CoordiQ : Coordinated Q-learning for Electric Vehicle Charging Recommendation
This addresses the challenge of optimizing EV charging recommendations to reduce waiting and driving times, with potential global savings of over 4 million person-hours annually, representing a strong domain-specific improvement.
The paper tackles the problem of efficiently routing electric vehicles to charging stations by developing a reinforcement learning model that improves user outcomes by over 30% compared to existing baselines in simulations.
Electric vehicles have been rapidly increasing in usage, but stations to charge them have not always kept up with demand, so efficient routing of vehicles to stations is critical to operating at maximum efficiency. Deciding which stations to recommend drivers to is a complex problem with a multitude of possible recommendations, volatile usage patterns and temporally extended consequences of recommendations. Reinforcement learning offers a powerful paradigm for solving sequential decision-making problems, but traditional methods may struggle with sample efficiency due to the high number of possible actions. By developing a model that allows complex representations of actions, we improve outcomes for users of our system by over 30% when compared to existing baselines in a simulation. If implemented widely, these better recommendations can globally save over 4 million person-hours of waiting and driving each year.