AN EFFICIENT ANN-BASED CONTROL STRATEGY FOR REDUCED VOLTAGE SENSOR UPQC IN PV-INTEGRATED POWER SYSTEMS

Abstract

The increasing penetration of photovoltaic (PV) generation into distribution networks has introduced significant power quality challenges, including voltage fluctuations, harmonic distortion, reactive power demand, and load unbalance. Unified Power Quality Conditioners (UPQCs) have emerged as effective solutions for mitigating both current- and voltage-related disturbances in power systems. However, conventional UPQC control strategies require multiple voltage sensors, resulting in increased implementation cost, computational burden, and reduced system reliability. This paper proposes an efficient Artificial Neural Network (ANN)-based control strategy for a reduced voltage sensor UPQC integrated with photovoltaic systems. The proposed approach minimizes the number of voltage sensors required for UPQC operation while maintaining effective compensation capabilities. The ANN controller is employed to estimate reference compensation signals and regulate the series and shunt converters under varying operating conditions. The intelligent controller enhances system adaptability, improves dynamic response, and effectively mitigates harmonics, voltage sags, swells, and reactive power demands. Furthermore, the PV system contributes active power support to the distribution network through the common DC-link of the UPQC. MATLAB/Simulink simulation studies validate the proposed method under different grid disturbances and irradiance conditions. The results demonstrate significant improvements in power quality, reduced sensor dependency, lower total harmonic distortion (THD), and enhanced system reliability compared with conventional PI-based UPQC controllers.