Advanced Sample-Based ANN MPPT for TCT Solar Panels in Partial Shading Environments

Due to their inherent potential and environmental benefits, renewable energy sources represent the most effective and sustainable alternatives for generating pollution-free energy in the contemporary era. Among these, solar energy stands out as a particularly promising option for supplying the essential power and energy needed to advance civilization. When the PV panel is shaded the output power will reduced. To overcome this issue MPPT is required. There are soft computing-based MPPT techniques available, but these are iterative-based. These are time-consuming but the ANN-based MPPT is fast to predict the global peak. In this paper a novel sample-based Artificial Neural Network (ANN) based MPPT method to optimize power extraction from Total Cross-Tied (TCT) configured photovoltaic panels under partial shading conditions. The proposed method along with TCT with different PSC. The proposed MPPT is compared with the Perturb & Observe (P&O), Incremental conductance (INC), Particle Swarm Optimization (PSO) and Cuckoo Search (CS). The proposed method is simulated with Matlab/Simulink software to examine the tracking time and efficiency. The proposed method is implemented using the DSP F28379D Launchpad micro controller (32-bit) and Chroma PV simulator. The result reveal that ANN MPPT is fast and better performance compare to other conventional methods.