AGC of a three area thermal system using MLPNN controller: A preliminary study

This paper deals with automatic generation control (AGC) of a three unequal area thermal system. The performance of a multilayer perception neural network (MLPNN) controller using reinforcement learning is evaluated. Bacterial foraging (BF) technique is used to simultaneously optimize the integral gains (K_Ii) and speed regulation parameter (R_i) keeping frequency bias fixed at frequency response characteristics. Investigations reveal that MLPNN controller with four numbers of hidden neurons (HN) provides better dynamic performance than any other numbers of HN for this system. The comparison of performances of Integral and MLPNN controller reveals that MLPNN controller gives better performance than Integral.