Power line loss analysis system and method based on big data

Abstract

The invention discloses a power line loss analysis system and method based on big data, and relates to the technical field of power line loss analysis, and the method comprises the steps: collecting the operation state and environment parameters of power grid equipment in real time, and constructing a power line loss data set; calculating a rank correlation coefficient of each power line loss data and a line loss rate, outputting a line loss strong correlation factor for empowerment, performing first line loss constraint analysis on real-time data of the line loss strong correlation factor of each line, judging whether constraint is satisfied, and sending a second line loss constraint analysis command to the outside; and performing exponential smoothing residual analysis on the line loss strong correlation factors of each line to obtain a second constraint analysis result, synthesizing the first constraint analysis result and the second constraint analysis result to obtain a third constraint analysis result, and performing real-time rendering on line loss rate distribution according to the third constraint analysis result. The residual error is further analyzed, the superposition influence of non-linear factors such as line aging and load abrupt change on the line loss is captured, and the decision robustness is improved in combination with multi-stage constraint analysis.

Description

Technical Field

[0001] The present invention relates to the technical field of power line loss analysis, and specifically to a power line loss analysis system and method based on big data. Background Art

[0002] In the power system, line loss analysis is an important link to ensure the economic operation of the power grid. However, traditional line loss analysis methods have the following limitations: insufficient data acquisition and processing. The manual meter reading method can only provide overall line loss data, which cannot be accurate to specific nodes or regions, and has poor real-time performance. For example, through manual meter reading, the overall line loss rate of a certain regional power grid is found to be high, but it is impossible to quickly locate the specific high-loss line segments. The monitoring equipment method has high costs, a long deployment cycle, and limited coverage, making it difficult to achieve real-time monitoring of the entire network. Traditional methods mostly rely on steady-state models or simplified formulas (such as the root mean square current method), ignoring the impact of dynamic factors (such as load fluctuations, equipment aging, and reactive power compensation status) on line losses. For example, in the scenario of distributed photovoltaic access, traditional models are difficult to accurately calculate the line loss changes caused by two-way power flow. Moreover, the data in the power generation, transmission, and distribution links are isolated, lacking a unified data sharing platform. For example, due to the lack of data sharing between the transformer maintenance team and the line operation and maintenance team, the fault handling is delayed, affecting the efficiency of line loss management. With the development of smart grids and informatization construction, the power industry has accumulated a large amount of data, promoting line loss analysis into the big data era.

[0003] In the Chinese invention application with the application publication number CN119780536A, a power line loss analysis system and method for a power transmission and transformation project are disclosed, including Step 1: obtaining acquisition data in real time, calculating the real-time power line loss value based on the acquisition data, and processing and analyzing the real-time power line loss value to determine whether the real-time power line loss value is abnormal; Step 2: collecting the line temperature in real time, deriving the relationship formula between the line temperature and the real-time power line loss value based on the line temperature and the historical data of the real-time power line loss value, and drawing a temperature influence curve based on the relationship formula, so as to obtain corresponding measure plans; it can more accurately reflect the power line loss situation, improve the accuracy and efficiency of power line loss analysis; contribute to reducing power line losses, reducing energy waste and environmental pollution, promoting energy conservation, emission reduction and sustainable development, improving the power factor of the power system, and making the power system operate more efficiently and stably.

[0004] In the Chinese invention application with the publication number CN119807965A, a method for intelligent analysis of abnormal substation line losses is disclosed, including the collection of basic data; the construction and training of an artificial intelligence line loss analysis model; abnormal detection and early warning; and the adjustment and optimization of the power supply strategy by managers according to the pushed line loss analysis and detection results. The present invention conducts in-depth analysis of substation line losses based on artificial intelligence technology, uses artificial intelligence technology to establish a line loss analysis model, quickly analyzes and locates line loss problems, thereby improving the efficiency of line loss analysis, reducing manual intervention and operation costs, providing more accurate management and decision-making support for power supply management, being able to reduce the labor cost in power supply line loss management, and improving work efficiency.

[0005] In the above invention application, Invention CN119780536A only considers the influence of temperature on line losses, but does not consider other influencing factors. Although Invention CN119807965A takes other influencing factors into account, it relies on a steady-state model or a simplified formula, ignores the influence of dynamic factors on line losses, is difficult to accurately calculate the line loss changes caused by bidirectional power flow, resulting in the line loss calculation results deviating from the actual situation, being unable to capture the real-time changes of complex power grids, and having low calculation accuracy.

[0006] Therefore, the present invention provides a power line loss analysis system and method based on big data. Summary of the Invention

[0007] (I) Technical Problems to be Solved Aiming at the deficiencies of the prior art, the present invention provides a power line loss analysis system and method based on big data. The present invention obtains a power line loss data set, calculates the Spearman rank correlation coefficient between each power line loss data and the line loss rate, outputs the strongly line loss-related factors for weighting, conducts a first line loss constraint analysis on the real-time data of the strongly line loss-related factors of each line to determine whether the constraints are met. If the first line loss constraints are not met, a second line loss constraint analysis command is sent out, and an exponential smoothing residual method analysis is conducted on the strongly line loss-related factors of each line to obtain a second constraint analysis result. If the second constraint analysis result is greater than 0.1, then the first constraint analysis result and the second constraint analysis result are combined to obtain a third constraint analysis result, and the line loss rate distribution is rendered in real time based on the third constraint analysis result. Further analyze the residuals to capture the superimposed influence of non-linear factors such as line aging and load mutation on line losses. The first constraint and the second constraint complement each other, the former ensures the basic accuracy, and the latter corrects the instantaneous fluctuations. Combining multi-stage constraint analysis improves the decision-making robustness, thus solving the technical problems recorded in the background art.

[0008] (II) Technical Solutions To achieve the above objectives, the present invention is realized through the following technical solutions: 1. A power line loss analysis method based on big data, characterized in that it includes the following steps: Collect the operation status of power grid equipment and environmental parameters in real time, gather equipment ledgers, line parameters, geospatial data, and user profiles, and use a time series filtering algorithm to eliminate outliers to construct a power line loss dataset; Obtain the power line loss dataset, calculate the Spearman rank correlation coefficient between each power line loss data and the line loss rate, output the strongly correlated factors of line loss for weighting, perform the first line loss constraint analysis on the real-time data of the strongly correlated factors of line loss for each line, judge whether the constraint is satisfied. If the first line loss constraint is not satisfied, send a second line loss constraint analysis command outward; After receiving the second line loss constraint analysis command, perform exponential smoothing residual method analysis on the strongly correlated factors of line loss for each line to obtain the second constraint analysis result. If the second constraint analysis result is greater than 0.1, then combine the first constraint analysis result and the second constraint analysis result to obtain the third constraint analysis result, and perform real-time rendering of the line loss rate distribution based on the third constraint analysis result.

[0009] Furthermore, obtain the power line loss dataset and calculate the Spearman rank correlation coefficient between each power line loss data and the line loss rate: ; where i represents the time sequence number of the sample data, i= 1, 2, 3, 4, …, n, n is a positive integer, n represents the total number of samples; and represent the sample data of different power line loss data and line loss rates, and represent the corresponding sample data means.

[0010] Furthermore, output the power line loss data with a Spearman rank correlation coefficient greater than 0.5 as the strongly correlated factors of line loss for weighting. Specifically: ; where represents the Spearman rank correlation coefficient of the strongly correlated factors of line loss.

[0011] Furthermore, the first constraint analysis is specifically to judge whether the real-time data of the strongly correlated factors of line loss for each line is within the corresponding threshold. If it is within the threshold, it is recorded as 0. If it is not within the threshold, it is recorded as the corresponding weight. After summing all the judgment results, it is recorded as the first constraint analysis result. If the first constraint analysis result is greater than 0.1, it is considered that this line does not satisfy the first line loss constraint, and a second line loss constraint analysis command is sent outward.

[0012] Further, if the first constraint analysis result is not greater than 0.1, it is considered that the line meets the first line loss constraint, and then the first constraint analysis result is output to perform real-time rendering of the line loss rate distribution. Lines with a result greater than 0.1 and less than 0.5 are marked with orange rendering, and lines with a result greater than 0.5 are marked with red rendering.

[0013] Further, after receiving the second line loss constraint analysis command, perform exponential smoothing residual method analysis on the strongly line loss-related factors of each line: ; ; ; Further, multiply the exponential smoothing residual results of the strongly line loss-related factors of each line by the corresponding weights and sum them, which is recorded as the second constraint analysis result.

[0014] Further, if the second constraint analysis result is not greater than 0.1, output the first constraint analysis result to perform real-time rendering of the line loss rate distribution. Lines with a result greater than 0.1 and less than 0.5 are marked with orange rendering, and lines with a result greater than 0.5 are marked with red rendering.

[0015] Further, if the second constraint analysis result is greater than 0.1, combine the first constraint analysis result and the second constraint analysis result to obtain the third constraint analysis result, and perform real-time rendering of the line loss rate distribution with the third constraint analysis result. Lines with a result greater than 0.1 and less than 0.5 are marked with orange rendering, and lines with a result greater than 0.5 are marked with red rendering.

[0016] Further, the third constraint analysis result is exp (the second constraint analysis result) * the first constraint analysis result.

[0017] A power line loss analysis system based on big data includes: A line loss data collection module that collects the operating status and environmental parameters of grid equipment in real time, aggregates equipment ledgers, line parameters, geospatial data, and user profiles, and uses a time series filtering algorithm to eliminate outliers to construct a power line loss data set; A first line loss analysis module that obtains the power line loss data set, calculates the Spearman rank correlation coefficient between each power line loss data and the line loss rate, outputs the strongly line loss-related factors for weighting, performs first line loss constraint analysis on the real-time data of the strongly line loss-related factors of each line, determines whether the constraint is met, and if the first line loss constraint is not met, sends a second line loss constraint analysis command externally; The second line loss analysis module, after receiving the second line loss constraint analysis command, performs exponential smoothing residual method analysis on the strongly related factors of line loss for each line to obtain the second constraint analysis result. If the second constraint analysis result is greater than 0.1, then the first constraint analysis result and the second constraint analysis result are combined to obtain the third constraint analysis result, and the line loss rate distribution is rendered in real time based on the third constraint analysis result.

[0018] (III) Beneficial effects The present invention provides a power line loss analysis system and method based on big data, having the following beneficial effects: 1. Real-time collect the operating status and environmental parameters of grid equipment, gather equipment ledgers, line parameters, geospatial data, and user profiles, and use time series filtering algorithms to eliminate outliers, construct a power line loss data set, provide real-time data support for grid dispatching, equipment maintenance, etc., and help decision-makers make more reasonable decisions.

[0019] 2. Obtain the power line loss data set, calculate the Spearman rank correlation coefficient between each power line loss data and the line loss rate, output the strongly related factors of line loss for weighting, perform the first line loss constraint analysis on the real-time data of the strongly related factors of line loss for each line, judge whether the constraint is satisfied. If the first line loss constraint is not satisfied, send out the second line loss constraint analysis command, provide basic data support for subsequent line loss analysis, ensure the accuracy and reliability of the analysis, improve work efficiency, reduce manual workload, and shorten the time to solve problems through the application of big data technology.

[0020] 3. After receiving the second line loss constraint analysis command, perform exponential smoothing residual method analysis on the strongly related factors of line loss for each line to obtain the second constraint analysis result. If the second constraint analysis result is greater than 0.1, then the first constraint analysis result and the second constraint analysis result are combined to obtain the third constraint analysis result, and the line loss rate distribution is rendered in real time based on the third constraint analysis result, further analyze the residuals, capture the superimposed effects of non-linear factors such as line aging and load mutation on line loss, the first constraint and the second constraint complement each other, the former guarantees the basic accuracy, the latter corrects the instantaneous fluctuations, and the decision-making robustness is improved by combining multi-stage constraint analysis. Brief description of the drawings

[0021] Figure 1 It is a schematic flow chart of a power line loss analysis method based on big data according to the present invention; Figure 2 It is a schematic structural diagram of a power line loss analysis system based on big data according to the present invention. Detailed implementation manners

[0022] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0023] Please refer to Figure 1 , the present invention provides a method for analyzing power line loss based on big data, including the following steps: Step 1: Real-time collect the operation status and environmental parameters of grid equipment, gather equipment ledgers, line parameters, geospatial data, and user profiles, and use a time series filtering algorithm to eliminate outliers, and construct a power line loss data set.

[0024] The first step includes the following contents: Step 101: Real-time collect the operation status and environmental parameters of grid equipment. The operation status includes current, voltage, power, three-phase unbalance degree, load rate, voltage deviation, harmonic content (THD), and line temperature, etc., and the environmental parameters include temperature, humidity, etc.

[0025] Step 102: Gather equipment ledgers, line parameters, and user profiles. The equipment ledger is the energy efficiency level and the accuracy of the metering equipment, the line parameter is the length, and the user profile is the historical total load, historical maximum load, and historical average load.

[0026] Step 103: For 10kV distribution lines and high-loss areas, specifically collect key indicators such as power supply quantity, public transformer / special transformer power, power factor, and power supply radius.

[0027] Step 104: Use a time series filtering algorithm to eliminate outliers caused by electricity theft and metering failures, and construct a power line loss data set.

[0028] When in use, combine the contents in steps 101 to 104: Real-time collect the operation status and environmental parameters of grid equipment, gather equipment ledgers, line parameters, geospatial data, and user profiles, and use a time series filtering algorithm to eliminate outliers, and construct a power line loss data set, providing real-time data support for grid dispatching, equipment maintenance, etc., and helping decision-makers make more reasonable decisions.

[0029] Step 2: Obtain the power line loss data set, calculate the Spearman rank correlation coefficient between each power line loss data and the line loss rate, output the strongly correlated factors of the line loss for weighting, perform the first line loss constraint analysis on the real-time data of the strongly correlated factors of the line loss of each line, determine whether the constraint is satisfied, and if the first line loss constraint is not satisfied, send a second line loss constraint analysis command outward.

[0030] The second step includes the following content: Step 201: Obtain the power line loss data set and calculate the Spearman rank correlation coefficient between each power line loss data and the line loss rate: ; where i represents the chronological order number of the sample data, i= 1, 2, 3, 4,... n, n is a positive integer, n represents the total number of samples; and represent the sample data of different power line loss data and line loss rates, and represent the corresponding sample data means.

[0031] Step 202: Output the power line loss data with a Spearman rank correlation coefficient greater than 0.5 as the strongly correlated factors of line loss and perform weight assignment. Specifically: ; where represents the Spearman rank correlation coefficient of the strongly correlated factors of line loss.

[0032] Step 203: Perform the first line loss constraint analysis on the real-time data of the strongly correlated factors of line loss for each line, determine whether it meets the constraint. If it does not meet the first line loss constraint, send a second line loss constraint analysis command outward.

[0033] The first constraint analysis is specifically to determine whether the real-time data of the strongly correlated factors of line loss for each line is within the corresponding threshold. If it is within the threshold, it is recorded as 0. If it is not within the threshold, it is recorded as the corresponding weight assignment. After summing all the judgment results, it is recorded as the first constraint analysis result. If the first constraint analysis result is greater than 0.1, it is considered that the line does not meet the first line loss constraint and a second line loss constraint analysis command is sent outward.

[0034] If the first constraint analysis result is not greater than 0.1, it is considered that the line meets the first line loss constraint. Then output the first constraint analysis result and perform real-time rendering of the line loss rate distribution. The lines with a value greater than 0.1 and less than 0.5 are marked with orange rendering, and the lines with a value greater than 0.5 are marked with red rendering.

[0035] When in use, combine the content in steps 201 to 203: Obtain the power line loss dataset, calculate the Spearman rank correlation coefficient between each power line loss data and the line loss rate, output the strongly correlated factors of line loss for weighting, perform the first line loss constraint analysis on the real-time data of the strongly correlated factors of line loss for each line, determine whether the constraint is satisfied. If the first line loss constraint is not satisfied, send out the second line loss constraint analysis command to provide basic data support for subsequent line loss analysis, ensure the accuracy and reliability of the analysis, and improve work efficiency, reduce manual workload, and shorten the time to solve problems through the application of big data technology.

[0036] Step 3: After receiving the second line loss constraint analysis command, perform exponential smoothing residual method analysis on the strongly correlated factors of line loss for each line to obtain the second constraint analysis result. If the second constraint analysis result is greater than 0.1, then combine the first constraint analysis result and the second constraint analysis result to obtain the third constraint analysis result, and perform real-time rendering of the line loss rate distribution based on the third constraint analysis result.

[0037] The said Step 3 includes the following contents: Step 301: After receiving the second line loss constraint analysis command, perform exponential smoothing residual method analysis on the strongly correlated factors of line loss for each line: ; ; ; Multiply the exponential smoothing residual result of the strongly correlated factors of line loss for each line by the corresponding weight and sum them, which is recorded as the second constraint analysis result.

[0038] Step 302: If the second constraint analysis result is not greater than 0.1, then output the first constraint analysis result and perform real-time rendering of the line loss rate distribution. Lines with a value greater than 0.1 and less than 0.5 are marked with orange rendering, and lines with a value greater than 0.5 are marked with red rendering.

[0039] Step 303: If the second constraint analysis result is greater than 0.1, then combine the first constraint analysis result and the second constraint analysis result to obtain the third constraint analysis result, and perform real-time rendering of the line loss rate distribution based on the third constraint analysis result. Lines with a value greater than 0.1 and less than 0.5 are marked with orange rendering, and lines with a value greater than 0.5 are marked with red rendering.

[0040] Among them, the third constraint analysis result is exp (second constraint analysis result) * first constraint analysis result.

[0041] When in use, combine the contents in Steps 301 to 303: After receiving the second line loss constraint analysis command, perform exponential smoothing residual method analysis on the strongly correlated factors of line loss for each line to obtain the second constraint analysis result. If the second constraint analysis result is greater than 0.1, then synthesize the first constraint analysis result and the second constraint analysis result to obtain the third constraint analysis result, and use the third constraint analysis result to render the line loss rate distribution in real time, further analyze the residuals, and capture the superimposed effects of non-linear factors such as line aging and load mutation on the line loss. The first constraint and the second constraint are complementary. The former ensures the basic accuracy, and the latter corrects the instantaneous fluctuations, and combines multi-stage constraint analysis to improve the decision-making robustness.

[0042] Please refer to Figure 2 , the present invention provides a power line loss analysis system based on big data, including: A line loss data acquisition module that real-time collects the operating status and environmental parameters of grid equipment, aggregates equipment ledgers, line parameters, geospatial data, and user files, and uses a time series filtering algorithm to eliminate outliers to construct a power line loss data set; A first line loss analysis module that obtains the power line loss data set, calculates the Spearman rank correlation coefficient between each power line loss data and the line loss rate, outputs the strongly correlated factors of line loss for weighting, and performs first line loss constraint analysis on the real-time data of the strongly correlated factors of line loss for each line to determine whether the constraint is satisfied. If the first line loss constraint is not satisfied, send a second line loss constraint analysis command outward.

[0043] A second line loss analysis module that, after receiving the second line loss constraint analysis command, performs exponential smoothing residual method analysis on the strongly correlated factors of line loss for each line to obtain the second constraint analysis result. If the second constraint analysis result is greater than 0.1, then synthesize the first constraint analysis result and the second constraint analysis result to obtain the third constraint analysis result, and use the third constraint analysis result to render the line loss rate distribution in real time.

[0044] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or by a combination of computer software and electronic hardware. Whether these functions are executed in hardware or software depends on the specific application and design constraints of the technical solution.

[0045] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0046] As described above, it is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present application can easily think of changes or substitutions, which should all be covered within the protection scope of the present application.

Claims

1. A method for analyzing power line losses based on big data, characterized in that: The steps include: Collect the operating status and environmental parameters of power grid equipment in real time, aggregate equipment records, line parameters, geospatial data and user profiles, and use time series filtering algorithms to remove outliers and construct a power line loss data set; Obtain the power line loss data set, calculate the Spearman rank correlation coefficient between each power line loss data and the line loss rate, output the line loss strong correlation factors for weighting, perform the first line loss constraint analysis on the real-time data of the line loss strong correlation factors of each line, and determine whether the constraint is met. If the first line loss constraint is not met, send a second line loss constraint analysis command outward; After receiving the second line loss constraint analysis command, the exponential smoothing residual method is used to analyze the line loss strongly correlated factors of each line to obtain the second constraint analysis result. If the second constraint analysis result is greater than 0.1, the first constraint analysis result and the second constraint analysis result are combined to obtain the third constraint analysis result, and the line loss rate distribution is rendered in real time based on the third constraint analysis result.

2. The power line loss analysis method based on big data according to claim 1, characterized in that: The first constraint analysis is specifically to determine whether the real-time data of the line loss strong correlation factors of each line is within the corresponding threshold. If it is within the threshold, it is recorded as 0. If it is not within the threshold, it is recorded as the corresponding weight. The sum of all judgment results is recorded as the first constraint analysis result. If the first constraint analysis result is greater than 0.1, it is considered that the line does not meet the first line loss constraint, and a second line loss constraint analysis command is sent out.

3. The power line loss analysis method based on big data according to claim 1, characterized in that: If the first constraint analysis result is not greater than 0.1, the line is considered to meet the first line loss constraint, and the first constraint analysis result is output, and the line loss rate distribution is rendered in real time. Lines greater than 0.1 and less than 0.5 are marked with orange rendering, and lines greater than 0.5 are marked with red rendering.

4. The power line loss analysis method based on big data according to claim 1, characterized in that: The exponential smoothing residual results of the line loss strong correlation factors of each line are multiplied by the corresponding weights and then summed up, which is recorded as the second constraint analysis result.

5. The power line loss analysis method based on big data according to claim 1, characterized in that: If the second constraint analysis result is not greater than 0.1, the first constraint analysis result is output, and the line loss rate distribution is rendered in real time. Lines with a value greater than 0.1 and less than 0.5 are marked with orange rendering, and lines with a value greater than 0.5 are marked with red rendering.

6. The power line loss analysis method based on big data according to claim 1, characterized in that: If the second constraint analysis result is greater than 0.1, the first constraint analysis result and the second constraint analysis result are combined to obtain the third constraint analysis result, and the line loss rate distribution is rendered in real time based on the third constraint analysis result. Lines with a value greater than 0.1 and less than 0.5 are marked in orange, and lines with a value greater than 0.5 are marked in red.

7. The power line loss analysis method based on big data according to claim 1, characterized in that: The third constraint analysis result is exp the second constraint analysis result * the first constraint analysis result.

8. A power line loss analysis system based on big data, which is used to implement the method described in any one of claims 1 to 7, and is characterized in that: include: The line loss data collection module collects the operating status and environmental parameters of power grid equipment in real time, aggregates equipment records, line parameters, geospatial data and user profiles, and uses a time series filtering algorithm to remove outliers to construct a power line loss data set; The first line loss analysis module obtains the power line loss data set, calculates the Spearman rank correlation coefficient between each power line loss data and the line loss rate, outputs the line loss strong correlation factors for weighting, and performs the first line loss constraint analysis on the real-time data of the line loss strong correlation factors of each line to determine whether the constraint is met. If the first line loss constraint is not met, a second line loss constraint analysis command is sent out; After receiving the second line loss constraint analysis command, the line loss second analysis module performs exponential smoothing residual analysis on the line loss strongly correlated factors of each line to obtain the second constraint analysis result. If the second constraint analysis result is greater than 0.1, the first constraint analysis result and the second constraint analysis result are combined to obtain the third constraint analysis result, and the line loss rate distribution is rendered in real time based on the third constraint analysis result.

Images