Energy Management for Fuel-Cell-Range-Extender Buses Based on Dynamic Programming and Neural Network

Decarbonizing the traffic sector requires public transport to switch to alternative drive technologies. Despite the increasing spread of electric vehicles, there are still challenges in the electrification of public transport. These challenges are particularly pronounced for electrified 18m-buses. Due to the limited range of 18m-buses, they are not suitable as a direct replacement for their diesel equivalents, making scheduling difficult for bus operators. A promising approach to extending the range is the integration of an additional energy source on board. This approach is implemented in fuel cell range extender (FC-REX) buses. It combines a battery and a fuel cell power supply, whereby the energy is mainly provided by the battery. The power distribution of the two energy sources is controlled by an energy management system (EMS).This paper first proposes an offline Dynamic Programming (DP) approach to determine the optimal fuel cell load in the EMS using a simulation of an FC-REX bus. The aim of DP is to find out whether the energy efficiency can be improved and thus the range can be increased. To enable a real-time capable EMS without prior knowledge of the route, a neural network is subsequently investigated to approximate that optimal control strategy by training based on DP data. ... mehrThe control strategy is referred to as Neural Network based on Dynamic Programming (DP-NN). DP-NN is intended to combine the advantages of DP in finding the global optimum with the computationally efficient real-time control of neural networks. For evaluation purposes, DP and DP-NN are compared with a constant fuel cell power supply operating close to its most efficient load.