A novel method of bayesian regularization based solar charging station employing maximum power point tracking for electric vehicle applications

Abstract

Any growing country's business development relies on the availability of electricity. Recent years have seen an increase in the development and marketing of electric vehicles (EVs) and hybrid electric cars due to environmental concerns and increasing oil costs (HEV). Electric vehicles are becoming more popular, and their accompanying equipment has become a necessary part of the equation. One module where this has been tried is the charging station. As part of the proposed work, ANN-based MPPT is utilized to monitor the solar panel's maximum power. This approach has the benefit of being more precise. ANN uses the Bayesian Regularization technique for maximum power point tracking. The neural network accustomed to manage the DC-DC converter's duty cycle is trained using this approach. Solar PV, energy storage, and the grid are all included in this electric car charging station. In case of an emergency, the PV and storage systems may draw electricity from the grid. The proposed method's efficiency is simulated and tested using the MATLAB/Simulink programme.

Energy Management Systems’ Modeling and Optimization in Hybrid Electric Vehicles

“…Bayesian regularization is a statistical approach and uses the principles of Bayes' theorem to optimize parameters by considering the estimation uncertainty along with the estimation of the weights and bias values [112]. It offers several advantages such as improved generalization ability, reduced overfitting, and faster convergence, and it also helps to reduce the effects of noise and uncertainty [113]. The SCG method uses an iterative approach to update the weights faster and more efficiently since it uses adaptive learning rate parameters [109,114,115].…”