A novel hybrid architecture for MPPT of PV array under partial shading conditions

The continuous change in the environmental conditions has affected the solar panel output power. The ultimate goal is to keep calculated power close to actual maximum power, having minimal steady-state oscillations under continuous change in operating conditions such as irradiances and temperature. Therefore, this paper proposes a new hybrid technique based on an artificial neural network (ANN) and fractional-order PID (FOPID) controller. The sanitized teacher learning-based optimization algorithm is utilized for training the feed-forward ANN using the experimental data. Then, the water cycle algorithm is employed to tune the parameters of the FOPID controller. To examine the performance of the proposed technique, two different solar panels are taken for the study under various operating conditions, cloudy conditions, and partial shading conditions. The proposed technique is also tested for different array configurations of the solar panel. It is noticed that the proposed hybrid technique demonstrates better results in terms of various performance indices such as maximum power, efficiency recorded close to 99.99%, relative error recorded to be 0.000549, and minimum tracking speed recorded to be 0.059 s as compared to latest published work in the literature.