Adaptive Power System Stabilizer Using Support Vector Machine

摘要

Power System Stabilizer (PSS) must be capable of providing appropriate stabilization signals over a broad range of operating conditions and disturbances. Traditional power system stabilizers rely on linear design methods. In the present paper, a novel approach for on-line adaptive tuning of Support Vector Machine based Power System Stabilizer (SVMPSS) parameters using and sigmoidal kernel is presented. The proposed SVMPSS is trained over a wide range of operating conditions. The simulation results of the proposed SVMPSS are compared to those of conventional stabilizers in for a Single Machine Infinite Bus (SMIB) system The effect of system parameter variations on the proposed stabilizer performance is also examined. The results show the Robustness of the proposed SVMPSS and its ability to enhance system damping over a wide range of operating conditions and system parameter variations.