Method, device and power distribution network detection system for determining voltage quality of a power distribution network

Abstract

The application provides a voltage quality determination method and device of a power distribution network and a power distribution network detection system. The method comprises: acquiring voltage data of the power distribution network; determining an over-limit time length of the power distribution network within a target time length according to the voltage data, wherein the over-limit time length is the sum of a first time length during which the voltage data exceeds a preset maximum value and a second time length during which the voltage data exceeds a preset minimum value; and determining a first qualification rate of the power distribution network according to the over-limit time length, wherein the over-limit time length and the first qualification rate are in a negative correlation relationship. The scheme solves the problem of inaccurate voltage quality evaluation of the power distribution network in the prior art.

Description

Technical Field

[0001] This application relates to the field of power quality assessment technology for distribution networks, and more specifically, to a method for determining the voltage quality of a distribution network, a device for determining the voltage quality of a distribution network, a computer program product, and a distribution network detection system. Background Technology

[0002] In modern urban power distribution networks, cable lines are widely used due to their highly reliable power supply performance and environmentally friendly characteristics. However, with the continuous increase in cable coverage and the increase in load fluctuations, power distribution networks face the challenge of declining power supply voltage quality.

[0003] Because the capacitance to ground of cable lines is much greater than that of overhead lines, and the charging power is much higher than that of overhead lines, there may be excess capacitive reactive power when the load level is low, which may lead to reactive power backfeed and cause the voltage at the end of the line to rise.

[0004] Currently, the power industry lacks methods for assessing the voltage quality of distribution networks, resulting in inaccurate voltage quality assessments. Summary of the Invention

[0005] The main objective of this application is to provide a method for determining the voltage quality of a distribution network, a device for determining the voltage quality of a distribution network, a computer program product, and a distribution network detection system, so as to at least solve the problem of inaccurate voltage quality assessment of distribution networks in the prior art.

[0006] To achieve the above objectives, according to one aspect of this application, a method for determining the voltage quality of a distribution network is provided, comprising: acquiring voltage data of the distribution network; determining, based on the voltage data, the over-limit duration of the distribution network within a target time period, wherein the over-limit duration is the sum of a first time period during which the voltage data exceeds a preset maximum value and a second time period during which the voltage data exceeds a preset minimum value; and determining a first pass rate of the distribution network based on the over-limit duration, wherein the over-limit duration and the first pass rate are negatively correlated.

[0007] Optionally, obtaining voltage data of the distribution network includes: obtaining an initial dataset, wherein the initial dataset includes at least the voltage amplitude of all monitoring points in the distribution network; obtaining electrical distance, wherein the electrical distance is the distance between the monitoring point and the main transformer; dividing the initial dataset according to the electrical distance to obtain data groups; and performing clustering processing on the data groups using the K-means algorithm to obtain the voltage data.

[0008] Optionally, after determining the over-limit duration of the distribution network within the target duration based on the voltage data, the method further includes: obtaining the total duration; calculating the quotient of the first duration and the total duration to obtain a first proportion, wherein the first proportion is the proportion of the first duration in the total duration; calculating the quotient of the second duration and the total duration to obtain a second proportion, wherein the second proportion is the proportion of the second duration in the total duration.

[0009] Optionally, after determining the first pass rate of the distribution network based on the over-limit duration, the method further includes: generating a scatter plot based on the first pass rate; and generating a target curve based on the first pass rate.

[0010] Optionally, after determining the first qualification rate of the distribution network based on the over-limit duration, the method further includes: obtaining a first sub-qualification rate, wherein the first sub-qualification rate is the qualification rate of the power supply voltage of the distribution network; obtaining a second sub-qualification rate, wherein the second sub-qualification rate is the qualification rate of the voltage at the monitoring point of the switching station of the distribution network; and determining the relationship between the first sub-qualification rate and the second sub-qualification rate based on the Pearson correlation coefficient.

[0011] Optionally, after determining the over-limit duration of the distribution network within the target time period based on the voltage data, the method further includes: acquiring relevant information about the distribution network, wherein the relevant information includes at least one or more of line length, transformer distribution location, load type, and environmental information; constructing a quality detection model, wherein the quality detection model is trained using multiple sets of training data, each set of training data including historical over-limit duration, historical relevant information, the historical over-limit duration, and the historical second pass rate corresponding to the historical relevant information within a historical time period; and inputting the over-limit duration and the relevant information into the quality detection model to obtain the second pass rate corresponding to the over-limit duration and the relevant information.

[0012] Optionally, after determining the first pass rate of the distribution network based on the over-limit duration, the method further includes: obtaining a preset pass rate threshold; and generating an early warning message when the first pass rate is less than or equal to the preset pass rate threshold.

[0013] According to another aspect of this application, a device for determining the voltage quality of a distribution network is provided, comprising: a first acquisition unit for acquiring voltage data of the distribution network; a first determination unit for determining, based on the voltage data, the over-limit duration of the distribution network within a target time period, wherein the over-limit duration is the sum of a first time period during which the voltage data exceeds a preset maximum value and a second time period during which the voltage data exceeds a preset minimum value; and a second determination unit for determining, based on the over-limit duration, a first pass rate of the distribution network, wherein the over-limit duration and the first pass rate are negatively correlated.

[0014] According to another aspect of this application, a computer program product is provided, comprising a computer program that, when executed by a processor, implements the steps of any of the methods for determining the voltage quality of the power distribution network.

[0015] According to another aspect of this application, a distribution network detection system is provided, comprising: one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs including a method for performing a method for determining the voltage quality of any of the aforementioned distribution networks.

[0016] The technical solution of this application takes into account voltage fluctuations, i.e. voltage overruns. By statistically analyzing the duration of voltage overruns, the voltage quality, i.e. the first pass rate, is determined. This can more objectively reflect the voltage quality status of the distribution network within a specific period, resulting in better accuracy of the assessment. Attached Figure Description

[0017] The accompanying drawings, which form part of this application, are used to provide a further understanding of this application. The illustrative embodiments and descriptions of this application are used to explain this application and do not constitute an undue limitation of this application. In the drawings:

[0018] Figure 1 A hardware block diagram of a mobile terminal for performing a method for determining the voltage quality of a distribution network, according to an embodiment of this application, is shown.

[0019] Figure 2 A flowchart illustrating a method for determining the voltage quality of a distribution network according to an embodiment of this application is shown.

[0020] Figure 3 A flowchart illustrating the process of constructing the scoring criteria for voltage compliance rate is shown.

[0021] Figure 4 A scatter plot of the monthly voltage compliance rate is shown;

[0022] Figure 5 A schematic diagram of the target curve for the monthly voltage compliance rate score is shown;

[0023] Figure 6 A structural block diagram of a voltage quality determination device for a power distribution network according to an embodiment of this application is shown.

[0024] The above figures include the following reference numerals:

[0025] 102. Processor; 104. Memory; 106. Transmission device; 108. Input / output device. Detailed Implementation

[0026] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. This application will now be described in detail with reference to the accompanying drawings and embodiments.

[0027] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0028] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate for the embodiments of this application described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0029] Commonly used methods for calculating voltage compliance rates are typically "two-way," failing to differentiate between voltage exceeding the upper and lower limits when assessing distribution network voltage deviations and compliance rates. This makes it difficult to fully reflect the voltage exceedance characteristics along the lines of distribution networks with high cable penetration rates. Furthermore, since voltage fluctuations in distribution networks are relatively small during normal operation, using evaluation methods that divide indicators into several levels may lead to misjudgments of voltage quality at certain monitoring points, affecting the accuracy of voltage mitigation measures.

[0030] As described in the background section, the voltage quality assessment of distribution networks in the prior art is inaccurate. To solve the above problems, embodiments of this application provide a method for determining the voltage quality of a distribution network, a device for determining the voltage quality of a distribution network, a computer program product, and a distribution network detection system.

[0031] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention.

[0032] The methods and embodiments provided in this application can be executed on a mobile terminal, computer terminal, or similar computing device. Taking running on a mobile terminal as an example, Figure 1 This is a hardware structure block diagram of a mobile terminal for a method of determining the voltage quality of a power distribution network according to an embodiment of the present invention. Figure 1 As shown, a mobile terminal may include one or more ( Figure 1 Only one is shown in the diagram. A processor 102 (which may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.) and a memory 104 for storing data are also shown. The mobile terminal may further include a transmission device 106 for communication functions and an input / output device 108. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the mobile terminal described above. For example, the mobile terminal may also include components that are more... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.

[0033] The memory 104 can be used to store computer programs, such as application software programs and modules, like the computer program corresponding to the device information display method in this embodiment of the invention. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, thereby implementing the above-described method. The memory 104 may include high-speed random access memory and non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to the mobile terminal via a network. Examples of the aforementioned networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof. The transmission device 106 is used to receive or send data via a network. Specific examples of the aforementioned networks may include wireless networks provided by the mobile terminal's communication provider. In one example, the transmission device 106 includes a network interface controller (NIC), which can be connected to other network devices via a base station to communicate with the Internet. In one example, the transmission device 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0034] This embodiment provides a method for determining the voltage quality of a power distribution network that operates on a mobile terminal, computer terminal, or similar computing device. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0035] Figure 2 This is a flowchart illustrating a method for determining the voltage quality of a power distribution network according to an embodiment of this application. Figure 2 As shown, the method includes the following steps:

[0036] Step S201: Obtain voltage data of the distribution network;

[0037] Specifically, voltage measurement devices in the distribution network switchgear and the DSCADA (Distribution Supervisory Control and Data Acquisition) system can be used to collect voltage data. These devices can monitor the voltage level in the distribution network in real time, including but not limited to steady-state power frequency voltage and instantaneous voltage fluctuations. The data sampling period is set to once every 15 minutes to ensure that details of voltage fluctuations can be captured while keeping the amount of data within a processable range.

[0038] Step S202: Based on the voltage data, determine the over-limit duration of the distribution network within the target duration, wherein the over-limit duration is the sum of the first duration during which the voltage data exceeds the preset maximum value and the second duration during which the voltage data exceeds the preset minimum value;

[0039] Specifically, based on the collected voltage data, the voltage over-limit duration of a high-cable-rate distribution network within a specific target time period is determined. This duration is the cumulative time during which the voltage data exceeds the preset maximum and minimum threshold values.

[0040] According to the State Grid's voltage quality standards, preset maximum and minimum voltage values ​​are set. For 220V low-voltage distribution networks, the acceptable voltage range is typically set at 220V ± 7%, that is, the acceptable voltage range is 205.4V to 234.6V. Any voltage value exceeding this range will be considered an over-limit.

[0041] Voltage data acquired from the distribution network switchgear and DSCADA system undergoes preprocessing, including data cleaning (removing invalid or abnormal data) and time synchronization, to ensure data accuracy and consistency. Then, voltage sampling data is checked every 15 minutes, marking the time points when the voltage exceeds a preset maximum value or falls below a preset minimum value.

[0042] Based on the time stamp results, the system calculates the first duration (first over-limit duration) for voltage data exceeding the preset maximum value and the second duration (second over-limit duration) for voltage data falling below the preset minimum value for each monitoring point within a month. For example, if a monitoring point has voltage values ​​exceeding the maximum value for 10 hours and falling below the minimum value for 5 hours within a month, then the over-limit duration for that monitoring point is 15 hours.

[0043] The duration of exceeding the limit at all monitoring points is summarized to obtain the total duration of exceeding the limit for the entire target area within the target time.

[0044] Step S203: Determine the first qualification rate of the above-mentioned distribution network based on the above-mentioned over-limit duration, wherein the above-mentioned over-limit duration and the above-mentioned first qualification rate are negatively correlated.

[0045] Specifically, the voltage compliance rate (first compliance rate) is an important indicator for measuring power quality, reflecting the proportion of time the voltage value remains within the specified range. Over-limit duration refers to the total time the voltage exceeds the preset maximum or minimum value within the assessment period. This relationship is particularly significant in distribution networks with high cable penetration rates, because the characteristics of cable lines (such as high ground capacitance) can cause voltage to exceed limits under certain conditions, thus affecting the voltage compliance rate. The longer the over-limit time, the lower the first compliance rate; the shorter the over-limit time, the higher the first compliance rate.

[0046] This embodiment takes into account voltage fluctuations, i.e. voltage overruns. By statistically analyzing the duration of voltage overruns, the voltage quality, i.e., the first pass rate, is determined. This can more objectively reflect the voltage quality status of the distribution network within a specific period, resulting in better accuracy of the assessment.

[0047] Specifically, this scheme considers the voltage exceeding characteristics of distribution lines with high cable penetration rates, constructs a scientific calculation method for the voltage qualification rate of distribution networks with high cable penetration rates, and compares the differences in voltage qualification rates between medium-voltage distribution networks and low-voltage distribution areas to clarify the characteristics of voltage exceeding limits in distribution networks with high cable penetration rates. By implementing the voltage qualification rate evaluation method for distribution networks with high cable penetration rates provided in this scheme, a two-way assessment of the voltage qualification rate based on both grid and load can be conducted for distribution areas with high cable penetration rates, providing a basis for voltage quality management.

[0048] In the specific implementation process, obtaining voltage data of the distribution network can be achieved through the following steps: obtaining an initial dataset, wherein the initial dataset includes at least the voltage amplitude of all monitoring points in the distribution network; obtaining the electrical distance, wherein the electrical distance is the distance between the monitoring point and the main transformer; dividing the initial dataset according to the electrical distance to obtain data groups; and using the K-means algorithm to cluster the data groups to obtain the voltage data.

[0049] In this scheme, voltage data of distribution networks with high cable coverage are effectively clustered based on electrical distance and K-means algorithm to identify the voltage characteristics of monitoring points in different regions or types. This provides strong support for more accurate assessment of voltage qualification rate and formulation of corresponding voltage optimization strategies.

[0050] Specifically, voltage measurements from distribution network switchgear and node voltage data collected by the DSCADA system were selected and filtered. Multi-regional, high-density steady-state power frequency voltage electrical quantities that can be collected by a multi-source power quality monitoring system were selected as dynamic data for data analysis and voltage quality evaluation. The sampling period was once every 15 minutes to accurately reflect the voltage qualification rate along high-cable-rate distribution lines. The transformer type at each monitoring point and the cable length between each station were selected to analyze the relationship between the voltage qualification rate of high-cable-rate medium-voltage distribution networks and low-voltage distribution areas.

[0051] As a further description of the above technical solution, the specific steps for data filtering are as follows:

[0052] (1) Construct datasets for each monitoring point based on the system network structure and operational data:

[0053]

[0054] Among them, T iThe transformer's type, name, and capacity; V i,t H represents the voltage amplitude at the monitored point. i User load type; L i,j The length of the cable line between two adjacent monitoring points;

[0055] (2) Calculate the electrical distance between each monitoring point and the main transformer, as shown in the following formula:

[0056]

[0057] L n This represents the electrical distance, and n represents the number of main transformers.

[0058] (3) Based on the correlation between the capacitive rise effect of cable lines and line length, the length interval [nΔL, (n+1)ΔL] is set; the voltage acquisition data is divided into several groups according to the electrical distance of each monitoring point from the main transformer;

[0059] (4) Based on the statistical monitoring point substation type or user load type, K-means clustering algorithm is used to obtain typical monitoring data, reduce the amount of data and ensure load characteristics.

[0060] Specifically, for each monitoring point, the electrical distance between it and the main transformer is calculated. This electrical distance reflects not only the physical distance but also factors such as line impedance and cable characteristics, providing a more accurate representation of the impact range of voltage variations. This distance is calculated using formulas from electrical engineering, typically including parameters such as cable length, impedance, and line losses. For example, if a monitoring point is connected to the main transformer via a 2km cable, the cable's impedance characteristics must also be considered when calculating the final electrical distance.

[0061] Specifically, the initial dataset is divided into several data groups. These groups are based on the similarity of electrical distance, rather than physical proximity. For example, all monitoring points with an electrical distance of 1-3 km from the main transformer are grouped together, those with a distance of 3-5 km are grouped together, and so on. This division aims to better identify the characteristics of the impact of cabling rate on voltage in subsequent cluster analysis.

[0062] Specifically, the data within each data group is clustered using the K-means algorithm. The K-means algorithm is a commonly used unsupervised learning method that automatically divides data into K clusters based on the similarity between data points. In this embodiment, the selection of K should consider factors such as the distribution of monitoring points, load characteristics, and the length distribution of cable lines to ensure the effectiveness and representativeness of the clustering.

[0063] Specifically, for example, K is set to 3, and then voltage data from a set of monitoring points (electrically distant from each other by 1-3 km) are clustered. The clustering results may show three different voltage variation patterns, each representing the impact of different types of loads or cable line characteristics on voltage.

[0064] Specifically, the results of K-means clustering were analyzed to identify characteristics of voltage data from different monitoring points. For example, it was found that monitoring points in one cluster had higher voltages at night, while monitoring points in another cluster had lower voltages during peak hours. These characteristics are related to the electrical distance and load type of the monitoring points.

[0065] Specifically, voltage data is standardized before K-means clustering to eliminate the influence of dimensions between different monitoring points. The calculation of electrical distance requires consideration of the physical length of the cable, its resistance and reactance, and the topology of the distribution network. The K value (number of clusters) in the K-means algorithm needs to be determined based on the actual electrical network structure, monitoring point distribution, and data characteristics, and can be optimized using methods such as the Elbow Method or the Silhouette Score.

[0066] In the specific implementation process, after determining the over-limit duration of the distribution network within the target duration based on the voltage data, the method further includes the following steps: obtaining the total duration; calculating the quotient of the first duration and the total duration to obtain a first proportion, wherein the first proportion is the percentage of the first duration in the total duration; calculating the quotient of the second duration and the total duration to obtain a second proportion, wherein the second proportion is the percentage of the second duration in the total duration.

[0067] In this scheme, the percentage of time the voltage exceeds the limit can be calculated, the percentage of time the voltage exceeds the upper limit and the percentage of time the voltage exceeds the lower limit, namely the first percentage and the second percentage. The voltage quality can then be further determined using these percentages.

[0068] Specifically, the duration of voltage anomalies at each monitoring point was statistically analyzed, and the index values ​​for each monitoring point were derived based on the voltage compliance rate evaluation method to clarify the voltage over-limit characteristics of distribution networks with high cable penetration rates. Based on the characteristics of distribution network monitoring data, the evaluation duration for voltage compliance rate was selected, and a voltage compliance rate scoring standard for distribution networks with high cable penetration rates was constructed.

[0069] As a further description of the above technical solution, the analysis method for the voltage qualification rate is as follows: calculate the proportion of the duration of voltage exceeding the upper limit at each monitoring point in the total evaluation period and the total duration of voltage exceeding the upper limit; calculate the voltage qualification rate of each distribution transformer by weighting, and measure the overall voltage qualification rate of the local low-voltage distribution area.

[0070] The percentage of time spent exceeding the voltage limit in the total evaluation time is shown below:

[0071]

[0072] In the formula, t max t is the duration for which the voltage exceeds the upper limit. Z Total assessment time.

[0073] The percentage of time spent exceeding the voltage limit in the total evaluation time is shown below:

[0074]

[0075] In the formula, t min The duration of voltage exceeding the upper limit.

[0076] By utilizing the proportion of voltage over-limit duration in the total over-limit duration, the characteristics of voltage over-limit in highly cabled power distribution lines can be clearly identified:

[0077]

[0078] Specifically, the steps to measure the overall power supply voltage qualification rate of cable feeders are as follows:

[0079] If the collected data includes the actual load values ​​supplied by each substation, the voltage qualification rate of the entire line can be calculated by weighting the proportions of each distribution load and the total load of the line; otherwise, based on the type and number of transformers in each cable line, and the load importance set according to the transformer type, the benchmark limit for voltage qualification rate of various power supply areas is determined, and the overall power supply voltage qualification rate of the line is obtained by weighted calculation.

[0080] Specifically, the formula is as follows:

[0081]

[0082] Where N is the total number of distribution transformers; N i The number of dedicated transformers, public transformers, and main transformers; The voltage qualification rate for each type of distribution transformer; ω i The method for determining the load weights based on the importance of power supply from various types of distribution transformers is as follows: First, an online evaluation system for the importance of substation power supply loads is constructed. For different types of substations in a given cable power supply line or area, the five-scale method is used to compare the importance between any two, thereby obtaining a judgment matrix.

[0083] A k =(a ij ) n×n k = 1, 2, ..., m

[0084] Where m represents the number of users participating in the evaluation. Next, a consistency check is performed. The consistency index is calculated as follows:

[0085]

[0086] Where, λ max To determine the largest eigenvalue of the matrix; and then to calculate the consistency ratio:

[0087]

[0088] Here, RI is the consistency index; in the consistency test, if the CR value is less than 0.1, it indicates that the consistency of the judgment matrix is ​​acceptable; then, the importance values ​​are normalized column-wise, and the weights are calculated using the arithmetic mean method:

[0089]

[0090] in,

[0091] This represents the weight vector obtained by the arithmetic mean of the column vectors of the judgment matrix; β is the number of weight vectors, and a ij This represents the load weight corresponding to any two types of distribution transformers.

[0092] As a further description of the above scheme, the method for constructing a scoring standard based on voltage monitoring data of distribution networks with high cable coverage is as follows: sort the index values ​​of each monitoring point and list them in the form of a scatter plot; analyze the distribution of the scatter plot of each index value; determine the grade interval based on characteristics such as slope and "inflection point"; set the score value corresponding to the grade boundary of the index calculation value; adopt the percentage evaluation method; set the score value corresponding to the grade boundary of the index value; calculate the scoring formula of each index; and draw the scoring curve of each voltage exceeding the upper limit index.

[0093] Specifically, the general scoring standard for the tiered indicators is as follows:

[0094]

[0095] In the formula, x represents the calculated value of the indicator, y represents the percentage score, and a and b represent the coefficient matrix of the indicator scoring formula.

[0096] Specifically, a specific evaluation period, such as one month, is selected as the statistical time window for calculating the first pass rate and exceeding limits. Within this period, the total amount of time data that can be collected is: 30 days × 24 hours / day × 4 samples / hour = 2880 sample points, which constitutes the total duration mentioned above.

[0097] Specifically, the collected voltage data is preprocessed and analyzed to identify voltage exceedance situations. Assuming the national power quality standard stipulates that the acceptable voltage range for low-voltage distribution networks is 220V ± 7%, meaning a voltage between 205.4V and 234.6V is considered acceptable. The time when the voltage exceeds the preset maximum value is defined as the first duration, and the time when it falls below the preset minimum value is defined as the second duration.

[0098] Specifically, for each monitoring point, the percentage of time the voltage exceeds the limit within the assessment period is calculated. The magnitude of the first percentage and the second percentage are negatively correlated with the voltage quality. The voltage quality can be determined based on the first percentage and the second percentage respectively. Of course, the voltage quality can also be determined by weighted averaging of these two percentages.

[0099] In the specific implementation process, after determining the first qualification rate of the above distribution network based on the above-mentioned over-limit duration, the above method also includes the following steps: generating a scatter plot based on the above-mentioned first qualification rate; generating a target curve based on the above-mentioned first qualification rate.

[0100] This scheme provides a visual way to assess voltage quality in distribution networks with high cable penetration rates by generating scatter plots and target curves. This approach helps power companies and grid operators better understand the distribution characteristics of voltage compliance rates through intuitive graphical displays.

[0101] Specifically, such as Figure 3 As shown, the relationship between the voltage qualification rate of medium-voltage distribution networks and low-voltage distribution areas is calculated using the Pearson correlation coefficient. Based on actual transformer parameters and line topology, the power supply voltage qualification rate for different areas is calculated.

[0102] As a further expression of the above scheme, the relationship between the voltage qualification rate of the medium-voltage distribution network and the low-voltage distribution area is analyzed using the Pearson correlation coefficient. The specific steps are as follows:

[0103] 1. Conduct a correlation analysis between the voltage qualification rate of power supply at distribution substations of the same type and the voltage qualification rate calculated from the voltage collected at adjacent switching stations:

[0104] Calculate the correlation coefficients between the distribution transformer power supply voltage qualification rate and the load type and size supplied by each station, the cable line length between adjacent switching stations and distribution stations, and the voltage qualification rate values ​​of the monitoring points at the switching stations:

[0105]

[0106] Where, r ab The value represents the degree of relevance; μ and σ represent the mean and standard deviation, respectively; and N represents the number of stations for the evaluation target after screening.

[0107] Following the above method, multi-period actual data were selected, and correlation calculations were performed again. A multiple linear regression model was used to determine the regression coefficients of the correlation coefficients among the above variables, reducing the correlation between the voltage qualification rate of low-voltage distribution areas and other influencing factors such as load type and cable length. The independent correlation between the distribution transformer power supply voltage qualification rate and the voltage qualification rate at adjacent switching stations was calculated.

[0108]

[0109] Where R represents the correlation coefficient between the power supply voltage of the low-voltage distribution transformer and the voltage qualification rate of adjacent switching stations; a1 is used to measure the independent correlation between the power supply voltage qualification rate of the distribution transformer and the voltage qualification rate at adjacent switching stations, n represents the number of adjacent switching stations, and T N This represents the number of relevant indicators that affect the voltage qualification rate at the distribution transformer, where b is a constant.

[0110] 2. Calculate the voltage qualification rate of the entire line by weighting the voltage qualification rates of the switching stations along the line, and conduct a correlation analysis with the power supply voltage qualification rate of the entire line.

[0111] In the practical application scheme, monthly low-voltage distribution area voltage data collected by the DSCADA system in the high-cable distribution area of ​​a certain city power supply company were selected. The duration of voltage anomalies at each monitoring point was statistically analyzed. The voltage qualification rate evaluation method for high-cable distribution networks using monitoring devices provided in this scheme was adopted to obtain the monthly voltage qualification rate evaluation results and evaluation standards.

[0112] The scatter plot of monthly voltage qualification rate is as follows: Figure 4 As shown in the figure. Based on the slope variation characteristics, the voltage exceeding the upper limit curve at the monitoring point is divided into 5 segments. Let the scores corresponding to voltage compliance rates of 96%, 80.95%, 65%, and 31.62% be 100, 80, 60, and 30 points respectively. Based on this, the scoring standard for the voltage exceeding the upper limit index can be obtained as follows: The monthly voltage compliance rate evaluation curve is shown in the figure. Figure 5 As shown.

[0113]

[0114] Specifically, a scatter plot is generated by using the electrical distance (or cable length) and the first pass rate for each monitoring point as variables on the X and Y axes. This helps to observe the relationship between electrical distance and voltage pass rate, and whether there are obvious distribution patterns or trends. For example, it can be expected that the voltage pass rate may decrease as the electrical distance increases, especially in areas with high cable penetration rates.

[0115] Specifically, a target curve is generated based on the data points on the scatter plot using curve fitting techniques. The target curve can be a straight line, a polynomial curve, or other forms of function; its specific form should be determined based on the characteristics of the data distribution. This curve will help quantify the relationship between electrical distance and the first pass rate, providing a reference for subsequent analysis and decision-making.

[0116] Specifically, by comparing scatter plots and target curves, the fluctuation patterns of voltage compliance rates and the specific impact of cabling rates on voltage quality can be identified. For example, the slope of the curve can reveal the strength of the influence of electrical distance on voltage compliance rates; the shape of the curve (such as linear, convex, or concave) can reflect the nature of the influence. In addition, outliers or dense areas in the scatter plot may also point to specific voltage problems or potential optimization opportunities.

[0117] Specifically, before generating scatter plots, data cleaning should be performed to remove invalid or extreme values, ensuring the accuracy of the analysis results. An appropriate fitting method (such as linear regression or multinomial regression) should be selected to generate the target curve, taking into account the nonlinear relationships of the data and fitting errors. Professional data visualization software (such as Python's Matplotlib library, Excel, SPSS, etc.) should be used to generate scatter plots and target curves for subsequent analysis and presentation. The slope, inflection points, and other characteristic parameters of the target curve, as well as the patterns in the scatter plots, can be used to interpret the impact mechanism of cable coverage rate on voltage qualification rate, providing strategic guidance for improving voltage quality.

[0118] In some embodiments, after determining the first qualification rate of the distribution network based on the aforementioned over-limit duration, the method further includes the following steps: obtaining a first sub-qualification rate, wherein the first sub-qualification rate is the qualification rate of the power supply voltage of the distribution network; obtaining a second sub-qualification rate, wherein the second sub-qualification rate is the qualification rate of the voltage at the monitoring point of the switching station of the distribution network; and determining the relationship between the first sub-qualification rate and the second sub-qualification rate based on the Pearson correlation coefficient.

[0119] In this scheme, by calculating the Pearson correlation coefficient, the correlation between the power supply voltage qualification rate and the voltage qualification rate of the monitoring point of the switching station can be analyzed, providing data support and decision-making basis for voltage quality management and optimization of distribution networks with high cable coverage.

[0120] Specifically, the power supply voltage data is analyzed, and the duration of voltage exceeding the upper and lower limits is statistically analyzed to calculate the power supply voltage qualification rate, which is the proportion of time the voltage is within the specified range out of the total monitoring time. This will serve as the first sub-qualification rate, reflecting the overall voltage quality of the distribution network.

[0121] Specifically, the voltage data from the monitoring points of each switching station are processed in the same way to calculate their respective voltage compliance rates. These voltage compliance rates from the monitoring points of each switching station will be used as a second sub-compliance rate to evaluate the voltage quality of a specific area or node.

[0122] Specifically, the Pearson correlation coefficient is used to measure the linear relationship between the first sub-qualification rate (power supply voltage qualification rate) and the second sub-qualification rate (voltage qualification rate at the switch station monitoring point). The Pearson correlation coefficient ranges from -1 to 1, with values ​​close to 1 indicating a positive correlation, close to -1 indicating a negative correlation, and close to 0 indicating no linear relationship.

[0123] Specifically, assuming a calculated Pearson correlation coefficient of 0.85, this indicates a significant positive correlation between the power supply voltage qualification rate and the voltage qualification rate at the switching station monitoring points. This means that when the overall power supply voltage of the distribution network is at a qualified level, the voltage quality at the switching station monitoring points also tends to be qualified; conversely, if the power supply voltage qualification rate is low, the voltage quality at the switching station monitoring points may also be affected.

[0124] Specifically, before calculating the pass rate, data cleaning is required to remove outliers and missing data, ensuring the accuracy and reliability of the analysis. In addition to calculating the Pearson correlation coefficient, a scatter plot can be used to visually observe the relationship between the first and second sub-pass rates. The analysis results should be combined with the specific conditions and load characteristics of the distribution network to formulate reasonable voltage quality improvement strategies. For example, areas with low first and second sub-pass rates may require more thorough grid upgrades or optimizations.

[0125] In some embodiments, after determining the over-limit duration of the distribution network within the target time period based on the voltage data, the method further includes the following steps: obtaining relevant information about the distribution network, wherein the relevant information includes at least one or more of line length, transformer distribution location, load type, and environmental information; constructing a quality detection model, wherein the quality detection model is trained using multiple sets of training data, each set of training data including historical over-limit duration, historical relevant information, and the historical second pass rate corresponding to the historical over-limit duration and the historical relevant information within a historical time period; and inputting the over-limit duration and the relevant information into the quality detection model to obtain the second pass rate corresponding to the over-limit duration and the relevant information.

[0126] This solution utilizes machine learning technology to build a quality inspection model that predicts voltage quality trends in distribution networks with high cable penetration rates based on historical data. This approach not only helps power companies anticipate and address voltage issues in advance but also provides data support for optimizing power quality and grid operation strategies, thereby improving grid stability and service quality.

[0127] Specifically, a large amount of historical data is collected from the DSCADA system, including but not limited to: voltage over-limit duration at different time periods (historical over-limit duration), cable length of the lines, transformer distribution locations (e.g., transformer type, name, and capacity), user load types, and environmental information (such as temperature and humidity). This data undergoes necessary cleaning and preprocessing, such as removing outliers, filling in missing values, and standardizing the data, to improve the accuracy of subsequent model training.

[0128] Specifically, the collected historical data is organized into training datasets. Each training dataset includes the duration of voltage exceedance within a historical time period, relevant line information (cable length, transformer location, load type, environmental information, etc.), and the corresponding voltage compliance rate (historical second compliance rate). For example, a training dataset might show that, for a specific cable length and load type, when the voltage exceeds the limit for 10 hours, the historical second compliance rate is 90%.

[0129] Specifically, a machine learning algorithm, such as Support Vector Machine (SVM), Random Forest (RF), or Neural Network (NN), is selected as the basis for the quality inspection model. The model is trained using multiple sets of constructed training data to learn the mapping relationship between the duration of exceeding limits and related information and the voltage pass rate. The goal of the training is to enable the model to predict the corresponding voltage pass rate based on the input duration of exceeding limits and related information.

[0130] Specifically, after model training, the predictive performance of the model is validated using an independent test dataset. Cross-validation can be used to ensure the model's generalization ability. If the error between the model's prediction and the actual voltage pass rate is large, it is necessary to adjust the model parameters or try other algorithms to optimize the model and improve prediction accuracy.

[0131] Specifically, the latest over-limit duration and distribution network information are input into the trained quality inspection model to obtain the predicted voltage compliance rate (second compliance rate). This prediction result can be used to provide early warning of voltage quality problems and guide power system operation and maintenance personnel to take preventive measures, such as adjusting reactive power compensation and optimizing load dispatching, to ensure that voltage quality meets standards.

[0132] Specifically, feature selection is required before model training to ensure that the information input into the model has a direct or indirect correlation with voltage quality. For example, temperature in environmental information may affect the conductivity of cables, thus indirectly affecting voltage quality. An appropriate machine learning model should be selected based on the characteristics of the training data. For example, if there are complex nonlinear relationships between the data, a neural network may be a better choice. The model's predicted pass rate needs to be interpreted in conjunction with actual operating conditions. For example, a decrease in the predicted pass rate may mean that immediate action is needed to prevent potential voltage problems from escalating.

[0133] In some embodiments, after determining the first pass rate of the power distribution network based on the aforementioned over-limit duration, the method further includes the following steps: obtaining a preset pass rate threshold; and generating an early warning message when the first pass rate is less than or equal to the preset pass rate threshold.

[0134] This solution provides an effective voltage quality early warning mechanism by setting a preset pass rate threshold and combining it with real-time monitoring data. It helps power companies promptly identify and address voltage quality issues, preventing power losses and equipment damage caused by voltage fluctuations, thereby improving the overall operational efficiency and service quality of the power grid.

[0135] Specifically, power companies or distribution network operators need to set a reasonable voltage compliance rate threshold based on national power quality standards, grid operation experience, and historical data. For example, assuming the preset compliance rate threshold is 98%, the system will generate an early warning message when the voltage compliance rate is below 98%.

[0136] Specifically, the DSCADA system and voltage monitoring devices in the distribution network are used to collect and analyze voltage data from each monitoring point in real time, and to calculate the voltage over-limit time (first duration), total assessment time (total duration), and voltage compliance rate (first compliance rate). This process is continuous, ensuring that the system can respond to changes in voltage quality in real time.

[0137] Specifically, the first pass rate calculated in real time is compared with a preset pass rate threshold. If the first pass rate is lower than or equal to the preset pass rate threshold (i.e., 98%), the system immediately generates an early warning message. The early warning message should include the following key information: monitoring point information that triggered the early warning, the current voltage pass rate, the specific circumstances of the voltage exceeding the limit (such as the frequency and duration of the exceeding the limit), and suggested preliminary countermeasures.

[0138] Specifically, upon receiving an early warning message, power system operation and maintenance personnel should immediately conduct a detailed inspection and analysis of the affected area. This may include reviewing load patterns, checking the status of reactive power compensation equipment, and analyzing the operating parameters of cable lines. Based on the early warning message and the results of on-site inspections, operation and maintenance personnel can formulate and implement specific voltage quality improvement measures.

[0139] In summary, this scheme constructs a voltage qualification rate evaluation method based on the voltage over-limit characteristics of distribution networks with high cable penetration rates. Based on voltage measurement data of medium-voltage distribution networks and low-voltage distribution areas with high cable penetration rates, this invention constructs a scoring standard construction method, analyzes the correlation between the voltage qualification rates of medium-voltage distribution networks and low-voltage distribution area monitoring points in different ranges of distribution areas with high cable penetration rates, and realizes a two-way evaluation of the voltage qualification rate of distribution networks with high cable penetration rates based on both grid and load.

[0140] This application also provides a device for determining the voltage quality of a distribution network. It should be noted that this device can be used to execute the method for determining the voltage quality of a distribution network provided in this application. This device is used to implement the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0141] The following describes the voltage quality determination device for the power distribution network provided in the embodiments of this application.

[0142] Figure 6 This is a structural block diagram of a voltage quality determination device for a power distribution network according to an embodiment of this application. Figure 6 As shown, the device includes:

[0143] The first acquisition unit 10 is used to acquire voltage data of the distribution network;

[0144] The first determining unit 20 is used to determine the over-limit duration of the above distribution network within the target duration based on the above voltage data, wherein the over-limit duration is the sum of the first duration of the above voltage data exceeding the preset maximum value and the second duration of the above voltage data exceeding the preset minimum value;

[0145] The second determining unit 30 is used to determine the first qualification rate of the above-mentioned distribution network based on the above-mentioned over-limit duration, wherein the above-mentioned over-limit duration and the above-mentioned first qualification rate are negatively correlated.

[0146] This embodiment takes into account voltage fluctuations, i.e. voltage overruns. By statistically analyzing the duration of voltage overruns, the voltage quality, i.e., the first pass rate, is determined. This can more objectively reflect the voltage quality status of the distribution network within a specific period, resulting in better accuracy of the assessment.

[0147] In the specific implementation process, the first acquisition unit includes a first acquisition module, a second acquisition module, a partitioning module, and a clustering module. The first acquisition module is used to acquire an initial dataset, wherein the initial dataset includes at least the voltage amplitude of all monitoring points in the distribution network. The second acquisition module is used to acquire the electrical distance, wherein the electrical distance is the distance between the monitoring point and the main transformer. The partitioning module is used to partition the initial dataset according to the electrical distance to obtain data groups. The clustering module is used to perform clustering processing on the data groups using the K-means algorithm to obtain the voltage data.

[0148] In this scheme, voltage data of distribution networks with high cable coverage are effectively clustered based on electrical distance and K-means algorithm to identify the voltage characteristics of monitoring points in different regions or types. This provides strong support for more accurate assessment of voltage qualification rate and formulation of corresponding voltage optimization strategies.

[0149] In the specific implementation process, the above-mentioned device further includes a second acquisition unit, a first calculation unit, and a second calculation unit. The second acquisition unit is used to acquire the total duration after determining the over-limit duration of the distribution network within the target duration based on the voltage data. The first calculation unit is used to calculate the quotient of the first duration and the total duration to obtain a first proportion, wherein the first proportion is the proportion of the first duration in the total duration. The second calculation unit is used to calculate the quotient of the second duration and the total duration to obtain a second proportion, wherein the second proportion is the proportion of the second duration in the total duration.

[0150] In this scheme, the percentage of time the voltage exceeds the limit can be calculated, the percentage of time the voltage exceeds the upper limit and the percentage of time the voltage exceeds the lower limit, namely the first percentage and the second percentage. The voltage quality can then be further determined using these percentages.

[0151] In the specific implementation process, the above-mentioned device also includes a first generation unit and a second generation unit. The first generation unit is used to generate a scatter plot based on the first qualification rate of the distribution network after determining the first qualification rate based on the above-mentioned over-limit duration. The second generation unit is used to generate a target curve based on the above-mentioned first qualification rate.

[0152] This scheme provides a visual way to assess voltage quality in distribution networks with high cable penetration rates by generating scatter plots and target curves. This approach helps power companies and grid operators better understand the distribution characteristics of voltage compliance rates through intuitive graphical displays.

[0153] In some embodiments, the above-described apparatus further includes a third acquisition unit, a fourth acquisition unit, and a third determination unit. The third acquisition unit is used to acquire a first sub-qualification rate after determining the first qualification rate of the distribution network based on the above-described over-limit duration, wherein the first sub-qualification rate is the qualification rate of the power supply voltage of the distribution network. The fourth acquisition unit is used to acquire a second sub-qualification rate, wherein the second sub-qualification rate is the qualification rate of the voltage at the monitoring point of the switching station of the distribution network. The third determination unit is used to determine the relationship between the first sub-qualification rate and the second sub-qualification rate based on the Pearson correlation coefficient.

[0154] In this scheme, by calculating the Pearson correlation coefficient, the correlation between the power supply voltage qualification rate and the voltage qualification rate of the monitoring point of the switching station can be analyzed, providing data support and decision-making basis for voltage quality management and optimization of distribution networks with high cable coverage.

[0155] In some embodiments, the above-mentioned device further includes a fourth acquisition unit, a construction unit, and a processing unit. The fourth acquisition unit is used to acquire relevant information about the distribution network after determining the over-limit duration of the distribution network within a target time period based on the voltage data. The relevant information includes at least one or more of line length, transformer distribution location, load type, and environmental information. The construction unit is used to construct a quality detection model, wherein the quality detection model is trained using multiple sets of training data. Each set of training data includes historical over-limit duration, historical relevant information, and historical second pass rate corresponding to the historical over-limit duration and the historical relevant information acquired within a historical time period. The processing unit is used to input the over-limit duration and the relevant information into the quality detection model to obtain the second pass rate corresponding to the over-limit duration and the relevant information.

[0156] This solution utilizes machine learning technology to build a quality inspection model that predicts voltage quality trends in distribution networks with high cable penetration rates based on historical data. This approach not only helps power companies anticipate and address voltage issues in advance but also provides data support for optimizing power quality and grid operation strategies, thereby improving grid stability and service quality.

[0157] In some embodiments, the above-mentioned device further includes a fifth acquisition unit and a third generation unit. The fifth acquisition unit is used to acquire a preset qualification rate threshold after determining the first qualification rate of the distribution network based on the above-mentioned over-limit duration. The third generation unit is used to generate early warning information when the above-mentioned first qualification rate is less than or equal to the above-mentioned preset qualification rate threshold.

[0158] This solution provides an effective voltage quality early warning mechanism by setting a preset pass rate threshold and combining it with real-time monitoring data. It helps power companies promptly identify and address voltage quality issues, preventing power losses and equipment damage caused by voltage fluctuations, thereby improving the overall operational efficiency and service quality of the power grid.

[0159] The voltage quality determination device for the aforementioned power distribution network includes a processor and a memory. The first acquisition unit, the first determination unit, and the second determination unit are all stored as program units in the memory. The processor executes these program units stored in the memory to achieve the corresponding functions. All of the above modules are located in the same processor; alternatively, the modules may be located in different processors in any combination.

[0160] The processor contains a kernel, which retrieves the corresponding program units from memory. One or more kernels can be configured, and adjusting kernel parameters can address the problem of inaccurate voltage quality assessment in existing power distribution networks.

[0161] The memory may include non-permanent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0162] This invention provides a computer-readable storage medium including a stored program, wherein, when the program is executed, it controls the device containing the computer-readable storage medium to perform a method for determining the voltage quality of the power distribution network.

[0163] This invention provides a processor for running a program, wherein the program executes a method for determining the voltage quality of the power distribution network.

[0164] This invention provides a device including a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, it implements at least the steps of a method for determining the voltage quality of a power distribution network. The device described herein may be a server, PC, PAD, mobile phone, etc.

[0165] A computer program product includes a non-volatile computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the method for determining the voltage quality of the power distribution network described in various embodiments of this application.

[0166] This application also includes a distribution network detection system, comprising one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs include a method for performing any of the above-described methods for determining the voltage quality of the distribution network.

[0167] It is obvious to those skilled in the art that the modules or steps of the present invention described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. They can be implemented using computer-executable program code, and thus can be stored in a storage device for execution by a computing device. In some cases, the steps shown or described can be performed in a different order than those described herein, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, the present invention is not limited to any particular combination of hardware and software.

[0168] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0169] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0170] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0171] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0172] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0173] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, like read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0174] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0175] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0176] As can be seen from the above description, the embodiments of this application achieve the following technical effects:

[0177] 1) The method for determining the voltage quality of the distribution network in this application takes into account voltage fluctuations, i.e. voltage overruns. By statistically analyzing the duration of voltage overruns, the voltage quality, i.e. the first pass rate, is determined. This can more objectively reflect the voltage quality status of the distribution network within a specific period, resulting in better accuracy of the assessment.

[0178] 2) The voltage quality determination device for the distribution network in this application takes into account voltage fluctuations, i.e. voltage over-limit situations. By statistically analyzing the duration of voltage over-limit situations, the voltage quality, i.e. the first pass rate, is determined. This can more objectively reflect the voltage quality status of the distribution network within a specific period, resulting in better accuracy of the assessment.

[0179] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A method of determining voltage quality of an electrical distribution network, characterized in that, The method comprises: obtaining voltage data of a power distribution network; determining, according to the voltage data, an over-limit time length of the power distribution network within a target time length, wherein the over-limit time length is a sum of a first time length during which the voltage data exceeds a preset maximum value and a second time length during which the voltage data exceeds a preset minimum value; determining, according to the over-limit time length, a first qualification rate of the power distribution network, wherein the over-limit time length and the first qualification rate are in a negative correlation relationship; obtaining voltage data of a power distribution network comprises: obtaining an initial data set, wherein the initial data set at least includes voltage amplitudes of all monitoring points in the power distribution network; obtaining electrical distances of the monitoring points from main transformer, wherein the electrical distances are calculated by combining physical lengths of cables, resistance and reactance values of the cables, and a topology of the power distribution network; dividing the initial data set according to the electrical distances to obtain data groups; and performing clustering processing on the data groups by using a K-means algorithm to obtain the voltage data.

2. The method of claim 1, wherein, After determining, according to the voltage data, the over-limit time length of the power distribution network within the target time length, the method further comprises: obtaining a total time length; calculating a quotient of the first time length and the total time length to obtain a first proportion, wherein the first proportion is a proportion of the first time length in the total time length; calculating a quotient of the second time length and the total time length to obtain a second proportion, wherein the second proportion is a proportion of the second time length in the total time length.

3. The method of claim 1, wherein, After determining, according to the over-limit time length, the first qualification rate of the power distribution network, the method further comprises: generating a scatter plot according to the first qualification rate; generating a target curve according to the first qualification rate.

4. The method of claim 1, wherein, After determining, according to the over-limit time length, the first qualification rate of the power distribution network, the method further comprises: obtaining a first sub-qualification rate, wherein the first sub-qualification rate is a qualification rate of a power supply voltage of the power distribution network; obtaining a second sub-qualification rate, wherein the second sub-qualification rate is a qualification rate of a voltage of a monitoring point of a switch station of the power distribution network; determining a relationship between the first sub-qualification rate and the second sub-qualification rate according to a Pearson correlation coefficient.

5. The method of claim 1, wherein, After determining, according to the voltage data, the over-limit time length of the power distribution network within the target time length, the method further comprises: obtaining relevant information of the power distribution network, wherein the relevant information at least includes one or more of line length, distribution position of a transformer, load type, and environmental information; constructing a quality detection model, wherein the quality detection model is trained using a plurality of sets of training data, and each set of training data in the plurality of sets of training data includes a historical over-limit time length obtained in a historical time period, historical relevant information, a historical second qualification rate corresponding to the historical over-limit time length and the historical relevant information; inputting the over-limit time length and the relevant information into the quality detection model to obtain a predicted second qualification rate corresponding to the over-limit time length and the relevant information, wherein the second qualification rate is used to early warn voltage quality problems.

6. The method of claim 1, wherein, After determining the first qualification rate of the power distribution network according to the over-limit duration, the method further comprises: obtaining a preset qualification rate threshold; generating a warning information in a case that the first qualification rate is less than or equal to the preset qualification rate threshold.

7. A device for determining the voltage quality of an electricity distribution network, characterized in that Comprise: a first obtaining unit, configured to obtain voltage data of a power distribution network; a first determining unit, configured to determine an over-limit duration of the power distribution network within a target duration according to the voltage data, wherein the over-limit duration is a sum of a first duration in which the voltage data exceeds a preset maximum value and a second duration in which the voltage data exceeds a preset minimum value; a second determining unit, configured to determine a first qualification rate of the power distribution network according to the over-limit duration, wherein the over-limit duration and the first qualification rate are in a negative correlation relationship; The first obtaining unit comprises a first obtaining module, a second obtaining module, a division module and a clustering module, the first obtaining module is used for obtaining an initial data set, wherein the initial data set at least includes voltage amplitudes of all monitoring points in the power distribution network; the second obtaining module is used for obtaining electrical distances of the monitoring points and main transformer, wherein the electrical distance is calculated by combining the physical length of the cable, the resistance and reactance value of the cable, and the topology structure of the power distribution network; the division module is used for dividing the initial data set according to the electrical distance to obtain a data group; the clustering module is used for clustering the data group by using K-means algorithm to obtain the voltage data.

8. A computer program product comprising a computer program, characterized in that, The computer program is executed by the processor to realize the steps of the determination method of the voltage quality of the power distribution network in any one of claims 1 to 6.

9. A power distribution network detection system characterized by, Comprise: one or more processors, memories, and one or more programs, wherein the one or more programs are stored in the memories and configured to be executed by the one or more processors, and the one or more programs comprise a program for executing the determination method of the voltage quality of the power distribution network in any one of claims 1 to 6.

Images