Reducing Range Prediction Uncertainty in Heavy-Duty Electric Vehicles Using a Route-Informed Transformer-Based Model

Electrification of heavy-duty on-road trucks used for regional freight transportation is a viable option for fleets to reduce operation and maintenance costs and lower their carbon footprint. However, there is considerable uncertainty in projecting their daily range because highly variable payload mass, among other factors, confounds battery state of charge (SOC) prediction algorithms. Previous work by the authors proposed an electric vehicle range prediction model based on two parallel recurrent neural networks (RNNs). The first RNN used mean-variance estimation to output a predicted mean and variance, and the second used bounded interval estimation to provide bounds on the SOC required to complete a trip. The dual RNN approach resulted in estimating the remaining range and error bands of the SOC over the route. The previous work was limited because it did not incorporate driving conditions, like road type and ambient temperature, that affect driver behavior and energy consumption. This work includes embedding additional contextual information about the road network and environmental conditions to narrow the error bands, which leads to more accurate state-of-charge prediction. The road-aware RNN algorithm is trained and tested on time series data collected from electric heavy-duty trucks over 30 months. The proposed model shows that the bands of uncertainty in the prediction of the remaining range can be improved by 67% compared to the previous model, thereby increasing confidence in daily operation by lowering the likelihood of unexpected battery depletion. Further, interpretation of the analysis shows that the algorithm can adapt to route geometry and ambient conditions, giving fleet managers a more robust basis to plan charging schedules under daily route variability. As a result, this refined approach for contextual road-awareness accelerates the adoption of electric heavy-duty trucks by mitigating range anxiety and improving operational planning.