Reducing EV range anxiety: How a simple AI model predicts port availability

Google Research · 7 months ago

A company developed a linear regression model to predict EV charging port availability at specific stations to help reduce range anxiety among electric vehicle drivers. The model was trained on real-time availability data from charging networks in California and Germany and achieved approximately 20% fewer wrong predictions during morning peak hours and 40% fewer during evening peak hours compared to a baseline approach. The lightweight model enables more accurate routing decisions and improved user experience by identifying periods of high occupancy turnover.