Grid operation KPI (key performance indicator) data self-learning method and system

Abstract

The invention relates to a grid operation KPI (key performance indicator) data self-learning method and system. Through the ETL (extract, transform and load) technology, collected grid operation data is subjected as required to data extraction, data transformation and washing to obtain grid operation KPI data; the washed grid operation KPI data is loaded to a grid operation KPI data warehouse; the data loaded to the grid operation KPI data warehouse is subjected to grid operation KPI data mining through a C4.5 algorithm; a KPI data correlation relationship is obtained through feature analysis, correlation analysis and clustering decision analysis; an accepted KPI data correlation relationship is obtained through trusted threshold filtering; after knowledge verification, a new grid operation KPI data mode is obtained and stored in a grid operation KPI experience and knowledge base. According to the method, knowledge expansion surely available and undiscovered by the traditional grid operation research theories, basis for enriching and improving specialized knowledge and capacities of grid operation personnel is provided, and fine management is achieved accordingly.

Description

technical field [0001] The invention relates to the technical field of electric power system intelligent dispatching, in particular to a method and a system for self-learning of power grid operation KPI data patterns. Background technique [0002] A large amount of data will be generated during the operation of the power network. Managing the operation data of the power grid, finding key information from these data, and mastering the operating status of the power system are of great significance for dispatchers to improve the decision-making efficiency of power generation adjustment. The key performance indicator KPI (Key Performance Indicator) shows the operation status of the power grid in a concentrated manner, and provides information on the safety, economy, quality and environmental protection of the power grid operation for the company's senior decision-makers and personnel in key positions in the power grid operation. The current power grid operation KPI data manageme...

AI Technical Summary

Problems solved by technology

[0004] The present invention aims at the problems of low power grid operation management efficiency and impossibility of refined management caused by the manual knowledge management of the existing power grid operation data and the fixed KPI data mode, and provides a self-learning method for the power grid operation KPI data mode, which can improve the power grid operation The data adopts ETL technology and power grid operation KPI data mining to obtain extended knowledge that is sure to be usable that has not been found in traditional power grid operation research theories, realizes self-learning of power grid operation KPI data models, and provides a basis for enriching and improving the professional knowledge and capabilities of power grid operators. In order to achieve refined management and improve the level of power grid operation and management

Images