A method and system for visualizing power grid data based on big data processing

By calculating the anomaly degree and weight of sub-data points in the power grid data, performing interpolation processing and building a rectangular window, the problem of grid data incompleteness is solved and the data accuracy and visualization effect are improved.

CN118551167BActive Publication Date: 2024-11-19HUBEI CENT CHINA TECH DEV OF ELECTRIC POWER
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411013128.1
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-07-26
Publication Date
2024-11-19
Estimated Expiration
2044-07-26

AI Technical Summary

Technical Problem

During the collection and transmission of power grid data, due to noise, electromagnetic interference, network failure and communication protocol errors, the collected power grid data is incomplete, which in turn affects the accuracy of the data, and it is difficult for the existing technology to effectively process and visualize it.

Method used

Using a method based on big data processing, the degree of exception and weight of sub-data points on both sides of the target data point is calculated, and the complete data is obtained, and visualized in the construction rectangular window to ensure the accuracy of the data.

Benefits of technology

It improves the accuracy of interpolation results, enhances the integrity of grid data and the accuracy after visual processing, reduces the impact of abnormal data, avoids errors, and provides more reliable data characteristics.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118551167B_ABST
    Figure CN118551167B_ABST
Patent Text Reader

Abstract

The present invention relates to the field of data processing technology, and in particular to a method and system for visualizing power grid data based on big data processing. The method includes the steps of: obtaining first power grid data to be interpolated, the first power grid data including data points to be interpolated; taking the data points to be interpolated as target data points, the data points on both sides of the target data points as sub-data points, calculating the abnormality of the data points on both sides of the target data points and determining the weight of each sub-data point, performing weighted calculation according to the sub-data points and their weights to obtain the interpolation result of the target data point, inserting the obtained interpolation result into the first power grid data to replace the target data point, and obtaining the complete first power grid data; constructing a rectangular window to realize the visualization of the complete first power grid data, so that the accuracy of the first power grid data after visualization can be effectively improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a method and system for visualizing power grid data based on big data processing. Background Art

[0002] With the rapid development of the power industry, the application of power systems in life has become increasingly widespread, including power supply, lighting, communications, transportation, industry, and medical fields. The operation of the power grid system supports the normal operation of modern society and is one of the indispensable infrastructures in modern society, providing important energy support for people's production and life. Therefore, accurately obtaining the power grid data in the power system and determining the status of the power grid system based on the power grid data will help the staff to maintain and repair the power grid system in a timely manner and reduce losses.

[0003] The application document with publication number CN117150434A discloses a power grid data processing method and system. The method obtains a set of power grid data to be processed, performs data cleaning operations on the power grid data based on the attribute information of each power grid data, and finally obtains the target fused power grid data to ensure the quality of the transmitted data.

[0004] However, during the collection and transmission of power grid data, the collected power grid data may be incomplete due to noise and electromagnetic interference in the surrounding environment; or when transmitting power grid data, the collected power grid data may be lost due to network failures and communication protocol errors. Processing power grid data based on missing data points will result in low accuracy of the power grid data obtained after processing by the power grid system terminal. Based on this, how to obtain more accurate visual power grid data based on incomplete power grid data is an urgent problem to be solved by technicians in this field. Summary of the invention

[0005] In order to solve the technical problem of how to obtain highly accurate visualized power grid data based on incomplete power grid data, the present invention provides a power grid data visualization method and system based on big data processing.

[0006] In a first aspect, the present invention provides a method for visualizing power grid data based on big data processing, which adopts the following technical solution:

[0007] A method for visualizing power grid data based on big data processing, comprising the steps of:

[0008] Acquire first power grid data to be interpolated, wherein the first power grid data includes data points to be interpolated;

[0009] The data point to be interpolated is taken as the target data point, and the data points on both sides of the target data point are taken as sub-data points. The abnormality degree of the data points on both sides of the target data point is calculated; and the weight of each sub-data point is calculated:

[0010] ; In the formula, Indicates The target data point The weight of each sub-data point, Indicates The target data point and The sampling time interval between sub-data points is Indicates The target data point The grid data value corresponding to each sub-data point is: Indicates The target data point The predicted value of the power grid data corresponding to each sub-data point, Indicates The target data point The abnormality of each sub-data point, Indicates A natural exponential function with α as the base; performing weighted calculation according to the sub-data points and their weights to obtain an interpolation result of the target data point, inserting the obtained interpolation result into the first power grid data to replace the target data point, and obtaining the complete first power grid data; constructing a rectangular window to realize the visualization of the complete first power grid data.

[0011] The effect is that by providing an accurate calculation method for sub-data point weights, when determining the interpolation result of the target data point, the influence of normal sub-data points is increased by assigning weights, while the influence of abnormal sub-data points is reduced, thereby effectively improving the accuracy of the interpolation result obtained; further, by inserting the interpolation result with higher accuracy into the data point to be interpolated in the first power grid data, the complete target first power grid data can be obtained, effectively improving the accuracy of the first power grid data after visualization processing.

[0012] According to a power grid data visualization method based on big data processing provided by the present invention, the calculation of the abnormality of data points on both sides of a target data point includes: based on the position of the target data point in the power grid data, obtaining a reference data segment of a sub-data point of the target data point, and calculating the abnormality of data points on both sides of the target data point: ; In the formula, Indicates The target data point The abnormality of each sub-data point, Indicates The target data point The grid data value corresponding to each sub-data point is: Indicates The target data point The average value of the power grid data of the reference data segment, and Respectively represent The target data point The change in the power grid data value between the sub-data point and the adjacent sub-data points on the left and right, Indicates The target data point The information entropy value of a reference data segment.

[0013] The effect is that: the deviation between the sub-data point and the corresponding reference data segment is used to screen and distinguish the sub-data points obtained from the target data point, which helps to eliminate or correct abnormal data and improve data quality; further, an accurate calculation formula for the degree of abnormality of the data point is provided, and the weight of each data point can be determined based on the abnormality degree of the data point with higher accuracy, which effectively improves the accuracy of the obtained weight value.

[0014] According to a power grid data visualization method based on big data processing provided by the present invention, weighted calculation is performed according to the sub-data points and their weights to obtain the interpolation result of the target data point, including: determining the unilateral interpolation of the target data point: ; Indicates One-sided interpolation of target data points, Indicates The number of sub-data points on one side of the target data point, Indicates The target data point The weight of a unilateral sub-data point is calculated, wherein the unilateral interpolation includes left-side interpolation or right-side interpolation; and the interpolation result of the target data point is obtained according to the average of the left-side interpolation and the right-side interpolation of the target data point.

[0015] The effect is that by respectively determining the left interpolation of the target data point on the left side and the right interpolation of the target data point on the right side, the different variation forms on both sides of the target data point are fully considered, and the error caused by directly determining the interpolation of the target data point based on all the sub-data points on both sides is effectively avoided, thereby improving the accuracy of the interpolation result of the target data point.

[0016] According to a power grid data visualization method based on big data processing provided by the present invention, before inserting the obtained interpolation result into the first power grid data to replace the target data point, it also includes: performing weighted calculation on each sub-data point of the first power grid data and its weight to obtain a preliminary interpolation of the target data point and preset the weight; obtaining the interpolation result of the data point corresponding to the target data point in the complete second power grid data, and the complete second power grid data has a positive correlation with the first power grid data; screening the first power grid data according to the interpolation result, presetting weights for the mean values ​​of the screened data points, obtaining the interpolation result of the target data point according to the preset weights of the mean values ​​of the data points and the preliminary interpolation preset weights, and inserting the interpolation result into the first power grid data.

[0017] The effect is that the first power grid data is corrected by the complete second power grid data, thereby avoiding the contingency of the interpolation result determined by the single power grid data and improving the accuracy of the interpolation result of the first power grid data.

[0018] According to a power grid data visualization method based on big data processing provided by the present invention, the weighted calculation formula is: ; In the formula, Indicates The interpolation result of the target data point, represents the preliminary interpolation of the first power grid data, Indicates the interpolation result screening of the complete second power grid data The mean value of the first grid data, represents the preliminary interpolation preset weight of the first power grid data, express The mean value of the first power grid data is preset with a weight.

[0019] According to a power grid data visualization method based on big data processing provided by the present invention, the first power grid data is screened according to the interpolation result, including: obtaining the actual value of the data point corresponding to the target data point in the complete second power grid data, and determining the difference between the interpolation result and the actual value; obtaining the difference between the interpolation result and the actual value of each data point in the first power grid data; in the difference of the first power grid data, screening out a number of sub-data points whose differences are equal to those of the complete second power grid data, and calculating the mean value of the power grid data corresponding to the sub-data points.

[0020] The effect is that the overall data deviation between different types of power grid data is eliminated by calculating the difference between the interpolation result and the actual value; on the contrary, if the deviation between the two is not considered and the correction is performed directly, the final interpolation result of the first power grid data is more inclined to the data characteristics of the second power grid data rather than the data characteristics of the first power grid data itself. In this way, a more reliable basis is provided for the subsequent effective improvement of the accuracy of the visible first power grid data.

[0021] According to a power grid data visualization method based on big data processing provided by the present invention, the construction of a rectangular window to realize the visualization of the complete first power grid data includes: establishing a rectangular window in the complete first power grid data with each data point as the center, and determining the average value of the power grid data in the rectangular window based on the power grid data value in the rectangular window; using the average value of the power grid data in the rectangular window as the target power grid data value of the data point belonging to the rectangular window, and obtaining the visible first power grid data based on the target power grid data values ​​of all data points.

[0022] In a second aspect, the present invention provides a power grid data visualization system based on big data processing, which adopts the following technical solutions:

[0023] A power grid data visualization system based on big data processing includes: a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the above-mentioned power grid data visualization method based on big data processing is implemented.

[0024] By adopting the above technical solution, the above-mentioned power grid data visualization method based on big data processing is generated into a computer program and stored in a memory to be loaded and executed by a processor, so that a terminal device is made according to the memory and the processor for easy use.

[0025] The present invention has the following technical effects:

[0026] The present invention provides a new method for calculating the weight of sub-data points. By calculating the degree of abnormality of each data point, when determining the interpolation result of the first power grid data, the weight of the data point with a higher degree of abnormality is reduced, and the weight of the data point with a lower degree of abnormality is increased. In this way, the interference of the sub-data points with a higher degree of abnormality is reduced by reducing the weight, and at the same time, the increase in the weight of the normal sub-data point can reflect the real and effective data point information to a greater extent, thereby effectively improving the accuracy of the interpolation result of the first power grid data; further, the present invention also takes into account the correlation between power grid data, based on which, the complete second power grid data that is correlated with the first power grid data is introduced to correct the preliminary interpolation of the first power grid data, which can further improve the accuracy of the interpolation result of the first power grid data. Combining the improvements in the above steps, the accuracy of the first power grid data after visualization processing is finally effectively improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] By reading the detailed description below with reference to the accompanying drawings, the above and other purposes, features and advantages of the exemplary embodiments of the present invention will become readily understood. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-restrictive manner, and the same or corresponding reference numerals represent the same or corresponding parts.

[0028] Figure 1 A flow chart of a method for visualizing power grid data based on big data processing provided in an embodiment of the present invention.

[0029] Figure 2 A flow chart of another method for determining an interpolation result of a target data point provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0030] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0031] It should be understood that when the terms "first", "second", etc. are used in the claims, descriptions, and drawings of the present invention, they are only used to distinguish different objects, rather than to describe a specific order. The terms "include" and "comprise" used in the description and claims of the present invention indicate the presence of the described features, wholes, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their collections.

[0032] The embodiment of the present invention discloses a method for visualizing power grid data based on big data processing, referring to Figure 1 , Figure 1 A flowchart of a method for visualizing power grid data based on big data processing provided by an embodiment of the present invention includes the following steps S1 to S5:

[0033] S1: Acquire first power grid data to be interpolated, where the first power grid data includes data points to be interpolated.

[0034] The first power grid data is power grid data with some data points missing that need to be interpolated.

[0035] After acquiring the grid data of the grid system, anomaly detection is performed on each data point in the first grid data, and the abnormal data points corresponding to the missing grid data values ​​are the data points to be interpolated for the first grid data.

[0036] For example, the first power grid data may be voltage data, current data, frequency data, power data, temperature data, humidity data, power load data, etc., and may be specifically set according to actual needs.

[0037] The frequency data can be obtained by collecting through a frequency measuring instrument, and the power load data can be obtained by collecting through a smart meter. The collection time can be 30 minutes, and the collection frequency can be once per second. The data collection method, collection time and collection frequency can be set according to actual needs, and the embodiment of the present invention does not impose too many restrictions on this.

[0038] It is understandable that when there are missing values ​​in the power grid data, directly visualizing the power grid data may result in incomplete or misleading results of the visualized power grid data information. Based on this, in order to effectively improve the accuracy of the obtained first visible power grid data, an embodiment of the present invention provides a power grid data visualization method based on big data processing. Before visualizing the first power grid data, the weight of each sub-data point is determined by obtaining the abnormal degree of the sub-data point of the target data point. When determining the first power grid data, the accuracy of the interpolation result can be improved by adjusting the corresponding weight, that is, performing the following steps:

[0039] S2: Take the data point to be interpolated as the target data point, the data points on both sides of the target data point as sub-data points, and calculate the abnormality of the data points on both sides of the target data point.

[0040] It should be noted that since the power grid data in the power grid system generally changes regularly, the data points on both sides of the target data point can be obtained as sub-data points. In order to verify the reliability of these sub-data points, it is also necessary to obtain the reference data segments corresponding to the sub-data points. The reliability of the sub-data points can be determined by analyzing the power grid data values ​​of the sub-data points and the fluctuations of the power grid data values ​​of each data point in the reference data segments corresponding to the sub-data points.

[0041] Specifically, to obtain the sub-data points and reference data segments of the target data point, in the power grid data, with the target data point as the center, an equal number of sub-data points can be uniformly obtained on the left and right sides of the target data point; if the number of data points on one side of the target data point is insufficient, the missing number can be supplemented on the other side of the target data point. The number of sub-data points can be set according to actual needs, and the embodiment of the present invention does not impose too many restrictions on this.

[0042] For example, setting the number of sub-data points to 100 means that 50 sub-data points need to be obtained on each side of the target data point. If there are only 30 data points on the left side of the target data point, 70 sub-data points can be obtained on the right side of the target data point.

[0043] Similarly, in the power grid data, when obtaining the reference data segment corresponding to the sub-data point with the sub-data point as the center, the same amount of data points can be evenly obtained on the left and right sides of the sub-data point to form the reference data segment; if the number of data points on one side of the sub-data point is insufficient, the missing number of data points can be supplemented on the other side of the sub-data point to form the reference data segment. The length of the reference data segment can be set according to actual needs, and the embodiment of the present invention does not impose too many restrictions on this.

[0044] After obtaining the sub-data points and reference data segments of the target data points in the frequency data and the power load data respectively based on the above method, the abnormality degree of each sub-data point can be determined based on the deviation between the sub-data point and the power grid data value of the reference data segment corresponding to the sub-data point and the power grid data prediction value of the sub-data point, that is, performing the following steps:

[0045] For example, in the embodiment of the present invention, the abnormality degree of the sub-data points on both sides of the target data point may be obtained based on the position of the target data point in the power grid data.

[0046] Among them, the abnormal degree of the sub-data point satisfies the formula:

[0047] ;

[0048] In the formula, Indicates The target data point The abnormality of each sub-data point, Indicates The target data point The grid data value corresponding to each sub-data point is: Indicates The target data point The mean value of the power grid data of the reference data segment corresponding to each sub-data point, Indicates The target data point The change in the power grid data value between the sub-data point and the previous sub-data point, Indicates The target data point The change in the power grid data value between the first sub-data point and the next sub-data point, represents the normalization function, Indicates The target data point The information entropy value in the reference data segment corresponding to the sub-data point.

[0049] Among them, the power grid data prediction value can be obtained by training the ARIMA model based on the power grid data. It can be set according to actual needs, and the embodiment of the present invention does not impose too many restrictions on this.

[0050] Indicates The target data point The power grid data value of the sub-data point is The difference between the mean values ​​of the power grid data in the reference data segment corresponding to the sub-data points. The larger the value, the The target data point The lower the reference degree of a sub-data point, the higher the abnormality of the sub-data point.

[0051] Indicates The target data point The change in the power grid data value between the sub-data point and the previous sub-data point and the The target data point The sum of the absolute values ​​of the changes in the power grid data values ​​between the first sub-data point and the next sub-data point. The larger the value, the greater the The target data point The lower the credibility of a sub-data point, the higher the abnormality of the sub-data point.

[0052] Indicates The target data point The information entropy value in the reference data segment corresponding to the sub-data point is larger, indicating The greater the data fluctuation in a reference data segment and the more unstable it is, the lower the credibility of the data point corresponding to the reference data segment.

[0053] To illustrate this formula, when determining the abnormality of the 24th sub-data point of the 3rd data point in the power grid data, is 3, is 24. Correspondingly, is the grid data value of the 24th sub-data point of the 3rd data point, is the change in the power grid data value between the 23rd sub-data point and the 24th sub-data point of the 3rd data point, is the change in the power grid data value between the 24th sub-data point and the 25th sub-data point of the 3rd data point, is the entropy value of the reference data segment corresponding to the 24th sub-data point of the 3rd data point. Substituting each parameter value into the above formula, the abnormality degree of the 24th sub-data point of the 3rd data point can be determined. .

[0054] It can be understood that the higher the abnormality of the sub-data point of the target data point, the lower the credibility of the sub-data point in determining the interpolation result of the target data point, and the weight corresponding to the sub-data point should be reduced accordingly. In order to more accurately adjust the value of each sub-data point based on the weight, the weight of each sub-data point can be determined by the following steps:

[0055] S3: Calculate the weight of each sub-data point.

[0056] For example, in an embodiment of the present invention, the degree of deviation of a sub-data point can be determined based on the difference between the power grid data value corresponding to the sub-data point and the power grid data prediction value obtained by model prediction; the sampling time points of the target data point and the sub-data point are obtained to determine the sampling time interval; the weight of the sub-data point is determined based on the abnormality degree of the sub-data point, the deviation degree of the sub-data point and the sampling time interval, and the specific formula can be seen:

[0057] ;

[0058] In the formula, Indicates The target data point The weight of each sub-data point, Indicates The target data point and The sampling time interval between sub-data points is Indicates The target data point The grid data value corresponding to each sub-data point is: Indicates The target data point The predicted value of the power grid data corresponding to each sub-data point, Indicates The target data point The abnormality of each sub-data point, Indicates An exponential function with base .

[0059] The smaller the sampling time interval between the target data point and the sub-data point, the more relevant the sub-data point is for determining the interpolation value of the target data point.

[0060] It is the difference between the power grid data value corresponding to the sub-data point and the power grid data prediction value obtained by model prediction. The larger the value is, the greater the deviation of the sub-data point is.

[0061] To illustrate this formula, when determining the weight of the 24th child data point of the 3rd data point, is 3, is 24. Correspondingly, Indicates the sampling time interval between the 3rd data point and the 24th sub-data point, Indicates the power grid data value of the 24th sub-data point of the 3rd data point, Indicates the predicted value of the power grid data of the 24th sub-data point of the 3rd data point, Indicates the abnormality of the 24th child data point of the 3rd data point. Substituting each parameter value into the above formula, the weight of the 24th child data point of the 3rd data point can be determined. .

[0062] After the weights of the sub-data points are obtained based on the above steps, the interpolation result of the first power grid data can be determined based on the weights of the sub-data points and the power grid data values ​​corresponding to the sub-data points, that is, the following steps are performed:

[0063] S4: performing weighted calculation according to the sub-data points and their weights to obtain an interpolation result of the target data point, inserting the obtained interpolation result into the first power grid data to replace the target data point, and obtaining complete first power grid data.

[0064] It should be noted that the characteristics of power grid data are constantly changing in real time, so the change forms of the sub-data points on the left and right sides of the target data point may be different. By separately determining the left interpolation of the target data point to the left side and the right interpolation of the target data point to the right side, the different change forms on both sides of the target data point are fully considered, and the error caused by directly determining the interpolation of the target data point based on all the sub-data points on both sides is effectively avoided.

[0065] For example, in an embodiment of the present invention, in order to accurately obtain the interpolation result of the target data point, the unilateral interpolation of the target data point can be determined respectively, and then the interpolation result is obtained based on the average value of the unilateral interpolation.

[0066] The one-sided interpolation includes left-side interpolation or right-side interpolation.

[0067] Among them, the one-sided interpolation of the target data point can be found in the formula:

[0068] ;

[0069] In the formula, Indicates One-sided interpolation of target data points, Indicates The number of sub-data points on one side of the target data point, Indicates The target data point The weight of the one-sided sub-data point, Indicates The target data point The power grid data value corresponding to the single-side sub-data point.

[0070] In the above formula, Indicates The target data point The contribution of a single-sided sub-data point to the single-sided interpolation. The larger the value, the higher the contribution of the single-sided sub-data to the single-sided interpolation.

[0071] Based on the above steps, the unilateral interpolation of the target data point can be obtained, that is, after respectively obtaining the left interpolation and the right interpolation of the target data point based on the above steps, the average of the left interpolation and the right interpolation of the target data point is used as the interpolation result of the target data point of the first power grid data, and then the complete first power grid data can be obtained.

[0072] It should be noted that the number of data points to be interpolated for missing grid data values ​​in the first grid data may be one or more than one. Therefore, if the number of data points to be interpolated for missing grid data values ​​is more than one, all data points to be interpolated need to be interpolated based on the above steps to obtain the complete first grid data, and the following step S5 is executed:

[0073] S5: Construct a rectangular window to visualize the complete first power grid data.

[0074] It should be noted that when directly observing the power grid data obtained by the power grid system, the power grid data lacks intuitiveness and cannot intuitively display the spatial distribution, equipment layout, operating status and other information of the power grid system, which is not conducive to the staff's in-depth understanding of the actual situation of the power grid system. Therefore, it is necessary to visualize the power grid data obtained by the power grid system.

[0075] By way of example, in an embodiment of the present invention, when processing the target first power grid data to obtain visible first power grid data, a rectangular window can be established in the complete first power grid data with each data point as the center; based on the number of data points and the power grid data value in the rectangular window, the average value of the power grid data in the rectangular window is determined; the average value of the power grid data in the rectangular window is used as the target power grid data value of the data point belonging to the rectangular window, and the visible first power grid data is obtained based on the target power grid data values ​​of all data points.

[0076] It should be noted that when visualizing the first power grid data, the average value of the power grid data in the rectangular window can intuitively reflect the average degree of the data points belonging to the rectangular window and the data points on both sides, effectively reducing the impact of the outliers of a single data point on the overall data, thereby improving the accuracy of the visible first power grid data obtained after visualization processing.

[0077] For example, if the rectangular window is 11 data points long, when processing the third data point in the complete first power grid data, a rectangular window with a length of 11 can be established with the third data point as the center, and based on the power grid data values ​​corresponding to each of the 11 data points in the window, the average power grid data is determined, and the average power grid data is used as the target power grid data value of the third data point. Based on this method, all data points in the target first power grid data are processed to obtain visible first power grid data composed of the target power grid data values.

[0078] The size of the rectangular window can be set according to actual needs, and the embodiment of the present invention does not impose too many restrictions on this.

[0079] It should be noted that, in order to obtain smoother visible first power grid data, the complete first power grid data may be repeatedly processed based on the above method.

[0080] It can be seen that in an embodiment of the present invention, when visualizing power grid data, first power grid data to be interpolated can be obtained, the first power grid data including data points to be interpolated; the data points to be interpolated are taken as target data points, the data points on both sides of the target data points are taken as sub-data points, and the degree of abnormality of the data points on both sides of the target data points is calculated; the weight of each sub-data point is calculated; weighted calculation is performed based on the sub-data points and their weights, and the interpolation results obtained are inserted into the first power grid data to replace the target data points to obtain complete first power grid data; and a rectangular window is constructed to realize visualization of the complete first power grid data.

[0081] In this way, by providing a new data point weight calculation method, the accuracy of the interpolation result of the first power grid data is effectively improved; further, in order to effectively improve the weight accuracy, the present invention calculates the abnormality of each data point, and when determining the interpolation result of the first power grid data, the weight of the data point with a higher degree of abnormality is reduced, and the weight of the data point with a lower degree of abnormality is increased; further, in order to effectively improve the accuracy of the final interpolation result of the first power grid data, the present invention also introduces a complete second power grid data that is correlated with the first power grid data to determine the correction of the interpolation result of the first power grid data. Combining the above steps, the accuracy of the first power grid data after visualization processing is finally effectively improved.

[0082] In the above step S4, in order to effectively improve the interpolation result of the first power grid data, the embodiment of the present invention also provides another method for determining the interpolation result of the target data point, see Figure 2 As shown, Figure 2 A flow chart of another method for determining an interpolation result of a target data point provided by an embodiment of the present invention, the method comprising the following steps:

[0083] S201: Perform weighted calculation on each sub-data point of the first power grid data and its weight to obtain a preliminary interpolation of the target data point and preset the weight.

[0084] It should be noted that, based on steps S1-S4 in the above embodiment, a preliminary interpolation of the target data point of the first power grid data can be obtained, and the embodiment of the present invention will not be described in detail here.

[0085] It should also be noted that in order to reduce the error caused by the excessive overall fluctuation of a single type of power grid data, the embodiment of the present invention introduces complete second power grid data as a control group to achieve correction of the preliminary interpolation of the first power grid data, thereby preparing for the subsequent improvement of the accuracy of the visible first power grid data.

[0086] S202: Obtain interpolation results of data points corresponding to target data points in the complete second power grid data.

[0087] The complete second power grid data has a positive correlation with the first power grid data.

[0088] Based on steps S1 to S4 in the above embodiment, an interpolation result of the complete second power grid data can be obtained, and the embodiment of the present invention will not be described in detail here.

[0089] For example, the complete second power grid data may be voltage data, current data, frequency data, power data, temperature data, humidity data, power load data, etc., which may be specifically set according to actual needs.

[0090] It is understandable that the first power grid data and the second power grid data cannot be the same type of power grid data. The embodiment of the present invention is described by taking the first power grid data as frequency data and the second power grid data as power load data as an example, but it does not mean that the embodiment of the present invention is limited to this.

[0091] For example, based on steps S1-S4 in the above embodiment, preliminary interpolation results of frequency data and interpolation results of power load data can be obtained respectively.

[0092] After obtaining the preliminary interpolation of the target data point of the first power grid data and the interpolation result of the complete second power grid data, continue to perform the following steps:

[0093] S203: Screening the first power grid data according to the interpolation result, and presetting a weight for the mean of each data point obtained by the screening.

[0094] By way of example, in an embodiment of the present invention, the grid data mean of the first grid data can be determined by obtaining the actual value of the data point corresponding to the target data point in the complete second grid data, and determining the difference between the interpolation result and the actual value; obtaining the difference between the interpolation result and the actual value of each data point in the first grid data; and screening out, from the difference of the first grid data, a number of sub-data points that are equal to the difference with the complete second grid data, and calculating the grid data mean corresponding to the sub-data points.

[0095] It should be noted that both the first power grid data and the second power grid data are power grid data generated during the operation of the power grid system, and the data changes between the two are correlated, so the first power grid data can be corrected based on the complete second power grid data to avoid errors caused by the target interpolation of the target data point determined only by the first power grid data itself. However, the first power grid data and the second power grid data are not the same type of power grid data, so there will be deviations between the power grid data values, and the difference relationship between the two can be determined first, and then the correction can be performed.

[0096] It should be noted that, when a number of first power grid data are obtained from the difference of the first power grid data based on the difference of the second power grid data, there may be insufficient number of sub-data points corresponding to the difference in the first power grid data.

[0097] In this case, a difference floating interval may be determined based on the difference of the second power grid data, and a sufficient number of sub-data points may be obtained in the first power grid data based on the difference floating interval.

[0098] The difference floating interval may be specifically set according to the difference and actual needs, and the embodiment of the present invention does not impose too many restrictions on this.

[0099] For example, when obtaining the frequency data mean of 10 sub-data points in the frequency data, the 10 sub-data points in the frequency data can be determined first. If the difference obtained from the power load data is 0.56, and the difference interval is [0.51, 0.61], 10 sub-data points with a difference of 0.56 between the preliminary interpolation and the actual value can be obtained in the frequency data first. If the number of sub-data points with a difference of 0.56 in the frequency data is insufficient, the sub-data points with differences of 0.55 and 0.57 can be obtained preferentially near the target data point in the frequency data, and so on, until 10 sub-data points are obtained.

[0100] S204: Obtain an interpolation result of the target data point according to the average preset weight of each data point and the preliminary interpolation preset weight, and insert the interpolation result into the first power grid data.

[0101] For example, in the embodiment of the present invention, the calculation formula of the weighted correction may be:

[0102] ;

[0103] In the formula, Indicates The interpolation result of the target data point, represents the preliminary interpolation of the first power grid data, Indicates the interpolation result screening of the complete second power grid data The mean value of the first grid data, represents the preliminary interpolation preset weight of the first power grid data, express The mean value of the first power grid data is preset with a weight.

[0104] in, , It can be 0.7, It can be 0.3, which can be set according to actual needs; The first grid data The specific settings can be made according to actual needs.

[0105] After the correction of the first power grid data by the complete second power grid data is realized based on the above steps S201-S204, the interpolation result is inserted into the first power grid data to replace the target data point to obtain the complete first power grid data, and the above step S5 is continued to perform visualization processing on the complete first power grid data.

[0106] It can be seen that in the embodiment of the present invention, the present invention provides a new method for calculating the weight of sub-data points. By calculating the abnormality of each data point, when determining the interpolation result of the first power grid data, the weight of the data point with a higher degree of abnormality is reduced, and the weight of the data point with a lower degree of abnormality is increased. In this way, the interference of the sub-data points with a high degree of abnormality is reduced by reducing the weight, and at the same time, the increase in the weight of the normal sub-data point can reflect the real and effective data point information to a greater extent, thereby effectively improving the accuracy of the interpolation result of the first power grid data; further, the present invention also takes into account the correlation between power grid data, based on which, the introduction of the complete second power grid data that is correlated with the first power grid data to correct the preliminary interpolation of the first power grid data can further improve the accuracy of the interpolation result of the first power grid data. Combining the improvements in the above steps, the accuracy of the first power grid data after visualization processing is finally effectively improved.

[0107] An embodiment of the present invention also discloses a power grid data visualization system based on big data processing, including a processor and a memory, wherein the memory stores computer program instructions. When the computer program instructions are executed by the processor, a power grid data visualization method based on big data processing according to the present invention is implemented.

[0108] The above system also includes other components well known to those skilled in the art, such as a communication bus and a communication interface, and their configuration and functions are known in the art, so they will not be described in detail here.

[0109] In the present invention, the aforementioned memory may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, apparatus, or device. For example, a computer-readable storage medium may be any suitable magnetic storage medium or magneto-optical storage medium, such as a resistive random access memory RRAM, a dynamic random access memory DRAM, a static random access memory SRAM, an enhanced dynamic random access memory EDRAM, a high bandwidth memory HBM, a hybrid memory cube HMC, etc., or any other medium that can be used to store the required information and can be accessed by an application, a module, or both. Any such computer storage medium may be part of a device or accessible or connectable to a device.

[0110] Although this specification has shown and described a number of embodiments of the present invention, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Those skilled in the art will conceive of many modifications, changes and alternatives without departing from the ideas and spirit of the present invention. It should be understood that in the practice of the present invention, various alternatives to the embodiments of the present invention described herein may be employed.

[0111] The above are all preferred embodiments of the present invention, and are not intended to limit the protection scope of the present invention. Therefore, any equivalent changes made based on the structure, shape, and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for visualizing power grid data based on big data processing, characterized in that: include: Acquire first power grid data to be interpolated, the first power grid data including data points to be interpolated; The data point to be interpolated is taken as the target data point, the data points on both sides of the target data point are taken as sub-data points, and the abnormality degree of the data points on both sides of the target data point is calculated, including: based on the position of the target data point in the power grid data, obtaining the reference data segment of the sub-data point of the target data point, and calculating the abnormality degree of the data points on both sides of the target data point: ; In the formula, Indicates The target data point The abnormality of each sub-data point, Indicates The target data point The average value of the power grid data of the reference data segment, and Respectively represent The target data point The change in the power grid data value between the sub-data point and the adjacent sub-data points on the left and right, Indicates The target data point The information entropy value of the reference data segment; Calculate the weight of each sub-data point: ; In the formula, Indicates The target data point The weight of each sub-data point, Indicates The target data point and The sampling time interval between sub-data points is Indicates The target data point The grid data value corresponding to each sub-data point is: Indicates The target data point The predicted value of the power grid data corresponding to each sub-data point, Indicates The target data point The abnormality of each sub-data point, Indicates The natural exponential function with base ; Performing weighted calculation according to the sub-data points and their weights to obtain an interpolation result of the target data point, inserting the obtained interpolation result into the first power grid data to replace the target data point, and obtaining complete first power grid data; A rectangular window is constructed to visualize the complete first grid data.

2. The method for visualizing power grid data based on big data processing according to claim 1, characterized in that: The step of performing weighted calculation according to the sub-data points and their weights to obtain the interpolation result of the target data point includes: Determine the one-sided interpolation value of the target data point: ; Indicates One-sided interpolation of target data points, Indicates The number of sub-data points on one side of the target data point, Indicates The target data point The weight of the sub-data points on one side, wherein the one-side interpolation includes left-side interpolation or right-side interpolation; The interpolation result of the target data point is obtained according to the average value of the left interpolation value and the right interpolation value of the target data point.

3. The method for visualizing power grid data based on big data processing according to claim 1, characterized in that: Before inserting the obtained interpolation result into the first power grid data to replace the target data point, the method further includes: A weighted calculation is performed on each sub-data point of the first power grid data and its weight to obtain a preliminary interpolation of the target data point and preset a weight; an interpolation result of a data point corresponding to the target data point is obtained in the complete second power grid data, and the complete second power grid data has a positive correlation with the first power grid data; the first power grid data is screened according to the interpolation result, and a weight is preset for the mean of each data point obtained by the screening; an interpolation result of the target data point is obtained according to the preset weight of the mean of each data point and the preliminary interpolation preset weight, and the interpolation result is inserted into the first power grid data.

4. The method for visualizing power grid data based on big data processing according to claim 3 is characterized in that: in, The weighted calculation formula is: ; In the formula, Indicates The interpolation result of the target data point, represents the preliminary interpolation of the first power grid data, Indicates the interpolation result screening of the complete second power grid data The mean of the first grid data, represents the preliminary interpolation preset weight of the first power grid data, express The mean value of the first power grid data is preset with a weight.

5. The method for visualizing power grid data based on big data processing according to claim 3 is characterized in that: The screening of the first power grid data according to the interpolation result includes: Acquire the actual value of the data point corresponding to the target data point in the complete second power grid data, and determine the difference between the interpolation result and the actual value; Obtain the difference between the interpolation result and the actual value of each data point in the first power grid data; in the difference of the first power grid data, select a number of sub-data points that are equal to the difference with the complete second power grid data, and calculate the mean value of the power grid data corresponding to the sub-data points.

6. The method for visualizing power grid data based on big data processing according to claim 1, characterized in that: The step of constructing a rectangular window to realize visualization of the complete first power grid data includes: Establishing a rectangular window in the complete first power grid data with each data point as the center, and determining an average value of the power grid data in the rectangular window based on the power grid data value in the rectangular window; The average value of the power grid data in the rectangular window is used as the target power grid data value of the data point belonging to the rectangular window, and the visible first power grid data is obtained based on the target power grid data values ​​of all data points.

7. A power grid data visualization system based on big data processing, characterized in that: include: A processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, a power grid data visualization method based on big data processing according to any one of claims 1 to 6 is implemented.