A hybrid dynamic programming-rule based algorithm for real-time energy optimization of plug-in hybrid electric bus

The optimization of the control strategy of a plug-in hybrid electric bus (PHEB) for the repeatedly driven bus route is a key technique to improve the fuel economy. The widely used rule-based (RB) control strategy is lacking in the global optimization property, while the global optimization algorithms have an unacceptable computation complexity for real-time application. Therefore, a novel hybrid dynamic programming-rule based (DPRB) algorithm is brought forward to solve the global energy optimization problem in a real-time controller of PHEB. Firstly, a control grid is built up for a given typical city bus route, according to the station locations and discrete levels of battery state of charge (SOC). Moreover, the decision variables for the energy optimization at each point of the control grid might be deduced from an off-line dynamic programming (DP) with the historical running information of the driving cycle. Meanwhile, the genetic algorithm (GA) is adopted to replace the quantization process of DP permissible control set to reduce the computation burden. Secondly, with the optimized decision variables as control parameters according to the position and battery SOC of a PHEB, a RB control is used as an implementable controller for the energy management. Simulation results demonstrate that the proposed DPRB might distribute electric energy more reasonably throughout the bus route, compared with the optimized RB. The proposed hybrid algorithm might give a practicable solution, which is a tradeoff between the applicability of RB and the global optimization property of DP.