Robust maximum power point tracking in PV generation system: a hybrid ANN-backstepping approach with PSO-GA optimization

The growing diversity of consumer loads emphasizes the need for efficient operation of photovoltaic generation systems (PVGSs). This paper presents a novel control framework for maximum power point tracking (MPPT) in PVGSs, designed to enhance efficiency, robustness, and adaptability under dynamic environmental conditions. The proposed methodology integrates optimized Artificial Neural Network (ANN) with nonlinear backstepping controller. Hybrid particle swarm optimization (PSO) and genetic algorithm (GA) approach is used to optimize ANN, which leverages the global search capabilities of PSO and the local refinement strengths of GA to optimize the ANN's weights and biases, ensuring accurate prediction of the PV reference voltage that is critical for MPPT. Additionally, the nonlinear backstepping controller ensures system stability and precise tracking of the predicted reference voltage by recursively constructing Lyapunov functions to guarantee asymptotic stability. The effectiveness of this control framework is evaluated through MATLAB/Simulink and validated with hardware testing. It is observed from simulation and hardware testing results, compared to existing ANN and conventional techniques, the proposed approach yielded significant improvements by achieving root mean square error of 0.103%, tracking accuracy of 99. 8%, and reduction of power loss to 0. 2%. The proposed control framework significantly enhances MPPT robustness and efficiency in dynamic environments and enables higher integration of renewable energy. This advancement supports scalable, resilient PV systems critical for sustainable energy transitions.