ANN based reactive power control of an autonomous wind-diesel hybrid power plant using PMIG and SG

Abstract

This paper presents an artificial neural network (ANN) technique for tuning of the proportional and integral (PI) gains of the static synchronous compensator which is used as a reactive power compensator in a wind diesel hybrid power system. The gains are optimized for typical values of the load voltage characteristics (n <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">q</sub> ) by conventional techniques. The method of multilayer feed forward ANN with error back propagation training is used to tune the gains of the STATCOM controller. The ANN tune STATCOM controller gain which is implemented for the compensation of reactive power of the wind-diesel hybrid power system. The permanent-magnet induction generator is connected with wind energy conversion system and synchronous generator is coupled to diesel engine set to meet the load demand. The dynamic responses of the system for small (1%) step increase in load reactive power with and without 1% step increase in input wind power are shown.