The widespread use of electric vehicles (EVs) is restricted by limited battery capacity and unpredictable energy demands during trips, which leads to range anxiety—drivers’ concern about running out of charge before reaching their destinations. This work presents an energy-efficient Q-learning- based strategy (EEQ) for optimizing EV routing, with the
objective of minimizing total energy consumption over all journeys. Simulation results show that the proposed EEQ algorithm identifies routes where EVs consume as little as 2.61 kWh
with a total travel time of 3.8 h. In contrast, less energy-efficient routes can consume up to 4.58 kWh and require 6.5 h of travel time. These findings highlight the potential of the
EEQ algorithm to significantly improve energy efficiency in EV transportation networks. Considering energy minimization as the primary objective, the proposed strategy achieves a low convergence instability of about 3.85%, outperforming related methods.

Electric vehicle, range anxiety, Q-learning, EEQ, energy efficiency, route optimization.