Application of Radial Basis Function Networks to Power System Load Frequency Control

摘要

An application of Artificial Neural Networks (ANN) to Load Frequency Control (LFC) of nonlinear power systems is presented in this paper. Power systems, such as other industrial processes, have parametric uncertainties that for controller design had to take the uncertainties into account. For this reason, to LFC controller design is being used of robust control theories and to improve stability of nonlinear system, in the various operating point and under different disturbances this controller has been reconstructed with the use of neural network capability based on Radial Basis Function (RBF). The motivation of using the robust control for training of the RBF neural networks controller is taking the large parametric uncertainties into account so that both stability of the overall system and good performance have been achieved for all admissible uncertainties. The variation bounds of power system parameters are obtained by changing parameters by 20% to 50% simultaneously from their typical values. Our simulation results on a single machine power system show that the proposed nonlinear neural controller can achieve good performance and stability of the overall system even in the presence of generation rate constraint (GRC).