Transformer-Based Traffic-Aware Predictive Energy Management of a Fuel Cell Electric Vehicle

The energy economy of fuel cell electric vehicles (FCEVs) plays a crucial role in determining their practicality, making the optimization of energy management strategies (EMS) essential. Predictive EMS (PEMS) based on future vehicle speed prediction offers great potential for enhancing EMS performance. However, current PEMS prediction models rely on historical speed data or static traffic information, overlooking the impact of real-time traffic conditions. In this article, we introduce a Transformer-based PEMS (TPEMS) that incorporates real-time predicted surrounding traffic information to improve FCEV operational economy. To better predict vehicle speed by accounting for the complex interactions between the controlled vehicle and surrounding vehicles, we developed a Transformer network-based predictor, which considers the speed and relative distance of six vehicles surrounding the controlled vehicle, generating speed predictions for the next 10 s. We then employ the deep reinforcement learning (DRL) method as a downstream optimizer, creating a fully data-driven PEMS. For training the TPEMS, we developed a dataset derived from the NGSIM dataset, consisting of numerous driving profile segments that include temporal-sequential characteristics of the controlled vehicle and surrounding traffic. Furthermore, we utilize the SUMO simulator to generate a traffic information-enabled driving profile for performance evaluation. Experimental results reveal our Transformer-based predictor outperforms existing predictors, i.e., recurrent neural networks (RNN), in processing traffic information and achieving improved predictions. The TPEMS enhances the economic efficiency of FCEVs by 4.6% relative to the current state-of-the-art long short-term memory (LSTM)-based PEMS.