An optimized method for fault detection in a honeycomb-shaped smart grid

Abstract

The present invention relates to the technical field of power grid fault location, and particularly to an optimized method for fault detection in a honeycomb-shaped smart grid. The present invention obtains the original data sequence in the smart grid, decomposes the original data sequence by using a time series decomposition algorithm to obtain an initial residual component sequence, and obtains the credibility of the initial residual component sequence according to the data distribution characteristics in the initial residual component sequence and the data difference between the initial residual component sequence and the original data sequence; if the credibility of the initial residual component sequence is not within the preset credibility range, optimize the preset parameters in the time series decomposition algorithm until the credibility of the new residual component sequence is within the preset credibility range to obtain the target residual component sequence; finally, perform fault detection on the smart grid according to the target residual component sequence. The present invention improves the accuracy of residual components for fault detection by optimizing the preset parameters in the time series decomposition algorithm.

Description

Technical Field

[0001] The present invention relates to the technical field of power grid fault location, and particularly to an optimized method for fault detection in a honeycomb-shaped smart grid. Background Art

[0002] A honeycomb-shaped smart grid is a power grid system with a distributed and modular structure. By drawing on the geometric characteristics of a honeycomb, it improves the reliability and flexibility of the power grid. Each honeycomb unit is equipped with intelligent sensors and a monitoring system, which can collect and analyze data in real time, and use advanced algorithms for fault detection to optimize system performance and resource utilization. Fault detection in a honeycomb-shaped smart grid is to ensure power supply stability, guarantee power grid safety, reduce maintenance and restoration costs, provide early warnings, improve the overall reliability of the power grid, and ensure the efficient, safe, and reliable operation of the power system to meet the social and economic demands for power supply.

[0003] Traditional fault detection methods for honeycomb-shaped smart grids usually rely on intelligent sensors equipped in honeycomb units to collect data in real time, and then obtain residuals through STL decomposition. Fault detection is carried out through the residuals after STL decomposition to identify abnormal fluctuations or emergencies. During the STL decomposition process, in order to improve the accuracy and reliability of time series data analysis, it is necessary to correct the seasonal component so that data analysis and model construction can focus on non-seasonal components, thereby providing more accurate insights to improve the effect of subsequent fault detection. However, insufficient or excessive correction of the seasonal component will indirectly affect the residuals, resulting in periodic patterns being mixed into the residuals, making abnormal signals mixed in periodic changes, or erasing important seasonal information, leading to an increase in noise. These will all reduce the accuracy of fault detection by the residuals.

[0004] Therefore, how to improve the correction effect of the seasonal component and then improve the accuracy of fault detection in a honeycomb-shaped smart grid has become an urgent problem to be solved. Summary of the Invention

[0005] In view of this, embodiments of the present invention provide an optimized method for fault detection in a honeycomb-shaped smart grid to solve the problem of how to improve the correction effect of the seasonal component and then improve the accuracy of fault detection in a honeycomb-shaped smart grid.

[0006] Embodiments of the present invention provide an optimized method for fault detection in a honeycomb-shaped smart grid, and the method includes the following steps:

[0007] Obtain grid time series data of any type in the smart grid, and preprocess the grid time series data to obtain an original data sequence;

[0008] Decompose the original data sequence using a time series decomposition algorithm to obtain an initial trend component sequence and an initial seasonal component sequence. According to the initial trend component sequence and the initial seasonal component sequence, obtain the corresponding initial residual component sequence. Based on the data distribution characteristics in the initial residual component sequence and the data difference between the initial residual component sequence and the original data sequence, obtain the credibility of the initial residual component sequence;

[0009] If the credibility of the initial residual component sequence is not within the preset credibility range, optimize the preset parameters in the time series decomposition algorithm to obtain a new trend component sequence and a new seasonal component sequence corresponding to the original data sequence. According to the new trend component sequence and the new seasonal component sequence, obtain the corresponding new residual component sequence, and repeat the method for obtaining the credibility until the credibility of the new residual component sequence is within the preset credibility range to obtain the target residual component sequence;

[0010] Perform fault detection on the smart grid according to the target residual component sequence.

[0011] Preferably, the obtaining the credibility of the initial residual component sequence according to the data distribution characteristics in the initial residual component sequence and the data difference between the initial residual component sequence and the original data sequence includes:

[0012] Obtain the degree of normal distribution of the initial residual component sequence according to the data distribution characteristics in the initial residual component sequence;

[0013] Obtain the degree of difference between the initial residual component sequence and the original data sequence according to the data difference between the initial residual component sequence and the original data sequence;

[0014] Obtain the credibility of the initial residual component sequence according to the degree of normal distribution and the degree of difference.

[0015] Preferably, the obtaining the degree of normal distribution of the initial residual component sequence according to the data distribution characteristics in the initial residual component sequence includes:

[0016] Obtain the data mean of the initial residual component sequence, obtain the number of data within the preset normal distribution region in the initial residual component sequence, calculate the ratio of the number of data within the preset normal distribution region in the initial residual component sequence to the number of data in the initial residual component sequence to obtain a first ratio, and obtain the sum of the absolute value of the data mean of the initial residual component sequence and the first ratio as the degree of normal distribution of the initial residual component sequence.

[0017] Preferably, obtaining the degree of difference between the initial residual component sequence and the original data sequence according to the data difference between the initial residual component sequence and the original data sequence includes:

[0018] Fitting the initial residual component sequence to obtain a residual component fitting curve, obtaining the original data curve composed of the original data sequence, obtaining each extreme point in the original data curve, and using each extreme point in the original data curve to divide the original data curve and the residual component fitting curve into at least two sub-curves respectively. The sub-curves of the original data curve and the sub-curves of the residual component fitting curve correspond one by one;

[0019] Obtaining the curvature of each sub-curve in the original data curve and the residual component fitting curve, respectively calculating the absolute value of the curvature difference between each sub-curve in the original data curve and the corresponding sub-curve in the residual component fitting curve, corresponding to obtain the cumulative value of the absolute values, and using the cumulative value of the absolute values as the independent variable of the sigmoid function to obtain the corresponding sigmoid function value as the degree of difference between the initial residual component sequence and the original data sequence.

[0020] Preferably, obtaining the credibility of the initial residual component sequence according to the degree of normal distribution and the degree of difference includes:

[0021] Performing a weighted summation process on the degree of normal distribution and the degree of difference, and using the obtained weighted summation result as the credibility of the initial residual component sequence.

[0022] Preferably, the preset parameters in the time series decomposition algorithm include: seasonal smoothing window and seasonal period.

[0023] Preferably, if the credibility of the initial residual component sequence is not within the preset credibility range, optimizing the preset parameters in the time series decomposition algorithm includes:

[0024] If the credibility of the initial residual component sequence is not within the preset credibility range, then within the length range of the preset seasonal smoothing window, increase or decrease the length of the seasonal smoothing window, and within the length range of the preset seasonal period, increase or decrease the length of the seasonal period.

[0025] The beneficial effects of the embodiments of the present invention compared with the prior art are:

[0026] The present invention obtains grid time-series data of any type in a smart grid, preprocesses the grid time-series data to obtain an original data sequence, decomposes the original data sequence by using a time-series decomposition algorithm to obtain an initial trend component sequence and an initial seasonal component sequence, obtains a corresponding initial residual component sequence according to the initial trend component sequence and the initial seasonal component sequence, obtains the credibility of the initial residual component sequence according to the data distribution characteristics in the initial residual component sequence and the data difference between the initial residual component sequence and the original data sequence; if the credibility of the initial residual component sequence is not within a preset credibility range, optimizes the preset parameters in the time-series decomposition algorithm to obtain a new trend component sequence and a new seasonal component sequence corresponding to the original data sequence, obtains a corresponding new residual component sequence according to the new trend component sequence and the new seasonal component sequence, repeats the method for obtaining the credibility until the credibility of the new residual component sequence is within the preset credibility range to obtain a target residual component sequence; and performs fault detection on the smart grid according to the target residual component sequence. The present invention first obtains the credibility of the initial residual component sequence. For the initial residual component sequence with low credibility, by optimizing the preset parameters in the time-series decomposition algorithm and correcting the initial seasonal component sequence, the correction effect of the seasonal component sequence is improved, thereby improving the credibility of the target residual component sequence, reducing the problem of low credibility of the residual component caused by insufficient or excessive correction of the seasonal component sequence, and improving the accuracy of the residual component for fault detection. Description of the Drawings

[0027] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for use in the embodiments or the description of the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0028] Figure 1 It is a flowchart of a method for optimizing fault detection of a honeycomb smart grid provided in Embodiment 1 of the present invention. Detailed Embodiment

[0029] The following details the embodiments of the present disclosure, and the examples of the embodiments are shown in the drawings. The embodiments described below with reference to the drawings are exemplary and are intended to explain the present disclosure and should not be construed as limiting the present disclosure.

[0030] It should be noted that the terms "first", "second", etc. in the specification of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily have to be used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. On the contrary, they are merely examples of devices and methods consistent with some aspects of the present disclosure.

[0031] In order to illustrate the technical solution of the present invention, the following will be described through specific embodiments.

[0032] See Figure 1 , which is a method flow chart of a fault detection optimization method for a honeycomb-shaped smart grid provided in the first embodiment of the present invention. As Figure 1 shown, the method may include:

[0033] Step S101, obtain grid time series data of any type in the smart grid, and preprocess the grid time series data to obtain an original data sequence.

[0034] Obtain different types of grid data in the honeycomb-shaped smart grid, such as: load data, grid status data, equipment data, etc. Collect grid data once a day, and collect each type of grid data for one year. There is no limit here and it can be set according to specific implementation scenarios to form the grid time series data corresponding to each type of grid data.

[0035] For any type of grid time series data in the honeycomb-shaped smart grid, check whether there are duplicate values and missing values in the grid time series data. Delete the duplicate values, and fill the missing values or delete the grid time series data corresponding to the missing values to obtain the original data sequence.

[0036] Step S102, decompose the original data sequence by using a time series decomposition algorithm to obtain an initial trend component sequence and an initial seasonal component sequence. According to the initial trend component sequence and the initial seasonal component sequence, obtain the corresponding initial residual component sequence. According to the data distribution characteristics in the initial residual component sequence and the data difference between the initial residual component sequence and the original data sequence, obtain the credibility of the initial residual component sequence.

[0037] The STL time series decomposition algorithm is a powerful tool for processing time series data. It can handle different types of complex seasonal data, has strong robustness to outliers, and has a clear decomposition structure. Its results can be displayed through visualization means, making it very suitable for processing various types of power grid data. Since the STL time series decomposition algorithm can decompose time series data into trend components, seasonal components, and residual components, by analyzing the residual components after STL decomposition, abnormal fluctuations or sudden events in the time series data can be effectively identified. Therefore, after obtaining the original data sequence, the STL time series decomposition algorithm is used to decompose the original data sequence to obtain the initial trend component sequence and the initial seasonal component sequence. According to the initial trend component sequence and the initial seasonal component sequence, the corresponding initial residual component sequence is obtained. The STL time series decomposition algorithm belongs to the prior art and will not be elaborated here.

[0038] In one embodiment, the parameters of the STL time series decomposition algorithm are set. The number of observation points in the seasonal period is set to 90, the length of the seasonal smoothing window is 23, the length of the trend smoothing window is 21, the step size of the seasonal smoothing window is 13, and the step size of the trend smoothing window is 11. There is no limitation here and it can be set according to the specific implementation scenario. The original data sequence is decomposed through the STL time series decomposition algorithm to obtain the initial trend component sequence and the initial seasonal component sequence. According to the initial trend component sequence and the initial seasonal component sequence, the corresponding initial residual component sequence is obtained.

[0039] Because the initial seasonal component sequence will introduce periodic fluctuations, masking the long-term trends and abnormal signals in the data, resulting in a low credibility of the obtained initial residual component sequence and inaccurate final fault detection results. Therefore, it is necessary to correct the initial seasonal component sequence to reduce the impact of these periodic fluctuations on data analysis. At the same time, it can also make the data more stable and improve the accuracy of the prediction model.

[0040] During the process of correcting the initial seasonal component sequence, since the correction of the initial seasonal component sequence changes the smoothing degree and detail capture ability of the initial seasonal component sequence, if the correction of the initial seasonal component sequence is insufficient or excessive, the part of the original data sequence allocated to the initial seasonal component sequence will change, causing the initial residual component sequence to change accordingly. For example, periodic patterns are mixed into the initial residual component sequence, making abnormal signals mixed in the periodic changes, or important seasonal information is erased, resulting in an increase in noise. These will cause the data in the initial residual component sequence to have non-normal characteristics, too high similarity with the original data sequence, etc., seriously affecting the accuracy of subsequent fault detection.

[0041] Therefore, it is necessary to analyze the data characteristics of the initial residual component sequence. Specifically, according to the data distribution characteristics in the initial residual component sequence and the data differences between the initial residual component sequence and the original data sequence, the credibility of the initial residual component sequence is obtained. According to the credibility of the initial residual component sequence, the initial seasonal component sequence is corrected to ensure the correction effect of the initial seasonal component sequence, and further ensure the accuracy of subsequent fault detection.

[0042] Among them, the method for obtaining the credibility of the initial residual component sequence includes:

[0043] (1) According to the data distribution characteristics in the initial residual component sequence, obtain the degree of normal distribution of the initial residual component sequence.

[0044] Specifically, obtain the data mean of the initial residual component sequence, obtain the number of data within the preset normal distribution region in the initial residual component sequence, calculate the ratio of the number of data within the preset normal distribution region in the initial residual component sequence to the number of data in the initial residual component sequence to obtain the first ratio, and obtain the sum of the absolute value of the data mean of the initial residual component sequence and the first ratio as the degree of normal distribution of the initial residual component sequence.

[0045] In an embodiment, calculate the degree of normal distribution of the initial residual component sequence:

[0046]

[0047] Among them, is the degree of normal distribution of the initial residual component sequence; is the i-th data in the initial residual component sequence; i is the serial number of the data in the initial residual component sequence; n is the number of data in the initial residual component sequence; is the number of data within ±3 standard deviations of the mean of the initial residual component sequence under normal distribution. There is no limit here and it can be set according to the specific implementation scenario.

[0048] It should be noted that is the data mean of the initial residual component sequence. Under normal circumstances, the initial residual component sequence will show an approximate normal distribution with 0 as the mean. The more the number of data within ±3 standard deviations of the mean of the initial residual component sequence under normal distribution, the more the initial residual component sequence conforms to the normal distribution, and the higher the degree of normal distribution of the initial residual component sequence (that is, is closer to 1), and the higher the accuracy of subsequent fault detection.

[0049] (2)Obtain the degree of difference between the initial residual component sequence and the original data sequence according to the data differences between the initial residual component sequence and the original data sequence.

[0050] Specifically, fit the initial residual component sequence to obtain a residual component fitting curve, obtain the original data curve composed of the original data sequence, obtain each extreme point in the original data curve, and use each extreme point in the original data curve to divide the original data curve and the residual component fitting curve into at least two sub-curves respectively. The sub-curves of the original data curve and the sub-curves of the residual component fitting curve correspond one by one;

[0051] Obtain the curvature of each sub-curve in the original data curve and the residual component fitting curve, calculate the absolute value of the curvature difference between each sub-curve in the original data curve and the corresponding sub-curve in the residual component fitting curve respectively, and correspondingly obtain the cumulative value of the absolute values. Take the cumulative value of the absolute values as the independent variable of the sigmoid function, and obtain the corresponding sigmoid function value as the degree of difference between the initial residual component sequence and the original data sequence.

[0052] In an embodiment, obtain the original data curve composed of the original data sequence, obtain each extreme point in the original data curve. The extreme points belong to the prior art and will not be elaborated here. Fit the initial residual component sequence to obtain a residual component fitting curve. According to the time points corresponding to each extreme point in the original data curve, the curve between every two adjacent time points forms a sub-curve. Divide the original data curve and the residual component fitting curve into t sub-curves respectively. The sub-curves of the original data curve and the sub-curves of the residual component fitting curve correspond one by one. Obtain the curvature of each sub-curve in the original data curve and the residual component fitting curve. The curvature belongs to the prior art and will not be elaborated here. Calculate the degree of difference between the initial residual component sequence and the original data sequence:

[0053]

[0054] Wherein, is the degree of difference between the initial residual component sequence and the original data sequence; is the curvature of the u-th sub-curve in the sub-curves into which the original data curve is divided; is the curvature of the u-th sub-curve in the sub-curves into which the residual component fitting curve is divided; F is the original data curve; f is the residual component fitting curve; u is the serial number of the sub-curves in the original data curve and the residual component fitting curve; t is the number of sub-curves in the original data curve and the residual component fitting curve; Sig() is the S-shaped function, also known as the S-shaped growth curve, which can map the output result to (0, 1); | | is the absolute value symbol.

[0055] It should be noted that represents the cumulative value of the absolute value of the curvature difference between the original data curves of each segment and the residual component fitting curves. The greater the curvature difference between each segment of the original data curve and the residual component fitting curve, the greater it is, and the greater the degree of difference between the initial residual component sequence and the original data sequence, indicating that the original data curve and the residual component fitting curve are less matched, the initial residual component sequence is less affected by the initial seasonal component sequence, and the accuracy of subsequent fault detection is higher.

[0056] (3) According to the degree of normal distribution and the degree of difference, obtain the credibility of the initial residual component sequence.

[0057] Specifically, perform a weighted sum processing on the degree of normal distribution and the degree of difference, and use the obtained weighted sum result as the credibility of the initial residual component sequence.

[0058] In one embodiment, calculate the credibility of the initial residual component sequence:

[0059]

[0060] Wherein, is the credibility of the initial residual component sequence; is the degree of normal distribution of the initial residual component sequence; is the degree of difference between the initial residual component sequence and the original data sequence; is the weight coefficient of the degree of normal distribution of the initial residual component sequence, ; is the weight coefficient of the degree of difference between the initial residual component sequence and the original data sequence, ; There is no limitation here, and it can be set according to the specific implementation scenario.

[0061] It should be noted that the higher the degree of normal distribution of the initial residual component sequence, the higher the credibility of the initial residual component sequence, and the higher the accuracy of subsequent fault detection; the greater the degree of difference between the initial residual component sequence and the original data sequence, the less the initial residual component sequence is affected by the initial seasonal component sequence, the higher the credibility of the initial residual component sequence, and the higher the accuracy of subsequent fault detection.

[0062] So far, the initial trend component sequence, the initial seasonal component sequence, and the initial residual component sequence decomposed by the STL time series decomposition algorithm, as well as the credibility of the initial residual component sequence, are obtained.

[0063] Step S103: If the credibility of the initial residual component sequence is not within the preset credibility range, optimize the preset parameters in the time series decomposition algorithm to obtain a new trend component sequence and a new seasonal component sequence corresponding to the original data sequence. According to the new trend component sequence and the new seasonal component sequence, obtain the corresponding new residual component sequence, and repeat the method for obtaining the credibility until the credibility of the new residual component sequence is within the preset credibility range to obtain the target residual component sequence.

[0064] The higher the credibility of the initial residual component sequence, the higher the accuracy of the initial residual component sequence in fault detection. Set the credibility range to [0.65, 1], which is not limited here and can be set according to the specific implementation scenario. When the credibility of the initial residual component sequence is within [0.65, 1], record the initial residual component sequence as the target residual component sequence. Using the target residual component sequence for fault detection can sufficiently ensure the accuracy of fault detection.

[0065] If the credibility of the initial residual component sequence is not within [0.65, 1], the normal fluctuations in the initial residual component sequence will be wrongly marked as anomalies, masking the actual abnormal distribution of the data and affecting the accuracy of the initial residual component sequence in fault detection. Therefore, it is necessary to optimize the preset parameters in the STL time series decomposition algorithm, and correct the initial seasonal component sequence again to obtain a residual component sequence whose credibility is within the credibility range.

[0066] Among them, optimizing the preset parameters in the STL time series decomposition algorithm refers to optimizing the seasonal smoothing window and the seasonal period in the STL time series decomposition algorithm. The specific optimization method is as follows:

[0067] If the credibility of the initial residual component sequence is not within the preset credibility range, then within the length range of the preset seasonal smoothing window, increase or decrease the length of the seasonal smoothing window, and within the length range of the preset seasonal period, increase or decrease the length of the seasonal period.

[0068] In one embodiment, the length range of the seasonal smoothing window is set to [3, 43]. If the credibility degree of the initial residual component sequence is not within [0.65, 1], taking 0.35 as the demarcation point, the credibility degree range not within [0.65, 1], that is, (0, 0.65), is divided into a first range and a second range. [0.35, 0.65) is the first range, and (0, 0.35) is the second range. When the credibility degree of the initial residual component sequence is within the first range, on the basis of the seasonal smoothing window having a length of 23, it is increased or decreased by 2 each time; when the credibility degree of the initial residual component sequence is within the second range, on the basis of the seasonal smoothing window having a length of 23, it is increased or decreased by 4 each time. There is no limitation here and it can be set according to the specific implementation scenario.

[0069] The length range of the seasonal period is set to [80, 100]. If the credibility degree of the initial residual component sequence is not within [0.65, 1], it is adjusted within the length range [80, 100] of the seasonal period. On the basis of the number of observation points in the seasonal period being 90, it is increased or decreased by 1 each time. There is no limitation here and it can be set according to the specific implementation scenario.

[0070] Illustrative example: Assume that the seasonal smoothing window is a sliding window including 23 days of data volume, and the seasonal period is 90 days of data volume. If the credibility degree of the initial residual component sequence is not within [0.65, 1], when the credibility degree of the initial residual component sequence is within [0.35, 0.65), then the seasonal smoothing window is adjusted to a sliding window including 21 days or 25 days of data volume, and the seasonal period is adjusted to 89 days or 91 days of data volume; if the credibility degree of the initial residual component sequence is less than 0.35, then the seasonal smoothing window is adjusted to a sliding window including 19 days or 27 days of data volume, and the seasonal period is adjusted to 89 days or 91 days of data volume.

[0071] After optimizing the preset parameters in the time series decomposition algorithm, the original data sequence is re - decomposed by STL using the optimized seasonal smoothing window and seasonal period to obtain a new trend component sequence and a new seasonal component sequence corresponding to the original data sequence. According to the new trend component sequence and the new seasonal component sequence, a corresponding new residual component sequence is obtained. Referring to the method for obtaining the credibility degree of the initial residual component sequence, the credibility degree of the new residual component sequence is obtained. If the credibility degree of the new residual component sequence is not within [0.65, 1], the preset parameters in the time series decomposition algorithm are optimized again, and so on, until the credibility degree of the new residual component sequence is within [0.65, 1], and a target residual component sequence is obtained.

[0072] Thus far, a target residual component sequence with a credibility degree within the preset credibility degree range is obtained.

[0073] Step S104: Perform fault detection on the smart grid according to the target residual component sequence.

[0074] After obtaining the target residual component sequence with the credibility within the preset credibility range, since the credibility of the target residual component sequence is within the preset credibility range, the accuracy of fault detection can be sufficiently guaranteed when using the target residual component sequence for fault detection.

[0075] Obtain the target residual component sequence of the grid time-series data according to the above steps, and perform fault detection on the honeycomb smart grid according to the target residual component sequence in the grid time-series data. Using the target residual component sequence for fault detection belongs to the prior art and will not be elaborated here. Classify the detected faults according to the type of grid time-series data, such as equipment faults, load abnormalities, communication problems, etc. Verify the fault results using methods such as cross-validation to ensure the accuracy of detection. Then conduct on-site investigations or remote diagnoses, check the equipment status to confirm the fault area location, and at the same time take repair measures and emergency response procedures to isolate, restore power supply or start the backup system, and compile a fault detection and handling report. Optimize the detection algorithm, system configuration or maintenance process according to the results and feedback to improve the safety and reliability of fault detection for the honeycomb smart grid.

[0076] In summary, this embodiment obtains grid time-series data of any type in the smart grid, preprocesses the grid time-series data to obtain an original data sequence, decomposes the original data sequence using a time-series decomposition algorithm to obtain an initial trend component sequence and an initial seasonal component sequence, obtains a corresponding initial residual component sequence based on the initial trend component sequence and the initial seasonal component sequence, obtains the credibility of the initial residual component sequence according to the data distribution characteristics in the initial residual component sequence and the data difference between the initial residual component sequence and the original data sequence. If the credibility of the initial residual component sequence is not within the preset credibility range, optimize the preset parameters in the time-series decomposition algorithm to obtain a new trend component sequence and a new seasonal component sequence corresponding to the original data sequence, obtain a corresponding new residual component sequence according to the new trend component sequence and the new seasonal component sequence, repeat the method for obtaining the credibility until the credibility of the new residual component sequence is within the preset credibility range to obtain a target residual component sequence, and perform fault detection on the smart grid according to the target residual component sequence. This embodiment first obtains the credibility of the initial residual component sequence. According to the credibility of the initial residual component sequence, for the initial residual component sequence with low credibility, by optimizing the preset parameters in the time-series decomposition algorithm, the credibility of the target residual component sequence is improved, reducing the problem of inaccurate fault detection caused by low credibility of the residual component and improving the accuracy of the residual component for fault detection.

[0077] The above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments or perform equivalent replacements on some of the technical features. These modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention and should all be included in the protection scope of the present invention.

Claims

1. A fault detection optimization method for a cellular smart grid, characterized in that: The method comprises: Acquire any type of grid time series data in the smart grid, preprocess the grid time series data, and obtain an original data sequence; Decomposing the original data sequence by using a time series decomposition algorithm to obtain an initial trend component sequence and an initial seasonal component sequence, and obtaining a corresponding initial residual component sequence according to the initial trend component sequence and the initial seasonal component sequence; According to the data distribution characteristics in the initial residual component sequence, the normal distribution degree of the initial residual component sequence is obtained; according to the data difference between the initial residual component sequence and the original data sequence, the difference degree between the initial residual component sequence and the original data sequence is obtained; according to the normal distribution degree and the difference degree, the credibility of the initial residual component sequence is obtained; If the credibility of the initial residual component sequence is not within the preset credibility range, the preset parameters in the time series decomposition algorithm are optimized to obtain a new trend component sequence and a new seasonal component sequence corresponding to the original data sequence, and a corresponding new residual component sequence is obtained according to the new trend component sequence and the new seasonal component sequence, and the credibility acquisition method is repeated until the credibility of the new residual component sequence is within the preset credibility range, thereby obtaining a target residual component sequence; According to the target residual component sequence, fault detection is performed on the smart grid.

2. A fault detection optimization method for a cellular smart grid according to claim 1, characterized in that: The step of obtaining the normal distribution degree of the initial residual component sequence according to the data distribution characteristics in the initial residual component sequence includes: Obtain the data mean of the initial residual component sequence, obtain the number of data in the initial residual component sequence that is within a preset normal distribution area, calculate the ratio of the number of data in the initial residual component sequence that is within a preset normal distribution area to the number of data in the initial residual component sequence to obtain a first ratio, and obtain the sum of the absolute value of the data mean of the initial residual component sequence and the first ratio as the degree of normal distribution of the initial residual component sequence.

3. A fault detection optimization method for a cellular smart grid according to claim 1, characterized in that: The obtaining, according to the data difference between the initial residual component sequence and the original data sequence, the degree of difference between the initial residual component sequence and the original data sequence comprises: Fitting the initial residual component sequence to obtain a residual component fitting curve, obtaining an original data curve composed of the original data sequence, obtaining each extreme point in the original data curve, and using each extreme point in the original data curve to divide the original data curve and the residual component fitting curve into at least two sub-curves, respectively, and the sub-curves of the original data curve and the sub-curves of the residual component fitting curve correspond to each other one by one; The curvature of each sub-curve in the original data curve and the residual component fitting curve is obtained, and the absolute value of the curvature difference between each sub-curve in the original data curve and the corresponding sub-curve in the residual component fitting curve is calculated respectively, and the accumulated value of the absolute value is obtained accordingly, and the accumulated value of the absolute value is used as the independent variable of the sigmoid function to obtain the corresponding sigmoid function value as the difference degree between the initial residual component sequence and the original data sequence.

4. A fault detection optimization method for a cellular smart grid according to claim 1, characterized in that: The obtaining the credibility of the initial residual component sequence according to the normal distribution degree and the difference degree includes: The normal distribution degree and the difference degree are weighted and summed, and the obtained weighted summation result is used as the credibility of the initial residual component sequence.

5. A fault detection optimization method for a cellular smart grid according to claim 1, characterized in that: The preset parameters in the time series decomposition algorithm include: seasonal smoothing window and seasonal cycle.

6. A fault detection optimization method for a cellular smart grid according to claim 5, characterized in that: If the credibility of the initial residual component sequence is not within a preset credibility range, optimizing the preset parameters in the time series decomposition algorithm includes: If the credibility of the initial residual component sequence is not within the preset credibility range, the length of the seasonal smoothing window is increased or decreased within the preset length range of the seasonal smoothing window, and the length of the seasonal cycle is increased or decreased within the preset length range of the seasonal cycle.

Images