Solar photovoltaic converter controller using opposition-based reinforcement learning with butterfly optimization algorithm under partial shading conditions.

Abstract

The major use of a power point tracking controller is to maximize or enhance the power generation in photovoltaic systems. These systems are steered to operate and maximize the power point. Under partial shading conditions, the power points may vary or fluctuate between global maxima and local maxima. This fluctuation leads to a decrease in energy or energy loss. Hence, to address the fluctuation issue and its variations, a new hybridized maximum power point tracking technique based on an opposition-based reinforcement learning approach with a butterfly optimization algorithm has been proposed. The proposed methodology has been tested on 6S, 3S2P and 2S3P photo-voltaic configurations under different shading conditions. Performance comparison and analysis have been presented with a butterfly optimization algorithm, grey wolf optimization algorithm, whale optimization algorithm, and particle swarm optimization-based maximum power point tracking techniques. Experimental results show that the proposed method performs better adaptation than the conventional approaches and mitigates the load variation convergence and frequent exploration and exploitation patterns.