An Effective ANFIS Approach for Interconnected DFIG-Based Wind Energy System With Model-In-Loop Validation

Abstract

This study introduces an effective control strategy for interconnected doubly-fed induction generator-based wind energy systems with model-in-loop validation. Using an adaptive neuro-fuzzy inference system, the proposed controller employs an improved fuzzy rule set and membership function configuration. While existing ANFIS controllers typically use between 9 and 25 fuzzy rules for the grid side and rotor side converter in a doubly-fed induction generator-based wind energy system, this research extends to 49 rules with 7 associated membership functions and considering two inputs to the ANFIS controller for the grid as well as rotor side, resulting in higher precision and control performance Real-time simulations conducted on the OPAL RT OP5700 platform validate the controller’s effectiveness under varying wind conditions, specifically at 15 m/s and 10 m/s. Furthermore, dynamic and transient performances are thoroughly assessed in the presence of grid-side faults such as single-line-to-ground and three-phaseto-ground faults. A comparative analysis with traditional PI and fuzzy logic controllers reveals that the proposed ANFIS controller attains a 14% acceleration in fault recovery under LG and LLLG fault conditions. This result suggests that the proposed ANFIS controller performs better than its traditional counterparts. The enhanced ANFIS demonstrated robustness and adaptability, significantly improving resilience during variations in wind speed and fault tolerance in real-time wind energy systems.