Hierarchical Energy Management Strategy of Hybrid Electric Truck Fleet under Connected Environment

Considering the slow-moving and energy-consuming issues that tend to occur when truck fleets drive, this paper proposes a hierarchical energy management strategy (EMS) for the hybrid electrical truck (HET) fleet, including speed planning and energy management. The speed threshold range that allows the whole fleet to pass through the traffic light is computed in the upper-layer speed planning. Within the model predictive control framework, a multi-objective optimization function is constructed for speed planning to find the optimum solution. In the lower-layer energy management, an offline model is established for power allocation between the Integrated Starter Generator and the Electric Motor and gear shift selection of automated manual transmission to reduce the dimensionality of the control variables. Then, an adaptive equivalent consumption minimum strategy (A-ECMS) is designed based on the fleet’s optimal speed provided. In the offline part, the transformation relationship between the co-state and equivalence factor is established based on Pontryagin’s minimum principle (PMP), and PMP obtains the globally optimal control sequence in the historical driving cycle to train a back-propagation neural network (BPNN). The BPNN model predicts the current optimal co-state in the online part, transformed into a real-time optimal equivalence factor to guide the A-ECMS online application. The simulation results indicate that the fuel economy of the proposed EMS is comparable to that of the global optimization method PMP and superior to that of Fixed EF-ECMS and PI-ECMS. Additionally, it enables the HET fleet to pass through traffic lights without stopping, thereby ensuring queue continuity and improving the passage efficiency of the fleet.