Comparison of Artificial Intelligence Methods for Load Frequency Control Problem

The Load Frequency Control (LFC) problem has been on of the major subjects in electric power system design/operation and is becoming much more significant today in accordance with increasing size, changing structure and complexity in interconnected power systems. Practice LFC systems use simple proportional-integral (PI) or integral (I) controllers. But the PI control parameters are usually tuned based on the classical or trial-and-error approaches and they are incapable to obtain good dynamic performance under various load conditions. For this problem, in this paper the artificial intelligence methods such as Genetic Algorithms (GA) and Fuzzy logic are proposed to tune the controllers for LFC problem in power system. A two-area power system example is considered as case study to illustrate the proposed methods. To show effectiveness of proposed methods and also comparing the performance of GA and Fuzzy controllers, several time domain simulations for various load changes scenarios are presented. Simulation results emphasis on the better performance of Fuzzy controllers than GA controllers in LFC problem