ANFIS based Neuro-Fuzzy Control of DFIG for Wind Power Generation in Standalone Mode

Abstract

This paper presents an adaptive neuro-fuzzy controller (NFC) for doubly fed induction generator (DFIG) based wind energy conversion system (WECS) to operate under standalone mode. The NFC is developed based on adaptive-network-based fuzzy inference system (ANFIS) architecture since it has the unique advantage of fast convergence combining the robustness of fuzzy logic and flexibility of neural network algorithm. For the isolated operation of DFIG-WECS, ANFIS is designed for load side converter (LSC) control. The proposed scheme demonstrates improved dynamic performance under variable wind speed and load conditions by maintaining stable output voltage. The supply frequency to the load remains stable by virtue of precise control of LSC while turbine rotation varies with fluctuating wind speed. The flux alignment is ensured by the proportional-integral (PI) control of rotor side converter. The simulation results exhibit the controller's outstanding performance through its robust control over load-voltage and supply frequency under the variation of demand load power and wind speed.