GA-based support vector machines for adaptive power system damping controller of SMES

This paper proposes the application of support vector machines (SVMs) to design of an adaptive power system damping controller for superconducting magnetic energy storage (SMES). A genetic algorithm is used to optimize the SVM parameters based on k-fold cross-validation. The SVMs for SMES controllers are trained by the data obtained from a multi-machine power system, and the optimal SVM parameters. The SVMs can be adapted by various operating conditions when the power system operates either inside or outside of the training set. Simulation results in a two-area four-machine power system demonstrate that the proposed SVMs for adaptive SMES is much superior to the conventional SMES controller with fixed parameters under various operating conditions and severe disturbances.