and calculating the key assessment index values of each substation area include:

[0071] Extract key feature points from the single-phase meter measurement data by using the principal component analysis algorithm and collect the historical load data of the key feature points;

[0072] Analyze the historical load data by using the support vector regression algorithm to identify the load distribution patterns of the key feature points;

[0073] According to the load distribution patterns of the key feature points, calculate the synchronous load mean value by using the statistical analysis method;

[0074] Calculate the difference between the current electricity quantity value of the key feature point and the synchronous load mean value, and calculate the electricity quantity difference rate of the substation area;

[0075] Determine the reference value of the line loss rate, and calculate the transformer loss compensation value, conductor loss compensation value, and contact loss compensation value according to the single-phase meter measurement data;

[0076] Determine the line loss rate of the substation area based on the difference between the line loss rate reference value and the transformer loss compensation value, the wire loss compensation value, and the contact loss compensation value, and integrate the line loss rate of the substation area and the power quantity difference rate of the substation area to form the key assessment index value of the substation area.

[0077] Specifically, in this embodiment, the principal component analysis algorithm is used to extract key feature points from the single-phase meter measurement data, and the historical load data of the key feature points is collected. The support vector regression (SVR) algorithm is used to analyze these data. As a supervised learning algorithm, the support vector regression algorithm can find the optimal hyperplane so that the data points are within the boundary of the hyperplane, thereby mining and identifying the law of load change and realizing the accurate identification of the load distribution pattern. According to the load distribution pattern of the identified key feature points, statistical analysis methods (such as mean calculation) are used to predict the current load level to obtain the synchronous load mean value, and this mean value is used as the benchmark for subsequent comparison and can be used to identify the load fluctuation situation.

[0078] In this embodiment, the key assessment index value includes the line loss rate and the power quantity difference rate of each substation area. These indexes are the key to evaluating the business performance of the power supply station. In this embodiment, the deviation degree between the current power quantity value of the key feature point and the synchronous load mean value is calculated, and the power quantity difference rate of the substation area is obtained accordingly to reflect the change of the power quantity of the substation area; for the line loss rate of the substation area, in this embodiment, the line loss rate reference value is determined according to the power loss level of the substation area in the ideal state. According to the line loss rate reference value, combined with various loss factors such as the transformer loss compensation value, the wire loss compensation value, and the contact loss compensation value, the actual line loss rate of the substation area is calculated to more accurately evaluate the power loss situation of the substation area. The calculation of these compensation values is based on the physical characteristics of the transformer and the power system, such as no-load loss and load loss. Among them, for the calculation process of the transformer loss compensation value, in this embodiment, the input power and output power of the transformer are obtained according to the single-phase meter measurement data, and the load loss is calculated according to the ratio of the difference between the input power and output power of the transformer to the transformer efficiency. The transformer loss compensation value is obtained according to the no-load loss value and the load loss of the transformer; for the calculation process of the wire loss compensation value, in this embodiment, the current value flowing through the wire is obtained according to the single-phase meter measurement data, and the wire loss is calculated according to the current value flowing through the wire. When calculating the line loss rate of the substation area, the average value of the wire loss is used as the wire loss compensation value; for the contact loss compensation value, in this embodiment, the current value flowing through the contact point is obtained according to the single-phase meter measurement data, and the contact loss is calculated according to the current value flowing through the contact point and the contact resistance. When calculating the line loss rate of the substation area, the average value of the contact loss is used as the contact loss compensation value.

[0079] S3. Determine the single-phase meter measurement inaccuracy level distribution data according to the single-phase meter measurement data deviation amplitude and the measurement inaccuracy characteristic data.

[0080] In this embodiment, the step of determining the single-phase meter measurement inaccuracy level distribution data according to the single-phase meter measurement data deviation amplitude and the measurement inaccuracy characteristic data includes:

[0081] Based on the measurement inaccuracy characteristic data and the single-phase meter measurement standard value, obtain the single-phase meter measurement data deviation amplitude, where the single-phase meter measurement data deviation amplitude includes the voltage deviation amplitude, current deviation amplitude, and power factor deviation amplitude of the single-phase meter measurement data;

[0082] Determine a moving data window, and perform statistical analysis on the single-phase meter measurement data deviation amplitude within the moving data window to obtain the measurement deviation amplitude characteristics; the measurement deviation amplitude characteristics include the deviation mean, deviation standard deviation, and maximum deviation value of the single-phase meter measurement data deviation amplitude;

[0083] Use a Gaussian Naive Bayes classifier to model the measurement deviation amplitude characteristics, and calculate the characteristic distribution probability values of each measurement deviation amplitude characteristic at different inaccuracy levels;

[0084] Based on the characteristic distribution probability values and the preset characteristic inaccuracy level probability distribution interval, perform inaccuracy level division on the measurement inaccuracy characteristic data to determine the single-phase meter measurement inaccuracy level distribution data.

[0085] Specifically, in this embodiment, based on the measurement inaccuracy characteristic data and the single-phase meter measurement standard value, calculate the voltage deviation amplitude, current deviation amplitude, and power factor deviation amplitude of the single-phase meter measurement data. For example, for each measurement parameter (voltage, current, power factor), the deviation amplitude can be represented by the difference between the actual measurement value and the standard value. Then, this embodiment determines an appropriate moving data window size. The moving data window should contain sufficient data points to reflect the dynamic changes of the single-phase meter measurement data. Perform statistical analysis on the single-phase meter measurement data deviation amplitude within the moving data window, and calculate measurement deviation amplitude characteristics such as the deviation mean, deviation standard deviation, and maximum deviation value. These measurement deviation amplitude characteristics can reflect the overall situation and dispersion degree of the deviation amplitude within the data window.

[0086] In this embodiment, a Gaussian Naive Bayes classifier is trained using the measurement deviation magnitude features and the corresponding out-of-accuracy level information in historical data. After the training is completed, the calculated measurement deviation magnitude features (deviation mean, deviation standard deviation, maximum deviation value) are used as the input features of the Gaussian Naive Bayes classifier, and the feature distribution probability values of each measurement deviation magnitude feature at different out-of-accuracy levels are calculated. It should be ensured that the feature distribution probability values are within the preset error range. These feature distribution probability values can reflect the distribution of features at different levels and provide a basis for subsequent level division. According to the feature distribution probability values output by the classifier, different probability distribution intervals of feature out-of-accuracy levels are set to divide the single-phase meter measurement out-of-accuracy levels. For example, the out-of-accuracy levels include normal, mild out-of-accuracy, moderate out-of-accuracy, and severe out-of-accuracy. If the probability of a feature at the normal level exceeds 95%, it is determined to be normal, thus obtaining the single-phase meter measurement out-of-accuracy level distribution data.

[0087] S4. Using the single-phase meter measurement out-of-accuracy level distribution data as the independent variable and the key assessment index values of each substation area as the dependent variable, establish an association model between the out-of-accuracy degree and the key assessment indexes of the substation area.

[0088] In this embodiment, the steps of establishing an association model between the out-of-accuracy degree and the key assessment indexes of the substation area, with the single-phase meter measurement out-of-accuracy level distribution data as the independent variable and the key assessment index values of each substation area as the dependent variable, include:

[0089] Perform normalization processing on the single-phase meter measurement out-of-accuracy level distribution data to obtain normalized out-of-accuracy level distribution data;

[0090] Use a random forest regressor to model the relationship between the normalized out-of-accuracy level distribution data and the key assessment index values of each substation area to obtain an association model between the out-of-accuracy degree and the key assessment indexes of the substation area.

[0091] Specifically, in this embodiment, normalization processing is performed on the single-phase meter measurement out-of-accuracy level distribution data, that is, the values of each level are mapped to the interval [0, 1] to eliminate the influence of the dimension between different levels and facilitate subsequent modeling analysis. At the same time, preprocessing is performed on the key assessment index values of the substation area (substation area line loss rate and substation area power consumption difference rate) to ensure their consistency with the normalized out-of-accuracy level distribution data in the time and space dimensions. Then, the normalized out-of-accuracy level distribution data is used as the input feature, and the preprocessed substation area assessment index values are used as the target variable. A random forest regressor is used to learn and model the potential relationship between the normalized out-of-accuracy level distribution data and the key assessment index values of the substation area, capture the influence of different measurement error levels on the substation area assessment indexes, and finally obtain an association model of the relationship between the out-of-accuracy degree and the assessment indexes, providing a scientific basis for the intelligent management and decision-making of the power supply station.

[0092] S5. Combine the correlation model and use a pre - constructed long short - term memory neural network to predict the change trend of the key assessment indicators of the test points at different misalignment levels, and obtain the expected indicator data.

[0093] In this embodiment, the step of combining the correlation model and using a pre - constructed long short - term memory neural network to predict the change trend of the key assessment indicators of the test points at different misalignment levels and obtaining the expected indicator data includes:

[0094] Perform linear interpolation on the probability distribution interval of the characteristic misalignment level to obtain test data points;

[0095] Calculate the confidence interval value of each test data point, and detect the validity of the test data point according to the confidence interval value, and filter out the valid test data points;

[0096] Obtain the single - phase meter measurement test data of the valid test data points, and obtain the corresponding key assessment indicators of the test points through the correlation model;

[0097] Input the key assessment indicators of the test points into the pre - constructed long short - term memory neural network to predict the change trend of the key assessment indicators of the test points at different misalignment levels, and obtain the expected indicator data.

[0098] Specifically, in this embodiment, linear interpolation is performed on the probability distribution interval of the characteristic misalignment level (i.e., the misalignment interval) to supplement data, so as to generate more test data points within the misalignment interval, provide a more complete data set for the model, and thus more accurately evaluate the performance of the correlation model. In this embodiment, linear interpolation technology is used to generate a series of test data points within the probability distribution interval of the characteristic misalignment level, calculate the confidence interval value of each test data point, and judge the validity of the test data point through the confidence interval value to filter out the valid test data points and ensure the accuracy of subsequent analysis. For example, according to a preset confidence level (such as 95% confidence level), determine whether the test data point falls within the acceptable confidence interval, and identify the data points within the confidence interval as valid, otherwise consider them invalid. At the same time, in order to convert the test data into specific assessment indicator values for subsequent analysis and prediction, in this embodiment, according to the single - phase meter measurement test data of the selected valid test data points, the corresponding key assessment indicators of the test points are calculated through the correlation model, and the calculated key assessment indicators of the test points are input into the long short - term memory neural network (LSTM). This network includes input - layer nodes, hidden - layer nodes, and output - layer nodes. The LSTM network is used to predict the change trend of the key assessment indicators of the test points at different misalignment levels and obtain the expected indicator data. Thus, the accuracy and effectiveness of the test can be evaluated by comparing the expected indicator data output by the LSTM network and the actual assessment indicator data, generating business test results, and providing strong support for the business automation test of the power supply station.

[0099] S6. Generate a business test result based on the expected index data and the actual assessment index data.

[0100] In this embodiment, the step of generating a business test result based on the expected index data and the actual assessment index data includes:

[0101] Compare the expected index data with the actual assessment index data. If the comparison result of the expected index data and the actual assessment index data is consistent, it is determined that the business test result is passed; if the comparison result of the expected index data and the actual assessment index data is inconsistent, it is determined that the business test result is failed.

[0102] The embodiment of the present invention provides a digital-employee-based automated testing method for power supply station services. The method uses digital employee technology to trigger the collection of single-phase meter measurement data in the to-be-tested service area of the power supply station, and extracts features from the single-phase meter measurement data to obtain measurement inaccuracy feature data; uses a support vector machine to analyze the single-phase meter measurement data and calculate the key assessment index values of each substation area; determines the single-phase meter measurement inaccuracy level distribution data according to the single-phase meter measurement data deviation range and the measurement inaccuracy feature data; establishes an association model between the inaccuracy degree and the key assessment index of the substation area with the single-phase meter measurement inaccuracy level distribution data as the independent variable and the key assessment index values of each substation area as the dependent variable; combines the association model and uses a pre-constructed long short-term memory neural network to predict the change trend of the key assessment index of the test point under different inaccuracy levels to obtain the expected index data; generates a business test result according to the expected index data and the actual assessment index data. Compared with the prior art, the automated testing method proposed in this embodiment accurately identifies measurement inaccuracy problems and quantitatively analyzes the deviation of substation area assessment indexes through digital employee technology and machine learning algorithms, improves the accuracy and reliability of power supply station service testing, and reduces the time and cost of manual testing.

[0103] It should be noted that the magnitudes of the serial numbers of the above processes do not mean the order of execution. The order of execution of each process should be determined according to its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

[0104] In one embodiment, as Figure 2 shown, the embodiment of the present invention provides a digital-employee-based automated testing system for power supply station services, and the system includes:

[0105] The data acquisition module 101 is used to trigger the acquisition of single-phase meter measurement data in the business area to be tested in the power supply station by using digital employee technology, and extract features from the single-phase meter measurement data to obtain measurement misalignment feature data; the single-phase meter measurement data includes power data, voltage data, and current data;

[0106] The data analysis module 102 is used to analyze the single-phase meter measurement data by using a support vector machine and calculate the key performance indicator values of each substation area; the key performance indicator values include the line loss rate and the electricity quantity difference rate of each substation area;

[0107] The misalignment analysis module 103 is used to determine the single-phase meter measurement misalignment level distribution data according to the single-phase meter measurement data deviation amplitude and the measurement misalignment feature data;

[0108] The model construction module 104 is used to establish an association model between the misalignment degree and the key performance indicators of the substation area, with the single-phase meter measurement misalignment level distribution data as the independent variable and the key performance indicator values of each substation area as the dependent variable;

[0109] The expected test module 105 is used to combine the association model and use a pre-constructed long short-term memory neural network to predict the change trend of the key performance indicators of the test points at different misalignment levels to obtain expected indicator data;

[0110] The test result generation module 106 is used to generate a business test result according to the expected indicator data and the actual performance indicator data.

[0111] For the specific limitations of a power supply station business automation test system based on digital employees, reference can be made to the above limitations on a power supply station business automation test method based on digital employees, which will not be elaborated here. Those of ordinary skill in the art can realize that, combined with the various modules and steps described in the embodiments disclosed in the present application, they can be implemented by hardware, software, or a combination of both. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present application.

[0112] An embodiment of the present invention provides a power supply station service automated testing system based on digital employees. The system uses digital employee technology through a data acquisition module to trigger the acquisition of single-phase meter measurement data in the service area to be tested in the power supply station, and extracts features from the single-phase meter measurement data to obtain measurement misalignment feature data. The data analysis module analyzes the single-phase meter measurement data using a support vector machine to calculate the key assessment index values for each substation area. The misalignment analysis module determines the single-phase meter measurement misalignment level distribution data based on the single-phase meter measurement data deviation range and the measurement misalignment feature data. The model construction module takes the single-phase meter measurement misalignment level distribution data as the independent variable and the key assessment index values for each substation area as the dependent variable to establish an association model between the misalignment degree and the key assessment index of the substation area. The expected test module combines the association model and uses a pre-constructed long short-term memory neural network to predict the change trend of the key assessment index of the test point under different misalignment levels to obtain expected index data. The test result generation module generates a service test result based on the expected index data and the actual assessment index data. Compared with the prior art, the automated testing system proposed in this embodiment uses digital employee technology and machine learning algorithms to accurately identify measurement misalignment problems and quantitatively analyze the deviation of substation area assessment indicators, improving the accuracy and reliability of power supply station service testing and reducing the time and cost of manual testing.

[0113] The above embodiments only represent several preferred embodiments of the present application, and their descriptions are relatively specific and detailed, but they should not be construed as limiting the scope of the invention patent. It should be noted that for those of ordinary skill in the art of this technology, without departing from the technical principle of the present invention, several improvements and substitutions can still be made, and these improvements and substitutions should also be regarded as the protection scope of the present application. Therefore, the protection scope of the patent of the present application should be subject to the protection scope of the claims.

Claims

1. A power supply station service automation testing method based on digital employees, characterized in that: The following steps are involved: The digital employee technology is used to trigger the collection of single-phase meter measurement data of the business area to be tested in the power supply station, and feature extraction is performed on the single-phase meter measurement data to obtain measurement inaccuracy feature data; The single-phase meter measurement data includes power data, voltage data and current data; The single-phase meter measurement data is analyzed by using a support vector machine to calculate the key assessment index values ​​of each substation; the key assessment index values ​​include the line loss rate and the power difference rate of each substation; Determine the single-phase meter measurement inaccuracy grade distribution data based on the single-phase meter measurement data deviation amplitude and measurement inaccuracy characteristic data; The distribution data of the inaccuracy level of single-phase meter is used as the independent variable, and the key assessment index value of each substation is used as the dependent variable, and the correlation model between the inaccuracy level and the key assessment index of the substation is established; Combined with the association model, a pre-built long short-term memory neural network is used to predict the change trend of key assessment indicators of test points under different misalignment levels to obtain expected indicator data; Generate business test results based on the expected indicator data and actual assessment indicator data; The step of using a support vector machine to analyze the single-phase meter measurement data and calculate the key assessment index values ​​of each substation includes: Extracting key characteristic points from the single-phase meter measurement data using a principal component analysis algorithm, and collecting historical load data of the key characteristic points; Using a support vector regression algorithm to analyze the historical load data and identify the load distribution pattern of key characteristic points; According to the load distribution pattern of the key characteristic points, the mean load value of the same period is calculated by using a statistical analysis method; Calculate the difference between the current power value of the key feature point and the average load value of the same period, and calculate the power difference rate of the substation; Determine a line loss rate reference value, and calculate a transformer loss compensation value, a conductor loss compensation value, and a contact loss compensation value based on the single-phase meter measurement data; Determine the line loss rate of the substation area according to the difference between the line loss rate reference value and the transformer loss compensation value, the conductor loss compensation value, and the contact loss compensation value, and integrate the line loss rate of the substation area and the power difference rate of the substation area to form a key assessment indicator value of the substation area; The step of determining the single-phase meter measurement inaccuracy grade distribution data according to the single-phase meter measurement data deviation amplitude and measurement inaccuracy characteristic data comprises: According to the measurement inaccuracy characteristic data and the single-phase meter measurement standard value, the single-phase meter measurement data deviation amplitude is obtained, and the single-phase meter measurement data deviation amplitude includes the voltage deviation amplitude, the current deviation amplitude and the power factor deviation amplitude of the single-phase meter measurement data; Determine the moving data window, and perform statistical analysis on the measurement data deviation amplitude of the single-phase meter within the moving data window to obtain the measurement deviation amplitude characteristics; The measurement deviation amplitude feature is modeled by using a Gaussian naive Bayes classifier, and the characteristic distribution probability value of each measurement deviation amplitude feature at different misalignment levels is calculated; The metering inaccuracy characteristic data is divided into inaccuracy levels according to the characteristic distribution probability value and a preset characteristic inaccuracy level probability distribution interval, and the single-phase meter metering inaccuracy level distribution data is determined.

2. A method for automated testing of power supply services based on digital employees as claimed in claim 1, characterized in that: The step of extracting features from the single-phase meter measurement data to obtain measurement inaccuracy feature data comprises: A five-point linear interpolation method is used to fill in the breakpoints and missing points of the single-phase meter measurement data to obtain the single-phase meter measurement completion data; The single-phase meter metering completion data is filtered through a seven-point sliding median filter window to obtain single-phase meter metering filtered data; Using Daubechies fourth-order wavelet to perform three-layer decomposition on the single-phase meter measurement filter data to obtain high-frequency component data, and extracting amplitude mutation points from the high-frequency component data as feature points; Constructing a statistical period data window, and using the statistical period data window to extract a voltage feature group, a current feature group, and a power feature group at the feature point under a preset reference value; Performing maximum and minimum value normalization processing on the voltage feature group, the current feature group, and the power feature group respectively to obtain corresponding standardized feature data; According to all the standardized characteristic data under the voltage characteristic dimension, the current characteristic dimension and the power characteristic dimension, a characteristic weight coefficient of each standardized characteristic data is calculated by using a weighted average method; The standardized feature data whose feature weight coefficient exceeds a preset misalignment threshold is used as measurement misalignment feature data.

3. The method for automated testing of power supply station services based on digital employees as claimed in claim 2, characterized in that: The voltage characteristic group includes voltage root mean square value, voltage peak-to-average ratio and voltage fluctuation rate; The current characteristic group includes a current peak factor and a current distortion degree; The power characteristic group includes power fluctuation and phase offset.

4. The method for automated testing of power supply station services based on digital employees as claimed in claim 1, characterized in that: The metering deviation amplitude characteristics include the deviation mean, deviation standard deviation and maximum deviation value of the deviation amplitude of the single-phase meter metering data.

5. The method for automated testing of power supply station services based on digital employees as claimed in claim 1, characterized in that: The steps of establishing a correlation model between the inaccuracy level distribution data of the single-phase meter as the independent variable and the key assessment index value of each substation as the dependent variable include: Normalizing the single-phase meter measurement inaccuracy level distribution data to obtain normalized inaccuracy level distribution data; A random forest regressor is used to model the relationship between the normalized misalignment level distribution data and the key assessment indicator values ​​of each substation, so as to obtain a correlation model between the misalignment degree and the key assessment indicators of the substation.

6. The method for automated testing of power supply station services based on digital employees as claimed in claim 1, characterized in that: The step of combining the association model and using the pre-built long short-term memory neural network to predict the change trend of the key assessment indicators of the test points under different misalignment levels to obtain the expected indicator data includes: Performing linear interpolation on the probability distribution interval of the feature misalignment level to obtain a test data point; Calculating the confidence interval value of each of the test data points, and detecting the validity of the test data points according to the confidence interval value, and screening out valid test data points; Acquire the single-phase meter measurement test data of the valid test data point, and obtain the corresponding key assessment indicators of the test point through the association model; The key assessment indicators of the test points are input into the pre-built long short-term memory neural network to predict the change trends of the key assessment indicators of the test points under different inaccuracy levels to obtain the expected indicator data.

7. The method for automated testing of power supply station services based on digital employees as claimed in claim 1, characterized in that: The step of generating a business test result according to the expected indicator data and the actual assessment indicator data includes: The expected indicator data is compared with the actual assessment indicator data. If the comparison results of the expected indicator data and the actual assessment indicator data are consistent, the business test result is determined to be a test pass; if the comparison results of the expected indicator data and the actual assessment indicator data are inconsistent, the business test result is determined to be a test failure.

8. A power supply station business automation test system based on digital employees, characterized in that: The system comprises: A data acquisition module is used to trigger the acquisition of single-phase meter measurement data of the business area to be tested in the power supply station by using digital employee technology, and to extract features of the single-phase meter measurement data to obtain measurement inaccuracy feature data; the single-phase meter measurement data includes power data, voltage data and current data; A data analysis module is used to analyze the single-phase meter measurement data using a support vector machine to calculate the key assessment index values ​​of each substation; the key assessment index values ​​include the line loss rate and the power difference rate of each substation; The inaccuracy analysis module is used to determine the single-phase meter inaccuracy grade distribution data according to the single-phase meter metering data deviation amplitude and metering inaccuracy characteristic data; A model building module is used to establish a correlation model between the degree of inaccuracy and the key assessment indicators of the substation using the distribution data of the inaccuracy level of the single-phase meter as the independent variable and the key assessment indicator values ​​of each substation as the dependent variable; An expected test module is used to combine the association model and use a pre-built long short-term memory neural network to predict the change trend of key assessment indicators of test points under different misalignment levels to obtain expected indicator data; A test result generation module, used to generate a business test result based on the expected indicator data and the actual assessment indicator data; The method of using a support vector machine to analyze the single-phase meter measurement data and calculate the key assessment index values ​​of each substation specifically includes: Extracting key characteristic points from the single-phase meter measurement data using a principal component analysis algorithm, and collecting historical load data of the key characteristic points; Using a support vector regression algorithm to analyze the historical load data and identify the load distribution pattern of key characteristic points; According to the load distribution pattern of the key characteristic points, the mean load value of the same period is calculated by using a statistical analysis method; Calculate the difference between the current power value of the key feature point and the average load value of the same period, and calculate the power difference rate of the substation; Determine a line loss rate reference value, and calculate a transformer loss compensation value, a conductor loss compensation value, and a contact loss compensation value based on the single-phase meter measurement data; Determine the line loss rate of the substation area according to the difference between the line loss rate reference value and the transformer loss compensation value, the conductor loss compensation value, and the contact loss compensation value, and integrate the line loss rate of the substation area and the power difference rate of the substation area to form a key assessment indicator value of the substation area; Determining the single-phase meter measurement inaccuracy grade distribution data according to the single-phase meter measurement data deviation amplitude and measurement inaccuracy characteristic data specifically includes: According to the measurement inaccuracy characteristic data and the single-phase meter measurement standard value, the single-phase meter measurement data deviation amplitude is obtained, and the single-phase meter measurement data deviation amplitude includes the voltage deviation amplitude, the current deviation amplitude and the power factor deviation amplitude of the single-phase meter measurement data; Determine the moving data window, and perform statistical analysis on the measurement data deviation amplitude of the single-phase meter within the moving data window to obtain the measurement deviation amplitude characteristics; The measurement deviation amplitude feature is modeled by using a Gaussian naive Bayes classifier, and the characteristic distribution probability value of each measurement deviation amplitude feature at different misalignment levels is calculated; The metering inaccuracy characteristic data is divided into inaccuracy levels according to the characteristic distribution probability value and a preset characteristic inaccuracy level probability distribution interval, and the single-phase meter metering inaccuracy level distribution data is determined.

Images