With the fast-growing demand in vehicle electrification nowadays, there still exist multiple critical challenges in using lithium-ion battery at large scale as the major power source, such as reliability issues, safety concerns, and especially the range anxiety. Thermal management plays a significant role in the life, performance, safety, and cost of the lithium-ion battery modules in electric vehicles (EVs). Battery thermal management systems (BTMS) aim to improve the temperature uniformity among all battery cells, and to prevent battery cells from very high temperature which may likely cause their explosion.
We have developed a model predictive control (MPC)-based energy management strategy to simultaneously control the BTMS, the air conditioning system, and the regenerative power of vehicles. A vehicle velocity forecasting framework is integrated with the MPC-based energy management to further improve the energy efficiency. Deep learning and image-based traffic light detection techniques have been leveraged for velocity forecasting. We have shown that the MPC-based energy management method could significantly improve the overall EV energy efficiency.
In addition, we are also exploring to leverage large-scale EVs connected to the grid to improve the resilience of the power grid under disruptive events, by providing grid services. For example, state of charge (SOC) and state of health (SOH) based charging/discharge profiles could be employed to forecast the EV capability for improving the grid reliability and resilience.
Battery thermal management, Vehicle-to-grid, Machine learning, Grid resilience