Parameter Tuning of Statcom Using Particle Swarm Optimization Based Neural Network

Abstract

AbstractImprovement of voltage profile in modern power system is a challenging task due to its stressed operating conditions. Use of Flexible AC Transmission System (FACTS) devices like SVC and Stacom can be an economic solution to this problem. Statcom is a second generation FACTS device, which is basically voltage source converter that can be used in voltage control mode or reactive power injection mode. For stable operation and control of power systems it is essential to provide real time solution to the operator in energy control centers.In this paper, particle swarm optimization (PSO) is proposed for development of feed forward neural networks for estimation of the control and operating parameters of Statcom used for improving voltage profile in a power system. The PSO-ANN provides result with faster convergence speed and avoids the local minima problem.Two PSO based three-layered feed-forward neural networks are developed to estimate the control/ operating parameters of statcom used for improving voltage profile at various loading condition of power system. The effectiveness of the proposed method is demonstrated on IEEE 30-bus power system. The results obtained clearly indicate the superiority of the proposed approach for parameter tuning of Statcom.KeywordsStatcom voltage and its phase angleReactive power in the connected busReactive power in statcomVector Quantization clustering techniquePSO-ANN