Adaptive Aquila Optimization Controlled Deep Convolutional Neural Network for Power Management in Supercapacitors/Battery of Electric Vehicles

Abstract

Electric Vehicles (EVs) may be a viable solution to reduce the huge energy consumption and greenhouse emissions of global transportation. However, the cost and range of batteries are two major obstacles for EV. An efficient Power management system for EVs, which includes Supercapacitor (SC) and battery with an optimized converter, is proposed in this paper. An optimal Direct Current (DC)-DC Bi-directional Buck-Boost Converter (BBBC) with a Proportional Integral Derivative (PID) controller is used for the optimal flow of power from the energy source to the drive during EV acceleration. The regenerative braking energy is allowed to return through the same bidirectional converter and retained in the Hybrid Energy Storage System (HESS) during the deceleration mode. A novel optimization is attained in the converter controller circuit using a Deep Convolution Neural Network (DCNN) and Adaptive Aquila Optimization Algorithm (AAqOA). The proposed strategy is validated using the results compared to conventional algorithms. In particular, the settling time of the suggested AAqOA model is 55.44%, 96.94%, 97.03%, and 91.87% better than the extant PI, DA, SSA, and AOA methods, respectively.