Reactive power compensation method of power network

Abstract

The invention provides a reactive power compensation method of a power network. The method comprises the steps of setting different types of line faults on an objective power network system model; setting corresponding reactive power compensation schemes for various line faults on the basis of the line faults; obtaining transient data before and after reactive power compensation separately by using a transient stability simulation program on the basis of the line faults and the reactive power compensation schemes; taking the transient data before and after reactive power compensation as input and output items separately, carrying out training by using a neural network and obtaining a trained reactive power compensation classifier; and combining new line fault information with various reactive power compensation schemes, carrying out grading by using the trained reactive power compensation classifier and obtaining the scheme with the highest score as an optimal scheme. The beneficial effects of accurately and quantitatively determining reactive power compensation places and total amount, reducing human intervention and greatly improving the stability and the security of the power network are achieved.

Description

technical field [0001] The present invention relates to the technical field of data grid control, and more specifically, to a reactive power compensation method for a grid. Background technique [0002] At present, the power grid is regarded as the most complex artificial system today, and people still cannot fully understand and master the operation rules of the power system. The traditional simulation modeling analysis makes a lot of assumptions and simplifications on the power system, which makes the simulated results deviate from the real system. With the development of distributed computing and machine learning, big data analysis has become an important means of understanding complex systems. Big data analysis regards the real system as a black box, and directly performs fitting and correlation analysis on the input and output. Compared with the traditional simulation analysis that needs to solve a large number of differential equations, the data-based machine learnin...

AI Technical Summary

Problems solved by technology

These two methods more or less have the characteristics of large amount of calculation, poor convergence and poor stability.

Therefore, in practical applications, the compensation mainly depends on the experience of the dispatcher, such as centralized compensation (unified compensation of the entire system) and decentralized compensation (local compensation next to the power load). The disadvantage is that it is relatively rough and cannot obtain optimal results.

Images