AN ARTIFICIAL NEURAL NETWORK BASED ADAPTIVE POWER-SYSTEM STABILIZER

An artificial neural network (ANN) based power system stabilizer (PSS) and its application to power system are presented in this paper. The ANN based PSS combines the advantages of self-optimizing pole shifting adaptive control strategy and the quick response of ANN to introduce a new generation PSS. A popular type of ANN, the multi-layer perceptron with error back-propagation training method, is employed in this PSS. The ANN was trained by the training data group generated by the adaptive power system stabilizer (APSS). During the training, the ANN was required to memorize and simulate the control strategy of APSS until the differences are within the specified criteria. Results show that the proposed ANN based PSS can provide good damping of the power system over a wide operating range and significantly improve the dynamic performance of the system.