Transient Voltage Stability Assessment Method for the UHVDC Power Grid with High Proportion of New Energy Based on Artificial Intelligence

Abstract

UHVDC has developed rapidly in recent years, due to its large transmission power, large disturbances such as blocking and commutation failure will have a huge impact on the reactive power balance of the sending power grid, resulting in large-scale new energy off-grid. This paper establishes an improved BP neural network model based on an adaptive genetic algorithm for transient overvoltage evaluation, and takes a UHVDC sending power grid in northern China as an example to explore the nonlinear relationship between transient overvoltage and system operation state and verify the effectiveness of the method.