Intelligent visualization and diagnosis system for key performance indexes of 10-kilovolt power grid

Abstract

The invention relates to the technical field of visualization and diagnosis systems, in particular to an intelligent visualization and diagnosis system for key performance indexes of a 10-kilovolt power grid. Comprising a big data integration and association module, an intelligent decision management module, an intelligent diagnosis and analysis module, a key performance index evaluation module, a multi-dimensional early warning module, an intelligent processing module and a data visualization module, and through cooperative work of all the modules, full-process optimization from data acquisition, processing and analysis to visual display and intelligent processing is achieved. The system not only can help power grid management personnel to quickly master the network operation condition and make a correct decision, but also can find and solve potential problems in advance through intelligent early warning and processing suggestions. According to the comprehensive and intelligent solution, the operation efficiency, reliability and safety of the power distribution network are greatly improved, and powerful technical support is provided for construction and operation of an intelligent power grid.

Description

Technical Field

[0001] The present invention relates to the technical field of visualization and diagnosis systems, and more specifically, to an intelligent visualization and diagnosis system for key performance indicators of a 10 kV power grid. Background Art

[0002] With the rapid development of power systems and the in-depth promotion of smart grid construction, the 10kV distribution network, as an important link between the power system and users, has a direct impact on the reliability and quality of power supply. In recent years, the intelligence level of distribution networks has been continuously improved, and the widespread application of various monitoring equipment and information systems has made the distribution network operation data present the characteristics of massive, multi-source and heterogeneous. However, how to effectively use this data to achieve comprehensive perception, intelligent diagnosis and visual display of the distribution network operation status is still a major challenge facing the power industry.

[0003] The existing 10 kV distribution network monitoring system mainly focuses on data collection and basic monitoring functions, and has obvious deficiencies in data analysis and decision support. Traditional systems often use a single data processing method, which is difficult to cope with the complex and changeable power grid operation conditions. For example, in line loss analysis, the commonly used fixed threshold judgment method cannot adapt to the line loss characteristics in different regions and different time periods, which can easily lead to misjudgment or missed judgment. In addition, the existing system is also relatively simple in data visualization, usually only providing basic chart displays, lacking interactivity and deep insight capabilities, and it is difficult to meet the needs of power grid operators to quickly grasp the network status and promptly discover potential problems.

[0004] In terms of early warning mechanisms, traditional systems mostly use a single indicator and fixed rules for early warning, which makes it difficult to fully reflect the operating status of the power grid. This method is not only prone to redundant or missing early warning information, but also fails to effectively identify complex faults caused by multiple coupling factors. At the same time, the existing system relies more on manual experience in early warning processing, lacks intelligent processing suggestions and automated processing capabilities, which affects the efficiency and accuracy of fault handling.

[0005] In addition, as the scale and complexity of distribution networks continue to expand, the traditional centralized system architecture faces severe challenges in data processing capabilities and system scalability. Problems such as slow system response speed and limited concurrent processing capabilities have seriously affected user experience and system practicality. Summary of the invention

[0006] In response to the above problems, the present invention proposes a 10 kV power grid key performance indicator intelligent visualization and diagnosis system. The system aims to realize intelligent analysis, multi-dimensional early warning, visualization and intelligent processing of distribution network operation data, thereby improving the operation efficiency, safety and reliability of the distribution network.

[0007] In order to solve the above technical problems, the present invention adopts the following technical solutions:

[0008] 10kV power grid key performance indicator intelligent visualization and diagnosis system, including:

[0009] Big data integration and correlation module for:

[0010] Based on the intelligent management platform, the integration and association of 10kV power grid basic data, substation business data, and distribution network structure data are realized;

[0011] An intelligent decision management module is electrically connected to the big data integration and association module and is used to:

[0012] Receiving the integrated correlation data sent by the big data integration and correlation module;

[0013] Based on the 10 kV power grid topology and the integrated associated data, determine and display the operating data of the current substation, feeder and distribution station;

[0014] The intelligent diagnosis and analysis module is electrically connected to the intelligent decision management module and is used to:

[0015] Receiving operation data sent by the intelligent decision management module;

[0016] Based on the operating data, multi-dimensional intelligent diagnostic analysis is performed, including line loss analysis, low voltage analysis, power theft analysis, and three-phase imbalance analysis;

[0017] Generate visual display data of diagnostic results;

[0018] The key performance indicator evaluation module is electrically connected to the intelligent diagnosis and analysis module and is used to:

[0019] Receiving the diagnostic result data sent by the intelligent diagnostic analysis module;

[0020] Based on the diagnosis result data, obtaining KPI index data through cluster analysis;

[0021] The multi-dimensional early warning module is electrically connected to the key performance indicator evaluation module and is used to:

[0022] Receiving KPI index data sent by the key performance indicator evaluation module;

[0023] Generate ledger warning, fault warning, and operation warning signals based on preset warning rules;

[0024] The intelligent processing module is electrically connected to the multi-dimensional early warning module and is used to:

[0025] Receiving the warning signal sent by the multi-dimensional warning module;

[0026] Based on the warning signal, automatically generate and execute a treatment plan;

[0027] The data visualization module is electrically connected to the intelligent diagnosis and analysis module, the key performance indicator evaluation module and the multi-dimensional early warning module, and is used to:

[0028] Receive data sent by the intelligent diagnosis and analysis module, the key performance indicator evaluation module and the multi-dimensional early warning module;

[0029] Based on the data, a graphical display interface is generated.

[0030] Preferably, the big data integration and association module includes:

[0031] Data acquisition unit, used to collect 10 kV power grid basic data, substation business data, and distribution network structure data;

[0032] A data preprocessing unit, electrically connected to the data acquisition unit, for cleaning, deduplicating and formatting the acquired data;

[0033] A data association unit, electrically connected to the data preprocessing unit, for performing association analysis on the preprocessed data based on a preset association rule;

[0034] The data storage unit is electrically connected to the data association unit and is used to store the data after the association analysis in a distributed database.

[0035] Preferably, the intelligent decision management module includes:

[0036] A topology analysis unit, used to analyze the grid structure characteristics based on the 10 kV grid topology structure;

[0037] a data fusion unit, electrically connected to the topology analysis unit, and configured to fuse the power grid structure characteristics with the integrated associated data;

[0038] A decision generating unit, electrically connected to the data fusion unit, for generating operation decision suggestions for the substation, feeder, and distribution station based on the fused data;

[0039] A visualization display unit is electrically connected to the decision generation unit and is used to display the operation decision suggestion in a graphical manner.

[0040] Preferably, the intelligent diagnosis and analysis module comprises:

[0041] Line loss analysis unit, used for line loss segmentation statistical analysis, line loss line analysis, line loss power supply radius analysis, and line loss household line analysis;

[0042] Low voltage analysis unit, used for statistical analysis of low voltage in the substation area;

[0043] The electricity theft analysis unit is used to analyze electricity theft in the substation area;

[0044] Three-phase unbalance analysis unit, used for three-phase unbalance analysis of the substation area and three-phase load unbalance analysis of the distribution network and distribution transformer;

[0045] The diagnosis result generating unit is electrically connected to the line loss analyzing unit, the low voltage analyzing unit, the power theft analyzing unit and the three-phase unbalance analyzing unit, and is used to integrate the analysis results of each unit to generate an overall diagnosis result.

[0046] Preferably, the key performance indicator evaluation module includes:

[0047] A data preprocessing unit, used for standardizing and normalizing the diagnosis result data;

[0048] A cluster analysis unit, electrically connected to the data preprocessing unit, and configured to perform K-means cluster analysis on the preprocessed data;

[0049] A KPI calculation unit, electrically connected to the cluster analysis unit, for calculating the KPI index of each key performance indicator based on the cluster analysis result;

[0050] An index evaluation unit is electrically connected to the KPI calculation unit and is used to perform a comprehensive evaluation on the key performance of the 10 kV power grid based on the KPI index.

[0051] Preferably, the multi-dimensional early warning module comprises:

[0052] Rule configuration unit, used to configure and manage warning rules;

[0053] Data monitoring unit, used to monitor the changes of KPI index data in real time;

[0054] An early warning generation unit, electrically connected to the rule configuration unit and the data monitoring unit, for generating a multi-dimensional early warning signal based on the early warning rule and the monitoring data;

[0055] The warning priority management unit is electrically connected to the warning generation unit and is used to prioritize and manage the multi-dimensional warning signals.

[0056] Preferably, the intelligent processing module comprises:

[0057] An early warning classification unit is used to classify the received early warning signals, including equipment processing early warnings and manual processing early warnings;

[0058] An automatic processing unit, electrically connected to the warning classification unit, for automatically generating and executing a processing plan for the device processing warning;

[0059] A manual processing recommendation unit, electrically connected to the warning classification unit, for generating processing suggestions for the manual processing warning and pushing them to relevant personnel;

[0060] The processing result feedback unit is electrically connected to the automatic processing unit and the manual processing recommendation unit, and is used to collect processing results and feed them back to the multi-dimensional early warning module for optimizing the early warning rules.

[0061] Preferably, the data visualization module comprises:

[0062] A data receiving unit, used to receive various types of data from other modules;

[0063] Visualization template library, used to store various visualization chart templates;

[0064] A chart generating unit, electrically connected to the data receiving unit and the visualization template library, for generating various charts based on the received data and the visualization template;

[0065] An interactive design unit, electrically connected to the chart generation unit, for designing and implementing interactive functions of the chart;

[0066] The display interface generation unit is electrically connected to the chart generation unit and the interaction design unit, and is used to integrate various charts and interaction functions to generate a final visual display interface.

[0067] As a preference, it also includes:

[0068] A load balancing module is electrically connected to the data visualization module and is used to:

[0069] Receive access requests from users;

[0070] Distribute the access request to different servers based on a preset load balancing strategy;

[0071] The load balancing strategies include a polling strategy, a minimum number of connections strategy, and a response time weighted strategy.

[0072] As a preference, it also includes:

[0073] A user rights management module is electrically connected to the data visualization module and is used to:

[0074] Manage user permissions for different roles, including system administrators, data administrators, and application administrators;

[0075] Control access rights to each functional module of the system based on user roles;

[0076] Wherein, the user authority management module also includes an identity authentication unit for implementing multi-factor identity authentication to improve system security.

[0077] Compared with the prior art, the beneficial effects of the present invention are embodied in the following aspects:

[0078] The system of the present invention effectively solves many problems existing in the prior art through innovative modular design and advanced data processing technology, and achieves remarkable technical effects. First, the big data integration and association module of the present invention realizes the effective integration of multi-source heterogeneous data, laying a solid foundation for subsequent intelligent analysis. This data fusion method not only improves data utilization, but also enables the system to fully perceive the operating status of the distribution network, greatly enhancing the accuracy and reliability of the analysis results.

[0079] Secondly, the intelligent decision management module and intelligent diagnosis analysis module of the present invention adopt advanced data mining and machine learning algorithms to achieve in-depth analysis and intelligent diagnosis of the distribution network operation status. This method breaks through the limitations of traditional fixed threshold judgment, can more accurately identify potential problems and abnormal conditions, and significantly improves the system's diagnostic accuracy and prediction ability.

[0080] In terms of early warning mechanism, the multi-dimensional early warning module and intelligent processing module of the present invention construct a comprehensive and flexible early warning processing system. Through multi-dimensional early warning indicators and dynamically adjusted early warning rules, the system can more accurately capture various potential risks. At the same time, intelligent processing suggestions and automated processing capabilities greatly improve the efficiency of fault handling and reduce the possibility of human error.

[0081] In terms of visualization, the data visualization module of the present invention provides rich and intuitive visualization effects and powerful interactive functions, which not only makes complex data analysis results easy to understand, but also supports operators to conduct in-depth data exploration and make more accurate decisions.

[0082] In addition, the distributed system architecture and load balancing technology adopted by the present invention greatly improve the performance and scalability of the system, which enables the system to cope with the needs of large-scale data processing and ensures efficient operation in a complex power grid environment.

[0083] In general, the 10 kV power grid key performance indicator intelligent visualization and diagnosis system of the present invention realizes the optimization of the whole process from data collection, processing, analysis to visualization and intelligent processing through the collaborative work of various modules. The system can not only help power grid managers quickly understand the network operation status and make correct decisions, but also discover and solve potential problems in advance through intelligent early warning and processing suggestions. This comprehensive and intelligent solution greatly improves the operating efficiency, reliability and safety of the distribution network, and provides strong technical support for the construction and operation of smart grids. BRIEF DESCRIPTION OF THE DRAWINGS

[0084] Figure 1 It is a flowchart of the overall system of the present invention.

[0085] Figure 2 It is a logical block diagram of the big data integration and association module of the present invention.

[0086] Figure 3 It is a logic block diagram of the intelligent decision management module of the present invention.

[0087] Figure 4 It is a logic block diagram of the intelligent diagnosis and analysis module of the present invention.

[0088] Figure 5 It is a logic block diagram of the key performance indicator evaluation module of the present invention.

[0089] Figure 6 It is a logic block diagram of the multi-dimensional early warning module of the present invention.

[0090] Figure 7 It is a logic block diagram of the intelligent processing module of the present invention.

[0091] Figure 8 It is a logic block diagram of the data visualization module of the present invention. DETAILED DESCRIPTION

[0092] like Figure 1-8 As shown, the present invention relates to an intelligent visualization and diagnosis system for key performance indicators of a 10 kV power grid. The system is intended to improve the operating efficiency, safety and reliability of the 10 kV power grid, and provide strong support for power grid management and decision-making through intelligent data analysis and visualization technology.

[0093] The 10 kV power grid key performance indicator intelligent visualization and diagnosis system of the present invention comprises the following key modules: big data integration and association module 1, intelligent decision management module 2, intelligent diagnosis and analysis module 3, key performance indicator evaluation module 4, multi-dimensional early warning module 5, intelligent processing module 6 and data visualization module 7. These modules cooperate with each other through electrical connection to jointly realize the functions of the system.

[0094] First, the big data integration and association module 1 is the data foundation of the entire system. Based on the intelligent management platform, this module realizes the integration and association of 10 kV power grid basic data, substation business data, and distribution network structure data. In practical applications, 10 kV power grid basic data may include transformer parameters, line impedance, etc.; substation business data may involve power consumption, power outage records, etc.; distribution network structure data may include topology structure, equipment layout and other information. The effective integration and association of these heterogeneous data is the key prerequisite for subsequent analysis.

[0095] The intelligent decision management module 2 is electrically connected to the big data integration and association module 1, and receives the integrated association data sent by it. The core function of this module is to determine and display the operating data of the current substation, feeder and distribution station based on the 10 kV power grid topology and integrated association data. For example, this module may analyze key operating parameters such as the substation load distribution, feeder voltage distribution, and transformer load rate of the distribution station. Through the comprehensive analysis of these data, the system can provide more comprehensive decision support for operators.

[0096] The intelligent diagnosis and analysis module 3 is the core analysis unit of the system. It is electrically connected to the intelligent decision management module 2, receives operation data and performs multi-dimensional intelligent diagnosis and analysis. Specifically, the module performs multiple diagnostic tasks such as line loss analysis, low voltage analysis, power theft analysis and three-phase imbalance analysis. Taking line loss analysis as an example, the module may use the following algorithm:

[0097]

[0098] Among them, the data on power supply and power sales come from the operating data provided by the intelligent decision-making management module 2.

[0099] For low voltage analysis, the system may set a voltage qualification rate threshold, such as 95%. When the voltage qualification rate of a certain substation is lower than this threshold, the system will issue a low voltage warning. The selection of this threshold is based on the experience value and relevant standards of the power industry.

[0100] Electricity theft analysis may involve more complex algorithms, such as abnormal electricity usage pattern recognition. The system may use machine learning methods, such as support vector machines (SVM) or random forest algorithms, to identify potential electricity theft by analyzing users' historical electricity usage data.

[0101] Three-phase imbalance analysis is an important indicator to ensure power supply quality. The system may use the following formula to calculate the three-phase imbalance:

[0102]

[0103] When the imbalance exceeds a certain threshold (such as 15%), the system will issue a warning.

[0104] These analysis results are then converted into visual display data to provide input for subsequent modules.

[0105] The key performance indicator evaluation module 4 is electrically connected to the intelligent diagnosis and analysis module 3, receives the diagnosis result data and obtains the KPI index data through cluster analysis. For example, the module may use the K-means clustering algorithm to classify each substation according to indicators such as line loss rate and voltage quality, so as to obtain the overall KPI evaluation result.

[0106] The multi-dimensional warning module 5 generates ledger warning, fault warning and operation warning signals based on the KPI index data provided by the key performance indicator evaluation module 4 and the preset warning rules. The warning rules may include specific conditions such as "issuing a warning when the line loss rate of a certain area exceeds 8% for 3 consecutive days".

[0107] The intelligent processing module 6 receives the warning signal sent by the multi-dimensional warning module 5 and automatically generates a processing plan. For example, for an abnormal line loss rate warning, the system may recommend line inspection or load adjustment.

[0108] Finally, the data visualization module 7 integrates the data from other modules to generate a graphical display interface. This may include a variety of visualization forms such as a heat map showing line loss distribution and a line graph showing voltage change trends.

[0109] The big data integration and association module 1 is further divided into a data collection unit 11 , a data preprocessing unit 12 , a data association unit 13 and a data storage unit 14 .

[0110] The data collection unit 11 is responsible for collecting various types of data. For example, it may collect real-time operation data through the SCADA system, collect power consumption data through the marketing system, and collect distribution network structure data through the GIS system.

[0111] The data preprocessing unit 12 is electrically connected to the data acquisition unit 11, and cleans, removes duplicates, and formats the collected data. This step is crucial because the original data may be missing, repeated, or have inconsistent formats. For example, for missing data, the system may use interpolation or mean filling methods to process it.

[0112] The data association unit 13 is electrically connected to the data preprocessing unit 12, and performs association analysis on the preprocessed data based on preset association rules. The association rules may include association based on geographic location, association based on time series, etc. For example, the system may associate the transformer operation data in the same substation with the power consumption data of the substation for subsequent more in-depth analysis.

[0113] The data storage unit 14 is electrically connected to the data association unit 13, and stores the data after association analysis in a distributed database. The use of distributed storage can improve the efficiency of data reading and writing and the scalability of the system. For example, the system may use the Hadoop Distributed File System (HDFS) to store large-scale historical data, and use a columnar database such as HBase to store recent data that needs to be accessed quickly.

[0114] The intelligent decision management module 2 is further subdivided into a topology analysis unit 21 , a data fusion unit 22 , a decision generation unit 23 and a visualization display unit 24 .

[0115] The topology analysis unit 21 analyzes the grid structure characteristics based on the 10 kV grid topology structure. This may involve graph theory algorithms, such as a minimum spanning tree algorithm to identify key lines, or a PageRank algorithm to evaluate the importance of each node.

[0116] The data fusion unit 22 is electrically connected to the topology analysis unit 21 to fuse the grid structure characteristics with the integrated associated data. This step may involve technologies such as data standardization and feature engineering to ensure that data from different sources can be effectively combined.

[0117] The decision generation unit 23 is electrically connected to the data fusion unit 22, and generates operation decision suggestions for the substation, feeder, and distribution station based on the fused data. This may involve an expert system or a machine learning model, such as a decision tree or a neural network, to generate targeted suggestions.

[0118] The visualization display unit 24 is electrically connected to the decision generation unit 23, and displays the operation decision suggestions in a graphical manner. For example, the system may use a dashboard to display key performance indicators and a geographic information system (GIS) to display spatially distributed decision suggestions.

[0119] Through this modular and hierarchical design, the system of the present invention can effectively process the complex data of the 10 kV power grid, provide intelligent diagnosis and decision support, and help operators quickly understand and respond to various situations through intuitive visual display. This system can not only improve the operating efficiency and reliability of the power grid, but also reduce operation and maintenance costs and improve customer satisfaction. The system of the present invention further includes an intelligent diagnosis and analysis module 3 as described in claim 4. This module is one of the core analysis units of the present invention, including a line loss analysis unit 31, a low voltage analysis unit 32, a power theft analysis unit 33, a three-phase unbalance analysis unit 34 and a diagnosis result generation unit 35. These units work together to provide comprehensive diagnostic analysis for the 10 kV power grid.

[0120] The line loss analysis unit 31 is responsible for performing line loss segmentation statistical analysis, line loss line analysis, line loss power supply radius analysis and line loss household line analysis. In a preferred embodiment of the present invention, the line loss segmentation statistical analysis adopts the following formula:

[0121]

[0122] Among them, P 入 is the input power of the segment, P 出 By comparing the line loss rates of different segments, the system can identify areas with higher line losses, thus providing direction for subsequent optimization.

[0123] The low voltage analysis unit 32 focuses on the statistical analysis of low voltage in the substation. Preferably, the unit uses the voltage qualification rate index to evaluate the low voltage situation:

[0124]

[0125] The system of the present invention marks the substations with a voltage qualification rate lower than 95% as objects requiring attention. This threshold is determined based on power industry standards and actual operating experience and can be adjusted according to specific circumstances.

[0126] The electricity theft analysis unit 33 uses advanced data mining technology to detect potential electricity theft behavior. In one embodiment of the present invention, the unit uses an anomaly detection algorithm, such as Isolation Forest, to identify abnormal electricity usage patterns. The core idea of ​​the algorithm is:

[0127]

[0128] Among them, E(h(x)) is the average path length of sample x, and c(n) is the average path length of the binary tree with sample size n. The closer the score is to 1, the more likely it is abnormal (electricity theft) behavior.

[0129] The three-phase unbalance analysis unit 34 is responsible for performing three-phase unbalance analysis in the substation area and three-phase load unbalance analysis in the distribution network. The present invention uses the following formula to calculate the three-phase unbalance:

[0130]

[0131] Among them, I A ,I B ,I C They are the three-phase current, I avg is the average value of the three-phase current. When the imbalance exceeds 20%, the system will issue a warning. This threshold is set based on the experience of power system operation.

[0132] The diagnosis result generation unit 35 is electrically connected to all the above analysis units, and integrates the analysis results of each unit to generate an overall diagnosis result. This unit adopts a weighted scoring method to weight the scores of each indicator and obtain the final diagnosis result. The weight allocation is based on expert experience and historical data analysis, and can be dynamically adjusted according to actual conditions.

[0133] The key performance indicator evaluation module 4 of the present invention is further divided into a data preprocessing unit 41, a cluster analysis unit 42, a KPI calculation unit 43 and an indicator evaluation unit 44. These units work together to convert complex diagnostic results into key performance indicators that are easy to understand and operate.

[0134] The data preprocessing unit 41 first standardizes and normalizes the diagnosis result data. The standardization process uses the Z-score method:

[0135]

[0136] Among them, x is the original data, μ is the mean value, and σ is the standard deviation. Normalization uses the Min-Max method:

[0137]

[0138] These treatments ensure that indicators of different purity can be compared on the same scale.

[0139] The cluster analysis unit 42 uses an improved K-means algorithm to perform cluster analysis on the preprocessed data. The improved K-means algorithm determines the optimal number of clusters through a dichotomy method, thereby improving the clustering effect. The purpose of clustering is to group areas or devices with similar characteristics into a group to facilitate subsequent KPI calculation and evaluation.

[0140] The KPI calculation unit 43 calculates the KPI index of each key performance indicator based on the clustering result. For example, for the line loss rate KPI, the following formula can be used:

[0141]

[0142] Among them, the target line loss rate can be set based on historical data and industry standards, usually between 6% and 8%.

[0143] The index evaluation unit 44 performs a comprehensive evaluation on the key performance of the 10 kV power grid based on various KPI indexes. The present invention adopts a fuzzy comprehensive evaluation method to obtain the final evaluation result by performing fuzzy matrix operations on various KPI indexes. This method can better handle the uncertainty and ambiguity in the evaluation process.

[0144] The multi-dimensional early warning module 5 of the present invention comprises a rule configuration unit 51, a data monitoring unit 52, an early warning generation unit 53 and an early warning priority management unit 54. These units work together to construct a comprehensive and flexible early warning system.

[0145] The rule configuration unit 51 allows the system administrator to configure and manage the warning rules according to actual needs. In a preferred embodiment of the present invention, the warning rules adopt an IF-THEN structure, for example:

[0146] IF (line loss rate > 8% AND duration > 3 days) THEN issue a high priority line loss warning;

[0147] This structure is both intuitive and flexible, making it easy for system administrators to make adjustments based on actual conditions.

[0148] The data monitoring unit 52 monitors the changes of KPI index data in real time. The unit uses sliding window technology to continuously calculate and update the short-term, medium-term and long-term trends of various indicators. For example, for line loss rate, the 24-hour, 7-day and 30-day moving averages may be monitored simultaneously.

[0149] The warning generation unit 53 generates a multi-dimensional warning signal based on the warning rules and monitoring data. The system of the present invention uses fuzzy logic to deal with the uncertainty in the warning generation process. For example, for line loss warning, the following fuzzy set may be defined:

[0150] Low line loss: [0%, 5%];

[0151] Medium line loss: [4%, 9%];

[0152] High line loss: [8%, 100%];

[0153] Through this fuzzy classification, the system can describe the line loss condition more accurately, thereby generating more accurate early warning signals.

[0154] The warning priority management unit 54 prioritizes and manages the generated multi-dimensional warning signals. The present invention uses the analytic hierarchy process (AHP) to determine the weights of different warnings, and calculates the final priority score based on the urgency and impact of the warning. This ensures that the most important and urgent warnings can be processed in a timely manner.

[0155] The intelligent processing module 6 of the present invention comprises an early warning classification unit 61, an automatic processing unit 62, a manual processing recommendation unit 63 and a processing result feedback unit 64. These units together constitute a closed-loop early warning processing system.

[0156] The warning classification unit 61 first classifies the received warning signals into two categories: equipment processing warnings and manual processing warnings. The classification process uses a decision tree algorithm to automatically classify according to the type, severity, historical processing methods and other characteristics of the warning.

[0157] The automatic processing unit 62 is responsible for automatically generating and executing a processing plan for the equipment processing warning. In one embodiment of the present invention, the unit uses a rule-based expert system to generate a processing plan. For example, for a three-phase imbalance warning, the system may automatically generate the following processing plan:

[0158] 1. Check whether the load distribution is reasonable;

[0159] 2. Adjust the phase switch status;

[0160] 3. Load transfer when necessary

[0161] The manual processing recommendation unit 63 generates processing suggestions for the manual processing warning and pushes them to relevant personnel. This unit uses case-based reasoning (CBR) technology to generate processing suggestions based on historical processing cases. The system calculates the similarity between the current warning and the historical case, and recommends the processing method of the most similar case.

[0162] The processing result feedback unit 64 collects the processing results and feeds them back to the multi-dimensional warning module 5 for optimizing the warning rules. This unit uses a reinforcement learning algorithm to adjust the parameters of the warning rules according to the effectiveness of the processing results. For example, if a warning occurs frequently but the processing effect is not good, the system may increase the trigger threshold of this type of warning.

[0163] Through this intelligent early warning processing mechanism, the system of the present invention can greatly improve the operating efficiency and reliability of the 10 kV power grid, reduce manual intervention, and improve the timeliness and accuracy of fault handling. The system of the present invention further includes a data visualization module 7 as described in claim 8. This module is an important part of the system of the present invention and is responsible for converting complex data analysis results into intuitive and easy-to-understand visual presentations. The data visualization module 7 includes a data receiving unit 71, a visualization template library 72, a chart generation unit 73, an interactive design unit 74, and a display interface generation unit 75. These units work together to provide users with a rich and interactive visualization experience.

[0164] The data receiving unit 71 is responsible for receiving various data from other modules of the system. In a preferred embodiment of the present invention, the unit adopts an asynchronous data transmission mechanism to ensure efficient reception and processing of large amounts of data. For example, for real-time monitoring data, the system may use the WebSocket protocol to achieve real-time data push; for large-scale historical data, a batch transmission strategy may be used to avoid the system burden caused by transmitting a large amount of data at one time.

[0165] The visualization template library 72 stores various visualization chart templates. The system of the present invention presets a variety of chart types suitable for displaying power grid data, such as line loss distribution heat map, voltage change trend map, load curve map, etc. Preferably, these templates are described in an extensible JSON format to facilitate dynamic loading and rendering of the system.

[0166] The chart generation unit 73 is electrically connected to the data receiving unit 71 and the visualization template library 72, and is responsible for generating various charts based on the received data and visualization templates. The system of the present invention adopts a modular chart generation strategy, and each chart type corresponds to an independent generator. This design facilitates the subsequent expansion of new chart types. During the chart generation process, the system automatically performs operations such as data mapping, scale adjustment, and color mapping to ensure that the generated chart is both beautiful and accurately reflects the data characteristics.

[0167] The interactive design unit 74 is electrically connected to the chart generation unit 73 and is responsible for designing and implementing the interactive functions of the chart. The system of the present invention provides a wealth of interactive options, such as data filtering, drilling, zooming, prompt boxes, etc. Preferably, these interactive functions are implemented in an event-driven manner to improve the system's response speed and user experience. For example, for a line loss distribution heat map, the system may implement the following interactions:

[0168] Hover the mouse to display detailed data;

[0169] Click on a certain area to drill down and display the detailed line loss situation of the area;

[0170] The time axis slides to dynamically display the changes in line loss distribution in different time periods.

[0171] The display interface generation unit 75 is electrically connected to the chart generation unit 73 and the interactive design unit 74, and is responsible for integrating various charts and interactive functions to generate the final visual display interface. The system of the present invention adopts a responsive design to ensure that the interface can be well displayed on different devices (such as PCs, tablets, and mobile phones). Preferably, the system adopts a grid layout system to facilitate flexible adjustment of the position and size of each chart. In addition, the system also provides a custom dashboard function, allowing users to combine and arrange different charts according to their own needs.

[0172] The system of the present invention also includes a load balancing module 8. This module is electrically connected to the data visualization module 7 and plays a key role in improving system performance and reliability. The load balancing module 8 is mainly responsible for receiving user access requests and distributing the requests to different servers based on a preset load balancing strategy.

[0173] In one embodiment of the present invention, the load balancing module 8 adopts software defined network (SDN) technology to achieve more flexible and intelligent load balancing. The system presets three load balancing strategies: polling strategy, minimum connection number strategy and response time weighted strategy.

[0174] The polling strategy is the simplest load balancing method. The system distributes requests to each server in sequence. This strategy is suitable for situations where the server performance is similar and the request complexity is similar. Its mathematical expression is as follows:

[0175] ServerIndex=(CurrentIndex+1)modN,

[0176] Where N is the total number of servers and CurrentIndex is the current server index.

[0177] The minimum number of connections strategy allocates requests based on the current number of connections of the server, and always selects the server with the least number of connections. This strategy is suitable for situations where the request processing time varies greatly. Its selection process can be expressed as:

[0178] SelectedServer=argmin i ConnectionCount i ,

[0179] Among them, ConnectionCount i is the current number of connections to the i-th server.

[0180] The response time weighting strategy takes into account the server's response time and current load. The system calculates the weight of each server:

[0181]

[0182] Then the requests are distributed according to the weight ratio. This strategy can better balance the server load and improve the overall system performance.

[0183] The system of the present invention will dynamically adjust the adopted load balancing strategy according to the real-time monitored server status and network conditions to achieve the best system performance.

[0184] Finally, the system of the present invention also includes a user rights management module 9. This module is electrically connected to the data visualization module 7 and is responsible for managing the user rights of different roles, including system administrators, data administrators and application administrators, and controlling access rights to various functional modules of the system based on user roles.

[0185] In a preferred embodiment of the present invention, the user rights management module 9 adopts a role-based access control (RBAC) model. The system predefines multiple roles, each of which corresponds to a set of rights. For example:

[0186] System administrator: has the highest authority and can perform system configuration, user management and other operations;

[0187] Data administrator: can perform operations such as data import, export, and cleaning;

[0188] Application administrator: can use the system's analysis functions, view reports, etc.

[0189] The system uses an access control matrix to manage permissions. The rows of the matrix represent user roles, the columns represent system functions, and the matrix elements represent whether the corresponding permissions are granted. For example:

[0190] Role System Configuration Data Management Data analysis Report View System Administrator 1 1 1 1 Data Administrator 0 1 1 1 Application Administrator 0 0 1 1

[0191] Among them, 1 means permission, and 0 means no permission.

[0192] In addition, the user rights management module 9 also includes an identity authentication unit for implementing multi-factor identity authentication to improve system security. The system of the present invention adopts a two-factor authentication mechanism, which requires the user to enter a dynamic verification code in addition to the traditional username and password. The verification code is generated using a time-based one-time password algorithm (TOTP):

[0193] TOTP=HOTP(K,T),

[0194] Where K is a user-specific key and T is the time step based on the current timestamp. The HOTP function is based on the HMAC algorithm:

[0195] HOTP(K,C)=Truncate(HMAC-SHA-1(K,C)),

[0196] This multi-factor authentication mechanism greatly improves the security of the system and effectively prevents unauthorized access.

[0197] Through the collaborative work of these modules, the 10 kV power grid key performance indicator intelligent visualization and diagnosis system of the present invention realizes efficient data processing, intelligent analysis, intuitive display and safe management. The system can not only help power grid managers quickly understand the network operation status and make correct decisions, but also discover and solve potential problems in advance through intelligent early warning and processing suggestions, thereby improving the operation efficiency and reliability of the power grid.

[0198] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto; any person familiar with the art who, within the scope disclosed by the present invention, makes substitutions or changes based on the scheme and improved concepts of the present invention shall be covered within the protection scope of the present invention.

Claims

1. 10 kV power grid key performance indicator intelligent visualization and diagnosis system, characterized by: include: Big data integration and correlation module for: Based on the intelligent management platform, the integration and association of 10kV power grid basic data, substation business data, and distribution network structure data are realized; An intelligent decision management module is electrically connected to the big data integration and association module and is used to: Receiving the integrated correlation data sent by the big data integration and correlation module; Based on the 10 kV power grid topology and the integrated associated data, determine and display the operating data of the current substation, feeder and distribution station; The intelligent diagnosis and analysis module is electrically connected to the intelligent decision management module and is used to: Receiving operation data sent by the intelligent decision management module; Based on the operating data, multi-dimensional intelligent diagnostic analysis is performed, including line loss analysis, low voltage analysis, power theft analysis, and three-phase imbalance analysis; Generate visual display data of diagnostic results; The key performance indicator evaluation module is electrically connected to the intelligent diagnosis and analysis module and is used to: Receiving the diagnostic result data sent by the intelligent diagnostic analysis module; Based on the diagnosis result data, obtaining KPI index data through cluster analysis; The multi-dimensional early warning module is electrically connected to the key performance indicator evaluation module and is used to: Receiving KPI index data sent by the key performance indicator evaluation module; Generate ledger warning, fault warning, and operation warning signals based on preset warning rules; The intelligent processing module is electrically connected to the multi-dimensional early warning module and is used to: Receiving the warning signal sent by the multi-dimensional warning module; Based on the warning signal, automatically generate and execute a treatment plan; The data visualization module is electrically connected to the intelligent diagnosis and analysis module, the key performance indicator evaluation module and the multi-dimensional early warning module, and is used to: Receive data sent by the intelligent diagnosis and analysis module, the key performance indicator evaluation module and the multi-dimensional early warning module; Based on the data, a graphical display interface is generated.

2. The system according to claim 1, characterized in that The big data integration and association module includes: Data acquisition unit, used to collect 10 kV power grid basic data, substation business data, and distribution network structure data; A data preprocessing unit, electrically connected to the data acquisition unit, for cleaning, deduplicating and formatting the acquired data; A data association unit, electrically connected to the data preprocessing unit, and configured to perform association analysis on the preprocessed data based on a preset association rule; The data storage unit is electrically connected to the data association unit and is used to store the data after the association analysis in a distributed database.

3. The system according to claim 1, characterized in that The intelligent decision management module includes: A topology analysis unit, used to analyze the grid structure characteristics based on the 10 kV grid topology structure; a data fusion unit, electrically connected to the topology analysis unit, and configured to fuse the power grid structure characteristics with the integrated associated data; A decision generating unit, electrically connected to the data fusion unit, for generating operation decision suggestions for the substation, feeder, and distribution station based on the fused data; A visualization display unit is electrically connected to the decision generation unit and is used to display the operation decision suggestion in a graphical manner.

4. The system according to claim 1, characterized in that The intelligent diagnosis and analysis module includes: Line loss analysis unit, used for line loss segmentation statistical analysis, line loss line analysis, line loss power supply radius analysis, and line loss household line analysis; Low voltage analysis unit, used for statistical analysis of low voltage in the substation area; The electricity theft analysis unit is used to analyze electricity theft in the substation area; Three-phase unbalance analysis unit, used for three-phase unbalance analysis of the substation area and three-phase load unbalance analysis of the distribution network and distribution transformer; The diagnosis result generating unit is electrically connected to the line loss analyzing unit, the low voltage analyzing unit, the power theft analyzing unit and the three-phase unbalance analyzing unit, and is used to integrate the analysis results of each unit to generate an overall diagnosis result.

5. The system according to claim 1, characterized in that The key performance indicator evaluation module includes: A data preprocessing unit, used for standardizing and normalizing the diagnosis result data; A cluster analysis unit, electrically connected to the data preprocessing unit, and configured to perform K-means cluster analysis on the preprocessed data; A KPI calculation unit, electrically connected to the cluster analysis unit, for calculating the KPI index of each key performance indicator based on the cluster analysis result; An index evaluation unit is electrically connected to the KPI calculation unit and is used to perform a comprehensive evaluation on the key performance of the 10 kV power grid based on the KPI index.

6. The system according to claim 1, characterized in that The multi-dimensional early warning module includes: Rule configuration unit, used to configure and manage warning rules; Data monitoring unit, used to monitor the changes of KPI index data in real time; An early warning generation unit, electrically connected to the rule configuration unit and the data monitoring unit, for generating a multi-dimensional early warning signal based on the early warning rule and the monitoring data; The warning priority management unit is electrically connected to the warning generation unit and is used to prioritize and manage the multi-dimensional warning signals.

7. The system according to claim 1, characterized in that The intelligent processing module comprises: An early warning classification unit is used to classify the received early warning signals, including equipment processing early warnings and manual processing early warnings; An automatic processing unit, electrically connected to the warning classification unit, for automatically generating and executing a processing plan for the device processing warning; A manual processing recommendation unit, electrically connected to the warning classification unit, for generating processing suggestions for the manual processing warning and pushing them to relevant personnel; The processing result feedback unit is electrically connected to the automatic processing unit and the manual processing recommendation unit, and is used to collect processing results and feed them back to the multi-dimensional early warning module for optimizing the early warning rules.

8. The system according to claim 1, characterized in that The data visualization module includes: A data receiving unit, used to receive various types of data from other modules; Visualization template library, used to store various visualization chart templates; A chart generating unit, electrically connected to the data receiving unit and the visualization template library, for generating various charts based on the received data and the visualization template; An interactive design unit, electrically connected to the chart generation unit, for designing and implementing interactive functions of the chart; The display interface generation unit is electrically connected to the chart generation unit and the interaction design unit, and is used to integrate various charts and interaction functions to generate a final visual display interface.

9. The system according to claim 1, characterized in that Also includes: A load balancing module is electrically connected to the data visualization module and is used to: Receive access requests from users; Distribute the access request to different servers based on a preset load balancing strategy; The load balancing strategies include a round-robin strategy, a minimum number of connections strategy, and a response time weighted strategy.

10. The system according to claim 1, characterized in that Also includes: A user rights management module, electrically connected to the data visualization module, for managing user rights of different roles, including system administrators, data administrators, and application administrators; Based on user roles, control access rights to various functional modules of the system; wherein the user rights management module also includes an identity authentication unit for implementing multi-factor identity authentication to improve system security.

Images