PERFORMANCE ENHANCEMENT OF DYNAMIC VOLTAGE RESTORER USING ANFIS -BASED ADAPTIVE CONTROL STRATEGY

Abstract

Power quality disturbances such as voltage sag, swell, harmonics, and grid faults pose serious challenges to sensitive loads in modern distribution systems. Dynamic Voltage Restorers (DVRs) are widely used custom power devices for mitigating such disturbances by injecting compensating voltages in series with the distribution line. However, the performance of conventional proportional– integral (PI) and fixed-rule fuzzy controllers degrades under nonlinear load variations and severe grid disturbances. To overcome these limitations, this paper proposes an Adaptive Neuro -Fuzzy Inference System (ANFIS)–controlled DVR for effective voltage disturbance compensation and power quality enhancement. The proposed controller adaptively tunes control parameters by combining neural network learning capabilities with fuzzy logic reasoning. The DVR performance is evaluated under voltage sag, swell, harmonic distortion, and fault conditions. Simulation results demonstrate superior voltage regulation, fast dynamic response, and significant reduction in total harmonic distortion (THD) compared with conventional controllers, validating the effectiveness of the proposed ANFIS -based DVR