Digital operation and maintenance system for power distribution network frame
By designing a digital operation and maintenance system for distribution network grids, the problems of single and low efficiency of distribution network management methods are solved, scientific evaluation and optimization of distribution networks are achieved, and operation stability and power supply capacity are improved.
Patent Information
- Application Number
- CN202411651744.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-19
- Publication Date
- 2025-03-04
AI Technical Summary
The existing distribution network management methods are single and low efficiency, and the overall power grid cannot be evaluated and optimized in a timely manner, resulting in unstable operation of the distribution network and affecting the safety and economical power supply.
Design a digital operation and maintenance system for distribution network grids, including CPU modules, main control modules, storage modules, evaluation modules and optimization modules. Through data acquisition, topological structure establishment and stability level index calculation, the stability of the distribution network is evaluated, and the operating efficiency and reliability of the distribution network are improved through load prediction and equipment optimization measures.
The scientific planning and transformation of the distribution network has been realized, the stability and power supply capacity of the distribution network have been improved, the operating costs and environmental impact have been reduced, and the continuous and reliable power supply for power users have been ensured.
Smart Images
Figure CN119559009A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of power systems, and in particular to a digital operation and maintenance system for a distribution network. Background Art
[0002] At present, the construction of distribution network in my country is still in the stage of continuous exploration. The distribution network is the terminal link of power transmission and is directly connected to users. Its importance is self-evident. The good operation and maintenance of distribution network equipment is a basic work to ensure the health of distribution network assets and realize the reliable operation of distribution network. It is related to the continuous and reliable power supply of the majority of power users and the safe and reliable operation of the power grid. Once the distribution equipment fails, it often causes power outages for users, resulting in direct and indirect economic losses. The forced shutdown of key equipment will even seriously affect the stable operation of the entire regional power grid.
[0003] Currently, when managing the distribution network, the operation and maintenance methods are single and inefficient, and it is impossible to evaluate and optimize the entire power grid in a timely manner, which needs to be improved. Summary of the invention
[0004] The purpose of the present invention is to provide a digital operation and maintenance system for a power distribution network to solve the problems raised in the above-mentioned background technology.
[0005] To achieve the above-mentioned purpose, the present invention provides the following technical solutions: a digital operation and maintenance system for a distribution network, comprising a CPU module, a main control module, a storage module, an evaluation module and an optimization module, wherein the CPU module is bidirectionally connected with the main control module, the storage module, the evaluation module and the optimization module, the main control module is used for an operator to log in to an account to operate the system, the storage module is used to store information data obtained by the system, the evaluation module is used to evaluate the stability of the distribution network, and the optimization module is used to optimize the distribution network.
[0006] Preferably, the evaluation module includes a data acquisition unit, a confirmation unit and a calculation unit; The data acquisition unit is used to collect distribution network data, wherein the data includes the load density of the distribution network, the total capacity parameters of the substations in the distribution network and the load rate that need to be acquired; The confirmation unit establishes a topological structure of the distribution network according to the load density of the distribution network, the total capacity parameters of the substations in the distribution network and the load rate acquired by the data acquisition unit; The calculation unit calculates the stability grade index of the distribution network based on the topological structure established by the confirmation unit and the pre-set stability parameters corresponding to various grid structures, the stability parameters including the failure rate and repair time corresponding to the load rate, and the number of nodes and stability parameters of various grid structures. The stability parameters used include the failure rate and repair time of cables and overhead lines, and the failure rate, repair time and switching time of switches and circuit breakers can also be considered. The stability grade index of the overall medium-voltage distribution network is obtained by multiplying the stability parameters corresponding to various grid structures by the number of nodes of various grid structures.
[0007] Preferably, before establishing the topological structure of the distribution network, it is necessary to obtain an analysis model of the proportional relationship between the line length, total capacity parameters, load density and load rate of the distribution network line, and then determine the topological structure of the distribution network based on the analysis model and the load rate; The analytical model includes determining the number of substations Y 变 , determine the number of lines Y in the distribution network 线 , determine the power supply radius R of the line and determine the line length L of the line; Y 变 = ,in is the load density, is the substation capacity, is the load factor; Y 线 = ,in is the total capacity parameter, Economic transmission capacity for distribution network lines; The distribution network is a power supply mode with the substation as the center and divided into zones and sections. The power supply area is approximately circular, so the power supply radius R of the distribution line can be calculated. ; The tortuosity coefficient of the distribution network is set to 1.414 in advance, so L=1.414RY 线 ; To simulate the distribution grid in different regions and at different development stages, the load density is 0.1MW / km. 2 、0.5MW / km 2 、1MW / km 2 、5MW / km 2 、10MW / km 2 、20MW / km 2 、30MW / km 2 、40MW / km 2 、50MW / km 2 Nine levels to consider.
[0008] Preferably, the establishment of the topological structure of the distribution network is to obtain the number of nodes of various grid structures in the distribution network, the grid structures include overhead network radial type, overhead network multi-segment single connection type, overhead network multi-segment multi-connection type, cable network single-shot type, cable network double-shot type, cable network opposite-shot type, cable network single-ring type, cable network double-ring type and cable network N-supply-one-standby type, according to the load rate, determine the node coefficient corresponding to each grid structure, according to the line length and the node coefficient, determine the number of nodes of each grid structure in the distribution network.
[0009] Preferably, when calculating the stability grade index, the weight values corresponding to various grid structures are first determined based on the failure rate and the repair time, and then the weight values corresponding to the various grid structures are multiplied by the number of grid nodes corresponding to the various grid structures, and the product value is used as the calculated value of the grid structure. Then, the number of grid nodes corresponding to the various grid structures is multiplied by the calculated value corresponding to the various grid structures to obtain the sub-stability grade index corresponding to the various grid structures, and finally, the sub-stability registration indices corresponding to the various grid structures are added to obtain the stability grade index of the total distribution network.
[0010] Preferably, the optimization module includes a prediction unit, an equipment unit, an energy control unit and a prevention unit; The prediction unit is used for data-driven load prediction and optimization. By analyzing and modeling historical data, accurate prediction of future load changes can be achieved, thereby rationally allocating equipment capacity and improving the stability and economy of the distribution network. The equipment unit is an equipment optimization and upgrade based on advanced technology, using advanced switchgear, sensors and automation technology to improve the operating efficiency and reliability of the distribution network and reduce energy loss; The energy control unit is responsible for multi-energy integration and intelligent scheduling, introduces renewable energy and energy storage technology, and realizes the coordinated operation of different energy sources through intelligent scheduling algorithms, thereby improving energy utilization efficiency and reducing environmental impact; The prevention unit is used to handle and solve the abnormal situations faced by the distribution network. Through the robust design for dealing with disasters and failures, the reliability engineering method is adopted, and the backup plan and self-healing control strategy are used to improve the disaster resistance and recovery speed of the distribution network and ensure the stability of power supply. These directions together constitute the comprehensive research content of the optimization of the distribution network grid scheme.
[0011] Preferably, before performing the modeling, a large amount of historical data, real-time monitoring data and other relevant data are first collected from the power system. These data will be used as training data to establish a load forecasting model, and then the obtained data is cleaned and processed. Cleaning and processing the data include removing abnormal data, processing missing values and extracting features, and then selecting an appropriate artificial intelligence algorithm, such as a neural network, a genetic algorithm, a deep learning algorithm, etc., to establish a load forecasting model based on the training data, and finally using test data to evaluate the accuracy and predictive ability of the model; by analyzing and modeling the historical data, an accurate and reliable load forecasting model is obtained, and specifically a time series method or an artificial neural network method is used for load forecasting modeling. When the time series method is used: based on the idea of time series analysis, ARIMA, SARIMA or VAR models are used to predict future load values; when the artificial neural network method is used: the working principle of human brain neurons is simulated, and a calculation model is constructed by connecting multiple neurons to each other, thereby realizing load forecasting. The neural network used is a BP neural network, an RBF neural network or an LSTM neural network.
[0012] Compared with the prior art, the present invention has the following beneficial effects: The present invention proposes a distribution network digital operation and maintenance system, which, by providing an evaluation module, promotes and improves the production technology and management of the electric power industry, and provides a scientific basis for the planning and transformation of the distribution network, thereby realizing the planning, design and construction of new systems, or the expansion, transformation and development of the power supply capacity of the existing distribution network based on the existing operating status of the distribution network; and is provided with an optimization module, which can predict the load of the distribution network as a whole, and take corresponding measures to improve the practical capacity and effect of the distribution network. BRIEF DESCRIPTION OF THE DRAWINGS
[0013] Figure 1 It is a schematic diagram of the system structure of the present invention.
[0014] Figure 2 It is a schematic diagram of the structure of the evaluation module of the present invention.
[0015] Figure 3 Schematic diagram of the evaluation module flow of the present invention.
[0016] Figure 4 This is a schematic diagram of the optimization module structure of the present invention.
[0017] Figure 5 The flowchart of the prediction unit modeling of the present invention is shown. DETAILED DESCRIPTION
[0018] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0019] See also Figures 1 to 5 The present invention provides a technical solution: a digital operation and maintenance system for a distribution network, including a CPU module, a main control module, a storage module, an evaluation module and an optimization module. The CPU module is bidirectionally connected with the main control module, the storage module, the evaluation module and the optimization module. The main control module is used for an operator to log in to an account to operate the system. The storage module is used to store information data obtained by the system. The evaluation module is used to evaluate the stability of the distribution network. The optimization module is used to optimize the distribution network.
[0020] The evaluation module includes a data acquisition unit, a confirmation unit and a calculation unit; The data acquisition unit is used to collect distribution network data, wherein the data includes the load density of the distribution network, the total capacity parameters of the substations in the distribution network and the load rate that need to be acquired; The confirmation unit establishes a topological structure of the distribution network according to the load density of the distribution network, the total capacity parameters of the substations in the distribution network and the load rate acquired by the data acquisition unit; The calculation unit calculates the stability grade index of the distribution network based on the topological structure established by the confirmation unit and the pre-set stability parameters corresponding to various grid structures. The stability parameters include the failure rate and repair time corresponding to the load rate. According to the number of nodes and stability parameters of various grid structures, the stability grade index of the distribution network is calculated. The stability parameters used include the failure rate and repair time of cables and overhead lines, and the failure rate, repair time and switching time of switches and circuit breakers can also be considered. The stability parameters corresponding to various grid structures are multiplied by the number of nodes of various grid structures to obtain the overall stability grade index of the medium-voltage distribution network.
[0021] Before establishing the topological structure of the distribution network, it is necessary to obtain an analysis model of the proportional relationship between the line length, total capacity parameters, load density and load rate of the distribution network line, and then determine the topological structure of the distribution network based on the analysis model and the load rate; The analytical model includes determining the number of substations Y 变 , determine the number of lines Y in the distribution network 线 , determine the power supply radius R of the line and determine the line length L of the line; Y 变 = ,in is the load density, is the substation capacity, is the load factor; Y 线 = ,in is the total capacity parameter, Economic transmission capacity for distribution network lines; The distribution network is a power supply mode with the substation as the center and divided into zones and sections. The power supply area is approximately circular, so the power supply radius R of the distribution line can be calculated. ; The tortuosity coefficient of the distribution network is set to 1.414 in advance, so L=1.414RY 线 ; To simulate the distribution grid in different regions and at different development stages, the load density is 0.1MW / km. 2 、0.5MW / km 2 、1MW / km 2 、5MW / km 2 、10MW / km 2 、20MW / km 2 、30MW / km 2 、40MW / km 2 、50MW / km 2 Nine levels to consider.
[0022] Establishing the topological structure of the distribution network means obtaining the number of nodes of various grid structures in the distribution network. The grid structures include overhead network radial type, overhead network multi-segment single connection type, overhead network multi-segment multi-connection type, cable network single-shot type, cable network double-shot type, cable network opposite-shot type, cable network single-ring type, cable network double-ring type and cable network N-supply-one-standby type. According to the load rate, the node coefficient corresponding to each grid structure is determined. According to the line length and the node coefficient, the number of nodes of each grid structure in the distribution network is determined. According to the load rate of the distribution network and the correlation between various grid structures in the distribution network, the node coefficient corresponding to each network structure at different load rates can be set in advance in the distribution network. The node coefficient is the number of various grid structures in the unit length of the line. Then, by calculating the node coefficient and the line length of the line, the number of nodes of various grid structures in the distribution network is obtained.
[0023] When calculating the stability grade index, the weight values corresponding to various grid structures are first determined based on the failure rate and repair time. The weight values can be obtained using the CRITIC weight method, hierarchical analysis method, subjective experience method, Delphi method, etc., and then the weight values corresponding to various grid structures are multiplied by the number of grid nodes corresponding to various grid structures. The product value is used as the calculated value of the grid structure, and then the number of grid nodes corresponding to various grid structures is multiplied by the calculated value corresponding to various grid structures to obtain the sub-stability grade index corresponding to various grid structures. Finally, the sub-stability registration indices corresponding to various grid structures are added to obtain the stability grade index of the total distribution network.
[0024] The optimization module includes prediction unit, equipment unit, energy control unit and prevention unit; The prediction unit is used for data-driven load prediction and optimization. By analyzing and modeling historical data, it can accurately predict future load changes, thereby rationally configuring equipment capacity and improving the stability and economy of the distribution network. The equipment unit is based on the optimization and upgrading of equipment with advanced technology, using advanced switchgear, sensors and automation technology to improve the operating efficiency and reliability of the distribution network and reduce energy loss; The energy control unit is responsible for multi-energy integration and intelligent scheduling, introducing renewable energy and energy storage technology, and realizing the coordinated operation of different energy sources through intelligent scheduling algorithms, thereby improving energy utilization efficiency and reducing environmental impact; The prevention unit is used to deal with and resolve abnormal situations faced by the distribution network. Through robust design to deal with disasters and faults, reliability engineering methods are adopted, and backup plans and self-healing control strategies are used to improve the distribution network's disaster resistance and recovery speed and ensure power supply stability. These directions together constitute the comprehensive research content of the distribution network grid scheme optimization.
[0025] Before modeling, a large amount of historical data, real-time monitoring data and other relevant data are collected from the power system, including load data from the past few years or longer periods of time, as well as meteorological data, holiday data, economic indicators, etc. related to the period. These data will be used as training data to establish a load forecasting model, and then the obtained data will be cleaned and processed. Cleaning and processing the data includes removing abnormal data, processing missing values, and extracting features. The data cleaning and processing formula is: X'(t) = g(X(t)), where X(t) represents the original input feature vector, X'(t) represents the new feature vector obtained after cleaning and processing, and g represents the data cleaning and processing function; by cleaning and processing the data, a more accurate and consistent data set can be obtained, thereby improving the performance and accuracy of the load forecasting model. Then select the appropriate artificial intelligence algorithm, such as neural network, genetic algorithm, deep learning, etc., build a load forecasting model according to the training data, and finally use the test data to evaluate the accuracy and predictive ability of the model; by analyzing and modeling historical data, an accurate and reliable load forecasting model is obtained. Specifically, the time series method or artificial neural network method is used for load forecasting modeling. When the time series method is used: based on the idea of time series analysis, ARIMA, SARIMA or VAR model is used to predict future load values; when the artificial neural network method is used: simulate the working principle of human brain neurons, and use the interconnection between multiple neurons to construct a computational model to achieve load forecasting. The neural network used is BP neural network, RBF neural network or LSTM neural network.
[0026] The present invention is provided with an evaluation module to promote and improve the production technology and management of the electric power industry, and to provide a scientific basis for the planning and transformation of the distribution network, thereby realizing the planning, design and construction of new systems, or the expansion, transformation and development of the power supply capacity of the existing distribution network based on the existing operating status of the distribution network; and an optimization module is provided to predict the load of the distribution network as a whole, and take corresponding measures to improve the practical capacity and effect of the distribution network.
[0027] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.
Claims
1. A digital operation and maintenance system for a distribution network, characterized in that: It includes a CPU module, a main control module, a storage module, an evaluation module and an optimization module. The CPU module is bidirectionally connected with the main control module, the storage module, the evaluation module and the optimization module. The main control module is used for the operator to log in to the account to operate the system. The storage module is used to store information data obtained by the system. The evaluation module is used to evaluate the stability of the distribution network. The optimization module is used to optimize the distribution network.
2. A distribution network digital operation and maintenance system according to claim 1, characterized in that: The evaluation module includes a data acquisition unit, a confirmation unit and a calculation unit; The data acquisition unit is used to collect distribution network data, wherein the data includes the load density of the distribution network, the total capacity parameters of the substations in the distribution network and the load rate that need to be acquired; The confirmation unit establishes a topological structure of the distribution network according to the load density of the distribution network, the total capacity parameters of the substations in the distribution network and the load rate acquired by the data acquisition unit; The calculation unit calculates the stability level index of the distribution network based on the topological structure established by the confirmation unit and the pre-set stability parameters corresponding to various grid structures, the stability parameters including the failure rate and repair time corresponding to the load rate, and the number of nodes and stability parameters of various grid structures.
3. A distribution network digital operation and maintenance system according to claim 2, characterized in that: Before establishing the topological structure of the distribution network, it is necessary to obtain an analysis model of the proportional relationship between the line length, total capacity parameters, load density and load rate of the distribution network line, and then determine the topological structure of the distribution network based on the analysis model and the load rate; The analytical model includes determining the number of substations Y 变 , determine the number of lines Y in the distribution network 线 , determine the power supply radius R of the line and determine the line length L of the line; Y 变 = ,in is the load density, is the substation capacity, is the load factor; Y 线 = ,in is the total capacity parameter, Economic transmission capacity for distribution network lines; The distribution network is a power supply mode with the substation as the center and divided into zones and sections. The power supply area is approximately circular, so the power supply radius R of the distribution line can be calculated. ; The tortuosity coefficient of the distribution network is set to 1.414 in advance, so L=1.414RY 线 ; To simulate the distribution grid in different regions and at different development stages, the load density is 0.1MW / km. 2 、0.5MW / km 2 、1MW / km 2 、5MW / km 2 、10MW / km 2 、20MW / km 2 、30MW / km 2 、40MW / km 2 、50MW / km 2 Nine levels to consider.
4. A distribution network digital operation and maintenance system according to claim 2, characterized in that: The establishment of the topological structure of the distribution network is to obtain the number of nodes of various grid structures in the distribution network, and the grid structures include overhead network radial type, overhead network multi-segment single connection type, overhead network multi-segment multi-connection type, cable network single-shot type, cable network double-shot type, cable network opposite-shot type, cable network single-ring type, cable network double-ring type and cable network N-supply-one-standby type. According to the load rate, the node coefficient corresponding to each grid structure is determined, and according to the line length and the node coefficient, the number of nodes of each grid structure in the distribution network is determined.
5. A digital operation and maintenance system for a power distribution network according to claim 2, characterized in that: When calculating the stability grade index, the weight values corresponding to various grid structures are first determined based on the failure rate and the repair time, and then the weight values corresponding to the various grid structures are multiplied by the number of grid nodes corresponding to the various grid structures, and the product value is used as the calculated value of the grid structure. Then, the number of grid nodes corresponding to the various grid structures is multiplied by the calculated value corresponding to the various grid structures to obtain the sub-stability grade index corresponding to the various grid structures. Finally, the sub-stability registration indices corresponding to the various grid structures are added to obtain the stability grade index of the total distribution network.
6. A distribution network digital operation and maintenance system according to claim 1, characterized in that: The optimization module includes a prediction unit, an equipment unit, an energy control unit and a prevention unit; The prediction unit is used for data-driven load prediction and optimization. By analyzing and modeling historical data, accurate prediction of future load changes can be achieved, thereby rationally allocating equipment capacity and improving the stability and economy of the distribution network. The equipment unit is an equipment optimization and upgrade based on advanced technology, using advanced switchgear, sensors and automation technology to improve the operating efficiency and reliability of the distribution network and reduce energy loss; The energy control unit is responsible for multi-energy integration and intelligent scheduling, introduces renewable energy and energy storage technology, and realizes the coordinated operation of different energy sources through intelligent scheduling algorithms, thereby improving energy utilization efficiency and reducing environmental impact; The prevention unit is used to handle and solve the abnormal situations faced by the distribution network. Through the robust design for dealing with disasters and failures, the reliability engineering method is adopted, and the backup plan and self-healing control strategy are used to improve the disaster resistance and recovery speed of the distribution network and ensure the stability of power supply. These directions together constitute the comprehensive research content of the optimization of the distribution network grid scheme.
7. A digital operation and maintenance system for a power distribution network according to claim 6, characterized in that: Before the modeling is performed, a large amount of historical data, real-time monitoring data and other relevant data are first collected from the power system. These data will be used as training data to establish a load forecasting model, and then the obtained data is cleaned and processed. Cleaning and processing the data include removing abnormal data, processing missing values and extracting features. By cleaning and processing the data, a more accurate and consistent data set can be obtained, thereby improving the performance and accuracy of the load forecasting model. Then, an appropriate artificial intelligence algorithm is selected, such as a neural network, a genetic algorithm, a deep learning algorithm, etc., and a load forecasting model is established according to the training data. Finally, the test data is used to evaluate the accuracy and prediction ability of the model; an accurate and reliable load forecasting model is obtained by analyzing and modeling the historical data. Specifically, a time series method or an artificial neural network method is used for load forecasting modeling. When the time series method is used: based on the idea of time series analysis, ARIMA, SARIMA or VAR models are used to predict future load values; when the artificial neural network method is used: the working principle of human brain neurons is simulated, and a calculation model is constructed by connecting multiple neurons to each other, thereby realizing load forecasting. The neural network used is a BP neural network, an RBF neural network or an LSTM neural network.