Modified Neural Network for Dynamic Control and Operation of a Hybrid Generation Systems

Abstract

This paper presents modified neural network for dynamic control and operation of a hybrid generation systems. PVand wind power are the primary power sources of the system to take full advantages of renewable energy, and thediesel-engine is used as a backup system. The simulation model of the hybrid system was developed using MATLABSimulink. To achieve a fast and stable response for the real power control, the intelligent controller consists of aRadial Basis Function Network (RBFN) and an modified Elman Neural Network (ENN) for maximum power pointtracking (MPPT). The pitch angle of wind turbine is controlled by ENN, and the PV system uses RBFN, where theoutput signal is used to control the DC / DC boost converters to achieve the MPPT. And the results show the hybridgeneration system can effectively extract the maximum power from the PV and wind energy sources.