Reactive power control of autonomous wind-diesel hybrid power systems using ANN

This paper presents an artificial neural network (ANN) based approach to tune the parameters of the SVC reactive power controller over a wide range of typical load model parameters. The gains of PI (proportional integral) based reactive power controller are optimised for typical values of the load voltage characteristics by conventional techniques. Using the generated data, the method of multilayer feed-forward ANN with the error back-propagation training is employed. An ANN tuned static var compensator (SVC) controller has been applied to control the reactive power of variable slip/speed model of isolated wind-diesel hybrid power system. Transient responses of sample hybrid power system have also been presented.