A Real-Time Energy Consumption Minimization Framework for Electric Vehicles Routing Optimization Based on SARSA Reinforcement Learning

A real-time, metadata-driven electric vehicle routing optimization to reduce on-road energy requirements is proposed in this work. The strategy employs the state–action–reward–state–action (SARSA) algorithm learn EV’s maximum travel policy as an agent. As a function of received reward signal, model evaluates optimal behavior Markov chain models (MCMs) are used estimate agent’s on road, which single step represents average consumption based practical driving conditions, including patterns, road and restrictions that may apply. real-time simulation Python with TensorFlow, NumPy, Pandas library was run, considering real-life data for two EVs trips retrieved from Google’s API. started at 4.30 p.m. 11 October 2021, Los Angeles, California, Miami, Florida, reach EV charging stations six miles away starting locations. According results, AI-based minimization framework reduces requirement by 11.04% 5.72%, respectively. results yield lower compared suggested routes previous work reported literature using DDQN algorithm.