Power system stabilization using a free-model based inverse dynamic neuro controller

Presents an implementation of a power system stabilizer using inverse dynamic neuro controller. Traditionally, a multilayer neural network is used for a universal approximator and applied to a system as a neuro-controller. In this case, at least two neural networks are required and continuous tuning of the neuro-controller is required. Moreover, training of the neural network is required considering all possible disturbances, which is impractical in real situation. In the paper, inverse dynamic neuro model (IDNM) is introduced to avoid this problem. The inverse dynamic neuro controller consists of the IDNM and the error reduction neuro model. Once the IDNM is trained, it does not require retuning for cases with other types of disturbances. The controller is tested for a one machine and infinite-bus power system for various operating conditions