MPPT Under Partial Shading Conditions Using Artificial Neural Network. Maximum Powerpoint Tracking; Radial Basis Function Neural Network; Boosted Salp Swarm Optimization

      Аннотация: This Book presents the deep radial basis function neural network learning-based MPPT for the PV module to obtain the maximum power. Moreover, the D-RBFN is trained using the proposed Boosted salp swarm optimization (BOSS) to reduce the tracking speed and improve efficiency. The BOSS optimization algorithm removes the local optima problem in the conventional salp swarm optimization algorithm by modifying the controlling parameter value, which is not only based on the maximum number of generations but also depends on the characteristics of the problem. The performance of the proposed BOSS-D-RBFN controller is analyzed under dynamic changing irradiance and two different cases of partial shading conditions. Also, the performance of the BOSS-D-RBFN method compared with state-of-the-art methods, including neural network-based MPPT, fuzzy logic-based MPPT, P&O-based MPPT, Incremental conductance, and evolutionary algorithm-based MPPT methods in terms of oscillation percentage, settling and tracking time, maximum power obtained, and efficiency.

Ключевые слова: maximum power point tracking, radial basis function neural network, Boosted Salp Swarm Optimization, Partial Shading Condition