Networked control system time-delay prediction method based on genetic algorithm optimized extreme learning machine

Abstract

The random time-delay of networked control system can cause system performance degradation, how to accurately predict time-delay is important. In order to improve the time-delay prediction accuracy, a time-delay prediction method based on genetic algorithm optimized extreme learning machine is proposed. Extreme learning machine has good predictive ability on nonlinear time series, it is used to predict the time-delay in this paper. But parameters of extreme learning machine have a great influence on the prediction accuracy. Genetic algorithm is introduced to solve parameters optimization problem of extreme learning machine. The optimal parameters of the prediction model are obtained through genetic algorithm. The simulation results show that the prediction accuracy and prediction error of the prediction method proposed in this paper is higher than the other prediction models.