CN112052620B

CN112052620B - Intelligent monitoring and analyzing system for urban distribution transformer area

Info

Publication number: CN112052620B
Application number: CN202010693955.5A
Authority: CN
Inventors: 胡伟; 王炜; 刘亚骏; 郭秋婷; 王伟恒; 刘宇
Original assignee: Tsinghua University; State Grid Corp of China SGCC; Shenyang Power Supply Co of State Grid Liaoning Electric Power Co Ltd
Current assignee: Tsinghua University; State Grid Corp of China SGCC; Shenyang Power Supply Co of State Grid Liaoning Electric Power Co Ltd
Priority date: 2020-07-17
Filing date: 2020-07-17
Publication date: 2023-02-28
Anticipated expiration: 2040-07-17
Also published as: CN112052620A

Abstract

The invention discloses an intelligent monitoring and analyzing system for an urban distribution transformer area, which comprises: the distribution area running state monitoring module is used for analyzing the running state of the urban power grid distribution area from multiple dimensions; the fault comprehensive information analysis module is used for analyzing fault information when the urban power grid distribution area has faults, summarizing and synthesizing the fault information after the urban power grid distribution area has faults, and analyzing the operating characteristics of the urban power grid distribution area so as to analyze the fault comprehensive information of the urban power grid distribution area; and the line loss analysis and intelligent diagnosis module is used for establishing a station area synchronous line loss index evaluation system according to synchronous line loss detection analysis and intelligent diagnosis of the urban power grid distribution station area so as to intelligently diagnose the operation of the urban power grid distribution station area. The system grasps the operation characteristics of the urban distribution network from the whole situation, and lays a foundation for guaranteeing the power supply reliability, reducing the peak-valley difference rate and the line loss rate of the power grid and realizing the intelligent monitoring of the urban distribution.

Description

Intelligent monitoring and analyzing system for urban distribution transformer area

Technical Field

The invention relates to the technical field of power distribution network management of a power system, in particular to an intelligent monitoring and analyzing system for an urban power distribution transformer area.

Background

With the rapid development of social economy and the continuous promotion of electric power reform, the electric power industry in China presents a good and fast development situation, the living standard of people is greatly improved obviously by the cross-over development, the change of the development mode, the improvement of the equipment level and the energy conservation and loss reduction, the requirement of people on the power supply quality is higher and higher, and the guarantee of the reliability and the economy of power supply of a power grid becomes one of important targets for the development of power supply enterprises. The urban power distribution network in China is large in scale and complex in structure, along with social and economic development and increased electricity load, the running state monitoring of the urban power distribution network distribution area is increasingly complex, risks such as heavy overload and voltage deviation are difficult to accurately control, and the problems of power failure and synchronous line loss of the distribution network area are increasingly prominent. The method has the advantages of reducing the fault power failure range, reducing the line loss of the power distribution network and ensuring the electric energy quality of the user side, and is the primary task of power supply enterprises.

Disclosure of Invention

The present invention is directed to solving, at least in part, one of the technical problems in the related art.

Therefore, the invention aims to provide an intelligent monitoring and analyzing system for an urban distribution network, which can master the operation characteristics of the urban distribution network from the whole situation and lay a foundation for guaranteeing the power supply reliability, reducing the peak-valley difference rate and the line loss rate of a power grid and realizing the intelligent monitoring of urban distribution.

In order to achieve the above object, an embodiment of the present invention provides an intelligent monitoring and analyzing system for an urban distribution area, including:

the system comprises a station running state monitoring module, a station monitoring module and a monitoring module, wherein the station running state monitoring module is used for monitoring running data of the urban power grid distribution station in a running state, carrying out running early warning and risk assessment according to the running data and analyzing the running state of the urban power grid distribution station from multiple dimensions;

the fault comprehensive information analysis module is used for analyzing fault information when the urban power grid distribution area has faults, summarizing and synthesizing the fault information after the urban power grid distribution area has faults, and analyzing the operating characteristics of the urban power grid distribution area so as to analyze the fault comprehensive information of the urban power grid distribution area;

and the line loss analysis and intelligent diagnosis module is used for establishing a station area synchronous line loss index evaluation system according to synchronous line loss detection analysis and intelligent diagnosis of the urban power grid distribution station area so as to intelligently diagnose the running of the urban power grid distribution station area.

According to the intelligent monitoring and analyzing system for the urban distribution transformer district, the technical advantages of Bootstrap and AJAX front-end frameworks are combined on the basis of the integration of a Spring Boot framework and a Spring + Spring MVC + MyBatis (SSM) framework, the technical advantages of Bootstrap and AJAX front-end frameworks are combined with a MySQL database, and a multilayer framework design idea based on a B/S structure is adopted, so that the development, configuration and deployment of the system are simple, and the maintainability and the fault tolerance of the system are greatly improved. The system comprises three functional modules of district operation state monitoring, fault comprehensive information analysis, line loss analysis and intelligent diagnosis, can master the operation characteristics of the urban distribution network district from the whole situation, and lays a foundation for guaranteeing the power supply reliability, reducing the peak-valley difference rate and the line loss rate of the power grid and realizing the intelligent monitoring of urban distribution.

In addition, the intelligent monitoring and analyzing system for the urban distribution substation according to the above embodiment of the present invention may further have the following additional technical features:

further, in an embodiment of the present invention, the operation data includes data of heavy overload, three-phase unbalance, low voltage and overvoltage in an operation state of the city power grid distribution station.

Further, in one embodiment of the present invention, the plurality of dimensions includes time, area, power unit, device type, and user composition.

Further, in an embodiment of the present invention, the establishing a distribution room synchronization line loss index evaluation system includes: establishing a line loss calculation model, determining a line loss fluctuation range, analyzing a comprehensive line loss rate of a transformer area, and screening the electricity stealing behavior of a user.

Further, in an embodiment of the present invention, the heavy overload data includes heavy overload prediction data, and the load condition of the urban power grid distribution area at a future time is predicted by using an ARIMA model in combination with a load-sharing innovation curve method according to historical data of the urban power grid distribution area, so as to obtain heavy overload prediction data.

Further, in an embodiment of the present invention, the fault comprehensive information analysis module is further configured to extract an independent component in the voltage time series data by using independent component analysis, characterize time series data characteristics by using static data, and perform clustering on the voltage time series data based on a K-means method to perform subscriber relationship identification.

Further, in an embodiment of the present invention, a region feature of the urban power grid distribution region is extracted through a convolutional neural network, and the line loss calculation model is obtained by training the region feature.

Additional aspects and advantages of the invention will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention.

Drawings

The foregoing and/or additional aspects and advantages of the present invention will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:

fig. 1 is a schematic structural diagram of an intelligent monitoring and analyzing system for urban distribution substations according to an embodiment of the present invention;

fig. 2 is a schematic structural diagram of an intelligent monitoring and analyzing system for an urban distribution substation according to an embodiment of the present invention.

Detailed Description

Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the drawings are illustrative and intended to be illustrative of the invention and are not to be construed as limiting the invention.

The following describes an intelligent monitoring and analyzing system for an urban distribution area according to an embodiment of the present invention with reference to the accompanying drawings.

Fig. 1 is a schematic structural diagram of an intelligent monitoring and analyzing system for an urban distribution substation according to an embodiment of the present invention.

As shown in fig. 1, the intelligent monitoring and analyzing system for urban distribution substations includes: the system comprises a transformer area running state monitoring module 100, a fault comprehensive information analysis module 200 and a line loss analysis and intelligent diagnosis module 300.

The station operation state monitoring module 100 is used for monitoring operation data of the urban power grid distribution station under the operation state, performing operation early warning and risk assessment according to the operation data, analyzing the urban power grid distribution station operation state from multiple dimensions, and improving the accurate control capability of a worker on the operation condition and the safety margin of the distribution network.

Further, the operation data comprises heavy overload data, three-phase unbalance data, low-voltage data and overvoltage data in the operation state of the urban power grid distribution area. The multiple dimensions include time, area, power supply unit, device type, and user composition.

Specifically, the conditions of heavy overload, three-phase imbalance, low voltage, overvoltage and the like in the running state of the urban power grid distribution area are analyzed, early warning and risk assessment are performed, and the running state of the power distribution network is analyzed from multiple dimensions such as time, area, power supply unit, equipment type and user composition.

It can be understood that the heavy overload data comprises heavy overload prediction data, and load conditions of the urban power grid distribution area at future time are predicted by adopting an ARIMA model in combination with a load-sharing innovation curve method according to historical data of the urban power grid distribution area, so that the heavy overload prediction data is obtained.

And the fault comprehensive information analysis module 200 is used for analyzing fault information when the urban power grid distribution area has faults, summarizing and synthesizing the fault information after the urban power grid distribution area has faults, and analyzing the operating characteristics of the urban power grid distribution area so as to analyze the fault comprehensive information of the urban power grid distribution area.

Specifically, the fault comprehensive information analysis module is used for researching the analysis of the power failure, the power restoration range and the number of households when the urban power grid distribution area has faults, the monitoring range of a user reaches more than 2000 households, the information after the urban power distribution area has faults is collected and synthesized, the operation characteristics of the power distribution network are analyzed, and the fault comprehensive information analysis of the urban power distribution area is realized.

Further, in an embodiment of the present invention, the fault comprehensive information analysis module is further configured to extract an independent component in the voltage time series data by using independent component analysis, characterize time series data characteristics by using static data, and perform clustering on the voltage time series data based on a K-means method to perform user relationship identification.

And the line loss analysis and intelligent diagnosis module 300 is used for establishing a station area synchronous line loss index evaluation system according to synchronous line loss detection analysis and intelligent diagnosis of the urban power grid distribution station area so as to intelligently diagnose the operation of the urban power grid distribution station area.

Specifically, the line loss analysis and intelligent diagnosis module establishes a line loss index evaluation system of the urban distribution network region through the research on the monitoring analysis and intelligent diagnosis of the urban distribution network region synchronous line loss, and comprises the steps of establishing a line loss calculation model, determining a reasonable line loss fluctuation range, analyzing the comprehensive line loss rate of the urban distribution network region, actively screening the electricity stealing behavior of a user and the like, so that the intelligent diagnosis of the operation of the urban distribution network region is realized, and a theoretical basis is laid for reducing the line loss rate of the distribution network and improving the electricity utilization economic benefit.

Specifically, the method comprises the steps of extracting the station area characteristics of the urban power grid distribution station area through a convolutional neural network, and training the station area characteristics to obtain a line loss calculation model.

Referring to fig. 2, the system is based on a Spring Boot framework, uses a Web browser as a software client, and the browser interacts with a back-end Web server through an http protocol to provide services for a user. The front end adopts the Bootstrap frame, echarts chart library and other technologies to show the station area user variation relationship and line loss condition. And the back end completes the interaction with the database by using a MyBatis framework, the database stores the information of each parameter by using a MySQL database, the model is solved by the calculation server, and the result is transmitted to the Web browser by the Web server after the calculation server interacts with the Web server.

The system comprises three functional modules of transformer area running state monitoring, fault comprehensive information analysis, line loss analysis and intelligent diagnosis.

The platform district running state monitoring module function includes: the method comprises the following steps of heavy overload condition overview, heavy overload prediction, overvoltage undervoltage condition monitoring, three-phase unbalance degree monitoring and risk assessment. The near-term operation condition of the transformer area can be monitored and analyzed, data are processed within 10 seconds, early warning information is issued, occurrence of high-risk events is predicted, and early warning is given.

The fault comprehensive information analysis module has the functions of: and identifying the user variation relationship and inquiring the fault range. The main flow of the user variable relationship identification is as follows:

(1) And carrying out data processing on the source data of the transformer area.

(2) And importing the processed platform area data to a MySQL database.

(3) Independent component analysis and feature extraction are carried out on the processed data by adopting the FastICA technology, and clustering analysis is carried out on the data after feature extraction by utilizing a K-means clustering method, so as to finally obtain the station area family change relation.

(4) And storing the platform area user change relation result into a database.

(5) The interface shows the user variation relationship.

When the user change relationship identification function is executed, the request flow of the Spring Boot framework is as follows:

(1) After the interface clicks the 'user variable relation recognition' button, the front end initiates a request.

(2) The Spring Boot will load the corresponding Controller to intercept. The Controller layer is the core of the identification and calculation of the user-variable relationship, and the code implementation comprises all functions of requesting data from a database, calculating, returning a result to a front end and the like.

(3) And after the interception processing, jumping to a corresponding Service processing layer.

(4) And then jumps to serviceinstance (service implementation class). The serviceimplementation realizes which database operations need to be performed specifically, such as querying data of platform region voltage, current and the like.

(5) And when the Service instance is executed, the Mapper layer is loaded to operate the database.

(6) And jumping to a Mapper layer implementation class, and enabling the Mapper to continuously find a corresponding Mapper.

(7) Then, the step 4 is skipped to continue the execution, and the result is returned to the step 2 after the execution is finished.

(8) And the Controller layer returns the data to the page in a JSON form and displays the data.

The line loss analysis and intelligent diagnosis module comprises the following functions: and establishing a line loss calculation model, displaying line loss conditions of the transformer area and screening electricity stealing behaviors. The main process for establishing the line loss calculation model comprises the following steps:

(1) And processing the data of the transformer area. The default values of voltage, current, power factor data are mainly filled and abnormal data are handled.

(2) And performing feature extraction on the platform area data based on the convolutional neural network.

(3) The data is divided into a training set and a test set. If the data of the first 11 months in the year is used as a training set, a line loss calculation model is trained, and then the data of 12 months is used for testing to evaluate the generalization capability of the model.

According to the urban distribution network area intelligent monitoring and analyzing system provided by the embodiment of the invention, the urban distribution network area operation characteristics are mastered globally by integrating the functions of monitoring the operation state of the distribution network area, analyzing fault comprehensive information, analyzing line loss, intelligently diagnosing and the like based on a big data technology, so that the urban distribution intelligent monitoring is realized. The front end of the system adopts an Echarts chart mode to provide various forms (charts, curves and the like) to display intelligent analysis results; the back end completes the interaction with the MySQL database by utilizing a MyBatis framework, and separates the service logic from the data access logic, so that the design of the system is clearer; through an IoC decoupling mechanism of a core SSM framework, the code reusability and maintainability are greatly improved.

Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present invention, "a plurality" means at least two, e.g., two, three, etc., unless specifically limited otherwise.

In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.

Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention, and that variations, modifications, substitutions and alterations can be made to the above embodiments by those of ordinary skill in the art within the scope of the present invention.

Claims

1. An intelligent monitoring and analysis system for urban distribution substations is characterized by comprising:

the system comprises a station running state monitoring module, a station monitoring module and a monitoring module, wherein the station running state monitoring module is used for monitoring running data of the urban power grid distribution station in a running state, carrying out running early warning and risk assessment according to the running data and analyzing the running state of the urban power grid distribution station from multiple dimensions; the operation data comprises heavy overload data, three-phase unbalance data, low-voltage data and overvoltage data in the operation state of the urban power grid distribution area; the multiple dimensions include time, area, power supply unit, device type, and user composition; the heavy overload data comprise heavy overload prediction data, and the load condition of the urban power grid distribution area at the future moment is predicted by adopting an ARIMA model in combination with an average load innovation curve method according to historical data of the urban power grid distribution area to obtain the heavy overload prediction data;

the fault comprehensive information analysis module is used for analyzing fault information when the urban power grid distribution area has faults, summarizing and synthesizing the fault information after the urban power grid distribution area has faults, and analyzing the operating characteristics of the urban power grid distribution area so as to analyze the fault comprehensive information of the urban power grid distribution area; the fault comprehensive information analysis module is also used for analyzing and extracting independent components in the voltage time sequence data by adopting the independent components, representing time sequence data characteristics by using static data, and clustering the voltage time sequence data based on a K-means method to identify the relationship of the platform users;

after clicking a 'user variable relation recognition' button, initiating a request through a front end;

loading a corresponding Controller for interception, wherein the Controller layer is a core for identifying and calculating the user-variable relationship and is used for requesting data from a database, calculating and returning a result to a front end;

after the interception processing, jumping to a corresponding Service processing layer;

jumping to the serviceinstance, wherein the serviceinstance is used for realizing which database operations are to be performed specifically; loading a Mapper layer when executing Service instance, and operating a database;

jumping to a Mapper layer implementation class, and enabling the Mapper to continuously find a corresponding Mapper.

Then, jumping to a Service processing layer for continuous execution, and returning a result to a Controller layer after the execution is finished;

the Controller layer returns the data to the page in a JSON form and displays the data;

the line loss analysis and intelligent diagnosis module is used for establishing a station area synchronous line loss index evaluation system according to synchronous line loss detection analysis and intelligent diagnosis of the urban power grid distribution station area so as to intelligently diagnose the operation of the urban power grid distribution station area; the method for establishing the stage area synchronization line loss index evaluation system comprises the following steps: the method comprises the steps of establishing a line loss calculation model, determining a line loss fluctuation range, analyzing a comprehensive line loss rate of a distribution area, screening a user electricity stealing behavior, extracting the distribution area characteristics of the urban power grid distribution area through a convolutional neural network, and training the distribution area characteristics to obtain the line loss calculation model.