Pso Based Neuro-fuzzy Controller for Lfc Design including Communication Time Delays

The Proportional Integral Derivative (PID) controller is the most adopted controllers for industrial plants, due to its simplicity and satisfactory performances for a wide range of processes. It should be noted that the accurate and efficient tuning of parameters such controllers is very important. On the other hand, industrial plants, such as power systems, usually have some features, such as nonlinearity, time-variability of system structure and time delay, which make controller parameter tuning more complex. Thus, the optimal tuning of PID gains is required to get the desired level of robust performance under different operation conditions. This paper presents an Adaptive Network based Fuzzy Inference System (ANFIS) to tune on-line optimal gains of a PID controller for Load Frequency Control (LFC) design in a restructured time delay power system. The problem of robustly off-line tuning of PID based LFC design is formulated as an optimization problem according to the time domain-based objective function which is solved by Particle Swarm Optimization (PSO) technique that has a strong ability to find the most optimistic results. It is used to yield optimal PID gains over a wide range of plant parameter change and different system time-delays for training the proposed ANFIS in order to adopt the gains of the PID based load frequency controller. This newly developed control strategy combines the advantage of neural networks and fuzzy inference system and has simple stricture that is easy to implement and tune. To demonstrate the effectiveness of the proposed control strategy a two-area restructured power system is considered as a test system under different operating conditions and system nonlinearities. The simulation results show that the tuned gains of the PID based load frequency controller using the ANFIS can provide better damping of frequency oscillations.