Robust Power System Stabilizer Design Using a Hybrid of ANN and ICA

The steady-state stability limit and the system positive damping can be improved by conventional Power System Stabilizer (PSS). However, in order to have abilities such as the online tuning and optimal real-time damping in the entire operating range, robust design of PSS in required. A novel robust PSS design using Artificial Neural Network (ANN) and Imperialist Competitive Algorithm (ICA) for damping electromechanical modes of oscillations and improving power system stability is proposed in this paper. The dynamics associated with a single machine connected to infinite bus power system is analyzed in this study. Optimal settings of PSS parameters are achieved by the means of hybrid ICA-ANN. ANN is used for online PSS parameters tuning. The results of ICA-based PSS (ICA-PSS) are used as training designs of ANN. Eigenvalue analysis and system simulations demonstrate the effectiveness of the proposed method in the damping of electromechanical oscillations and improving the system dynamic stability.