CPS compliant fuzzy neural network load frequency control

Power systems are characterized by non-linearity and uncertainty. A neural network predictive fuzzy control is proposed for load frequency control. Recurrent neural network is employed to forecast controller and system´s future output, based on the current area control error (ACE) and the predicted change-of-ACE. The control performance standard (CPS) criterion is introduced into the fuzzy controller design, thus improves the dynamic quality of system. Simulations on a two-area power system that takes into account load disturbance demonstrate the effectiveness of the proposed methodologies.