Advanced Deep learning-based Controller for Robust EV Speed Management

The significant increase in electric vehicle demand (EV) has highlighted the importance of environment-conscious and erudite architecture for speed control methods. The speed controller is an essential component of an EV for addressing issues such as managing battery energy and adjusting to driving conditions. Because the function of an EV system is time-variant due to parametric uncertainties and road conditions, regulating such mechanisms is a complicated task that traditional predetermined monitoring techniques cannot successfully achieve. To discuss the control issues associated with the EV, in this study advanced Deep Learning (DL) controllers are used to robustly manage the speed of the EVs. In this study, a threshold speed is given to two different controllers as Neural Network (NN) controller and the Adaptive Neuro-Fuzzy Inference System (ANFIS) controller and the performance of the controller is analyzed. For this process, a mathematical model of a complete EV is designed and the speed control is done in that particular model. Further, in order to determine the most efficient controller the error metrics such as ISE (Integral Square Error), IAE (Integral Absolute Error), and ITAE (Integral Time Absolute Error) values are calculated. Comparing the performance values and the error values of both the DL-based controllers, it is found that the ANFIS controller exhibits efficient performance and less error value compared to the NN controller.