In this paper, a Hippopotamus optimization Algorithm (HOA)-optimized Artificial Neural Network (ANN)-based Maximum Power Point Tracking (MPPT) method is proposed for a hybrid AC-DC microgrid powered by photovoltaic (PV) and wind energy systems. Hybrid AC-DC microgrids have emerged as a viable solution for integrating multiple renewable energy sources to ensure reliable and efficient power supply. However, the alternating nature of PV and wind power poses significant challenges in achieving optimal power generation. Traditional MPPT techniques often suffer from slow response, poor accuracy under partial shading and rapid weather changes, and increased complexity in hybrid systems. The proposed approach leverages the robust optimization capabilities of the HOA to train the ANN, ensuring fast and accurate MPPT under various environmental conditions. The ANN, optimized using HA, effectively learns and adapts to varying inputs, providing superior performance Simulation studies are conducted on a hybrid microgrid model in MATLAB/Simulink, analyzing the system’s performance under different irradiance and wind speed. The proposed HOA-optimized ANN MPPT achieves faster convergence and achieved efficiency of 97.86%. The superiority of the proposed approach in minimizing power loss and enhancing system reliability in hybrid AC-DC microgrids.