Method and system for correcting SVG control strategy based on BP neural network

Abstract

The invention relates to a method and a system for correcting an SVG control strategy based on a BP neural network. The method comprises the following steps: collecting active and reactive values of anew energy power station grid-connected point and active and reactive values of a new energy power station assessment point; training a BP neural network model by taking the active value and the reactive value of the new energy power station grid-connected point as input and taking the active value and the reactive value of the new energy power station assessment point as output; collecting the active real-time value and the reactive real-time value of the current grid-connected point, and calculating the active value and the reactive value of the assessment point through the final BP neuralnetwork model; and taking the obtained active value and reactive value of the assessment point as control parameters of SVG to realize optimization of reactive control and power factor control. According to the method and the system, the reasonable utilization rate of the SVG by the new energy power station can be improved, the off-grid reactive assessment rate of the new energy power station canbe reduced, and the method and the system are of great significance to safe, stable, economical and reliable operation of the new energy power station and the power grid.

Description

Technical field [0001] The present invention belongs to the field of new energy power station automation control technology. Aiming at the current inconsistent reactive power values ​​between the grid connection point and the assessment point of the new energy power station due to line loss, the Static Var Generator (SVG) uses the grid connection point reactive power as the control object The problem of under-adjustment is easy to occur, and a method based on BP neural network to modify SVG control strategy is proposed. Background technique [0002] With the rapid development of society, new energy power stations have been built on a large scale. Take Yunnan as an example. As of the end of 2019, the scale of photovoltaic power plants reached 3.5115 million kilowatts, the installed wind power capacity reached 8.204 million kilowatts, and there were hundreds of new energy power plants large and small. [0003] The new energy power station is connected to the power grid through a tie...

AI Technical Summary

Problems solved by technology

Usually, when a new energy power station uses SVG for reactive power adjustment, the value displayed on the check point's gate meter will often be too small, because the existence of line loss leads to react

Images