Unified Power Flow Controller for PV Systems Using AI-Driven Power Quality Improvement Using Coupled Inductor Dual Boost Converter

Voltage stability, power flow regulation, and Power Quality have become major issues as a result of the increasing integration of renewable energy sources, especially photovoltaic (PV) systems, into power transmission networks. The main objective of this research is to improve the power quality (PQ) in power system utilizing Renewable Energy Sources (RESs), notably by eliminating the harmonic content in voltage and current that arise from power electronics interfaces. To address this, a Unified Power Flow Controller (UPFC), is proposed comprising both series and shunt converters interlinked with DC-link capacitor. In addition, a Photovoltaic (PV) system is integrated with a Coupled Inductor Dual Boost (CIDB) converter to ensure a stable and continuous energy supply. To accomplish these objectives, a Coyote Optimized Radial Basis Function Neural Network (COA-RBFNN) based Maximum Power Point Tracking (MPPT) is adopted for ensuring efficient energy extraction from PV system. Furthermore, a Decoupled Neural Network (DNN) based control technique is integrated to manage UPFC efficiently. The research is modelled and simulated in Matlab. The most important results of the study demonstrate a significant improvement in improving PQ, even under changing load conditions. Moreover, the converter ranks with improved efficiency of 88%, with improved voltage and current characteristics. The significance of the results is found in the ability to integrate renewable energy with contemporary power control technologies while guaranteeing dependable and high-quality power delivery.