Adaptive decentralized-coordinated neural control of hybrid wind-thermal power system

Hybrid wind-thermal power systems (HWTP) are widely used, and the scales of wind energy in such systems are growing rapidly. Classical decentralized coordinated controls of power systems are all based on synchronous generator (SG), which ignore wind farms. It is unsuitable that applying SG based decentralized coordinated control on a renewable power system. This paper presents an adaptive decentralized-coordinated neural control (ADNC) of hybrid wind-thermal power systems. Our method makes use of the interaction measurement modeling, multiple model linear optimal theory and artificial neural network (ANN) techniques. An ANN based dynamic weighting calculation is proposed to cope with the nonlinearity and continuous variations of the system operating points. Simulation results for an illustrative system are presented. The results show that the proposed method not only has an accurate tracking performance, but also enhances the transient stability of the system.