INTELLIGENT CONTROLLER DESIGN FOR AUTOMATIC GENERATION CONTROL

Abstract

The primary purpose of the AGC is to balance the total system generation against system load and losses so that the desired frequency and power interchange with neighboring systems is maintained. Any mismatch between generation and demand causes the system frequency to deviate from scheduled value. Thus high frequency deviation may lead to system collapse. This necessitates an accurate and fast acting controller to maintain constant nominal frequency. The intelligent controllers, viz. ANN have used for Automatic Generation Control for the single area system and higher area interconnected power systems. The limitations of the conventional controls viz., Proportional, Integral and Derivative (PID) are slow and lack of efficiency in handling system non-linearity. This dissertation work proposes an artificial neural network (ANN) based controller for multi-area Automatic Generation Control (AGC) scheme. In conventional AGC scheme two area• and four area system area considered. A conventional neural network (CNN) based controller is designed for two area and four area system. A three layer feed forward neural network (NN) is proposed for controller design and trained with Back propagation algorithm (BPA). For comparative study, the performance of system equipped with CNN controller is compared with system performance of system equipped with conventional PID controller tuned with Genetic Algorithm (GA). This dissertation work also proposes an artificial neural network (ANN) based controller for multi-area Automatic Generation Control (AGC) scheme in a deregulated electricity market. Both conventional neural network (CNN) and dynamic neural network (DNN) based controller has been proposed for designing ANN controller in deregulated electricity market. The ANN controller has been developed for multi-area system having Poolco, bilateral and mixed transactions. The functioning of the proposed controllers has been demonstrated on a two area 39-bus system and four area 75-bus Indian power system network. The result of the CNN, DNN, and GAPID controller are compared.