Naturalistic Data-Driven Predictive Energy Management for Plug-In Hybrid Electric Vehicles

A predictive energy management strategy considering travel route information is proposed to explore the energy-saving potential of plug-in hybrid electric vehicles. The extreme learning machine is used as a short-term speed predictor, and the battery temperature is added as an optimization term to the cost function. By comparing the training data sets, it is found that using the real-world historical speed information for training can achieve higher prediction accuracy than using typical standard driving cycles. The speed predictor trained based on the data considering travel route information can further improve the prediction accuracy. The impact of battery temperature on the total cost is also analyzed. By adjusting the temperature weighting coefficient of the battery, a balance between economy and battery aging can be achieved. In addition, it is found that the ambient temperature also affects vehicular energy consumption. Finally, the proposed method is compared with PMP, MPC, and CD-CS methods, showing its effectiveness and practicability.

Automated summary

The study proposed a predictive energy management strategy considering travel route information for exploring the energy-saving potential of plug-in hybrid electric vehicles. By training speed predictor based on real-world historical speed information, higher prediction accuracy was achieved. Moreover, adjusting battery temperature and ambient temperature can have significant impacts on total cost and energy consumption of vehicles.