Parameter coordination optimization of power system stabilizer based on similarity index of power system state-BP neural network

Abstract

Power system stabilizer (PSS) is widely used to improve power system stability. The current parameter coordination optimization method is easy to fall into the local optimization, to solve the problem and find the optimal parameter combination of PSS, the sample screening method based on the similarity index of power system state (SIPSS) and BP neural network is proposed for global optimization parameters of PSS. The SIPSS screening method uses a similar metric index of the grid state variable as the criterion to screen out the required samples. The BP neural network fits the predicted and expected values of the minimum damping ratio of the system after random fluctuations of PSS parameters under various operating modes to minimize the mean square deviation by fitting the streamlined training samples. Firstly, the SIPSS-BP neural network model is obtained by analyzing the mapping relationship between generator power, node power, branch power, and minimum damping ratio. Then, the sensitivity of the PSS parameters damping ratio is calculated, and the PSS parameter optimization model is established. The optimal adjustment of the PSS parameter is obtained, and the minimum damping ratio is modified to improve the system’s stability. Finally, the minimum damping ratio after correction is obtained. The test results of the SIPSS-BP network with the IEEE 3-machines and 9-nodes show that the method can achieve good prediction accuracy, the parameter optimization effect of PSS can be remarkable, and the stability of the power system has been greatly improved.