Enhancing power quality in grid-connected hybrid renewable energy sources using a fennec fox optimization-amplitude transformed quantum convolutional neural network with cascaded H-bridge multilevel inverter

The integration of Hybrid Renewable Energy Sources (HRESs), combining Photovoltaic (PV) and Wind Turbine (WT) systems, presents significant Power Quality (PQ) challenges in modern electrical grids. Grid connection of these systems often results in reliability concerns due to generation fluctuations and harmonic distortions introduced by power electronic converters. To address these issues, this manuscript proposes a novel hybrid approach—Fennec Fox Optimization-Amplitude Transformed Quantum Convolutional Neural Network (FFO-ATQCNN)—to enhance PQ in grid-connected HRESs employing a Cascaded H-Bridge Multilevel Inverter (CHBMLI). The FFO algorithm optimizes energy allocation and control parameters to reduce power losses and fluctuations, while the ATQCNN model predicts future power generation or demand, enabling proactive system control and improved PQ. The proposed technique aims to reduce Total Harmonic Distortion (THD), stabilize voltage levels, and maximize overall system performance. Implementation in MATLAB and comparative analysis with existing methods—including GA-PSO, NBO-RERNN, EO, IANN, CNN, MAO-RERNN, and SC-ANN—demonstrate the superior performance of the FFO-ATQCNN approach. The system achieves an efficiency of 98.6 % and reduces THD to 1.4 %, significantly enhancing PQ in grid-connected HRESs. This approach offers a reliable and intelligent solution for managing hybrid renewable energy systems, ensuring their stable and efficient operation in modern power networks.