Energy saving and speed control in autonomous electric vehicle using enhanced manta ray foraging algorithm optimized intelligent systems

Abstract

The integration of autonomous vehicles (AVs) with hybrid electric vehicles (HEVs) aims to address the problem of optimizing energy economy while improving reliability and safety. By using intelligent driver support technologies and sophisticated control algorithms, this method aims to lower emissions and fuel consumption. Therefore, the HEVs develop an intelligent driver aid system that integrates an energy management system (EMS) with adaptive cruise control (ACC). To maximize energy use, the system integrates HEVs with autonomous vehicle technologies. In order to maintain safe distances from the lead vehicle, identify the desired acceleration, and switch between speed and distance control, the ACC uses a deep learning system in conjunction with a tilt integral derivative (TID) controller. This ensures stability. Based on ACC commands, the EMS controls energy usage. An enhanced manta ray foraging optimization (EMRFO) technique is used to significantly enhance speed control and energy economy. Simulink/MATLAB analysis of the suggested model shows notable gains in energy consumption control, particularly with the ACC with deep neural network (DNN) system, and considerable reductions in driving risks. In addition, the system precisely controls engine torque to maintain a 72.75 % State of Charge (SoC) and an average engine energy efficiency of 32.36 %. To validate the performance, the proposed approach is put into practice in real-time configuration. The configuration for the experiment produced an ideal efficiency of 31.99 % with minimal error using the proposed method.