An advanced intelligent MPPT control strategy based on the imperialist competitive algorithm and artificial neural networks

The development of a robust optimization control technique, which can handle numerous nonlinear system problems, is one of the most challenging aspects of science production. In this study, hybrid intelligent Maximum Power Point Tracking (MPPT) control approach based on the Imperialist Competitive Algorithm (ICA), and an adaptive Artificial Neural Network (ANN) model is proposed to solve the efficiency optimization problem of Photovoltaic (PV) systems, which are considered as one of the most demanded source energy in the world. Consequently, a comparison between various metaheuristic algorithms based ANN including, Particle Swarm Optimization, Grey Wolf Optimization, and Whale Optimization Algorithm, is made for four distinct PV panel architectures to prove the effectiveness of the suggested approach in the optimization process based ICA technique, and in the training phase based three training algorithms namely, Bayesian Regularization (BR), Levenberg Marquardt (LM), and Scaled Conjugate Gradient (SCG). Accordingly, the obtained outcomes have proven that the ICA–ANN approach-based BR algorithm outperformed in three of four cases the other techniques by reaching an accuracy that can go up to 99.9994%. In the second part of this study, the evaluation of the obtained findings confirmed that our proposed model was able to track the Maximum Power Point (MPP) faster with a response time between 1.9 and 9.6 ms, and efficiency higher than 99.9652%, which is can up to 99.9984%, and it has shown excellent remarkable stability compared to the Perturb & Observe, Incremental Conductance, and the most applied metaheuristic-based MPPT techniques that we have used to conduct the optimization performance comparison.