Power system load frequency control using RBF neural networks based on μ-synthesis theory

This paper describes a nonlinear Radial Basis Function Neural Networks (RBFNN) controller based on p synthesis technique to load frequency Control (LFC) of the power systems. Power systems such as other industrial plants have some uncertainties and deviations due to multivariable operating conditions and load variations that for controller design had to take the uncertainties into account. For this reason, in design of the proposed load frequency controller the idea of p synthesis theory is being used. The motivation of using the mu-based robust controller for training of the RBFNN controller is to take the large parametric uncertainties and modeling error into account. The proposed controller is effective and can guarantee the stability of overall system in the presence of plant parameter changes and system nonlineatities. The simulation results on a two-area power system show that the proposed RBFNN controller gives good dynamic responses and is superior to the conventional PI and mu-based robust controllers.