ANN based controller for SMES units in power systems

Abstract

A neural network based controller is designed for the Superconducting Magnetic Energy Storage Unit (SMES) to improve the transient stability of synchronous generators. The power modulation capability of the SMES is used to improve the dynamic performance of the system. The neural network is trained by learning linguistic rules. Normalized values of generator speed deviation and acceleration are used to train the network. The gain of the ANN controller is adapted on-line depending on the operating conditions. This allows the SMES unit to provide appropriate compensation required by the system following a disturbance. The control system is tested both for single and multi-machine systems. The simulation results show that the substantial improvement in stability is achieved when equipped with this type of control.