Research Of Train Energy-efficient Strategy Based On Improved Particle Swarm Optimization Algorithm

In urban transit system the problem of energy consumption is more and more important, reducing the energy consumption has become the goals of urban cities. Nowadays, the communication based train control system(CBTC) has been widely applied to urban rail transit automatic control system. The target speed curve is tracked by ATO system when operating in most of urban rail transit systems which could achieve a good effect in terms of punctuality, safety and energy-saving effect. Therefore, to study and obtain the energy-efficient speed target curve has become one of the most effective ways to reduce the energy consumption. In previous studies, people optimize the train control and train operation plan as two separate processes. However, in fact the train operation control program is optimized on the base of schedule time as they influence each other. So the purpose of this paper is to study and obtain an effective train energy-efficient bi-level optimization method which could reduce the energy consumption.In the running process, the modern automatic train control system (such as CBTC system) would produce and storage large numbers of traffic information, such as line conditions (slope, permanent speed limit), temporary speed limits, running time and so on. And at the same time, these traffic factors would also influence the train energy-efficient driving strategy. Therefore it is necessary to adopt an algorithm which could deal with large numbers of traffic constraint information and obtain the optimization results. The evolutionary algorithm is widely used with global high robustness and adaptability to a large range of optimization algorithms which could effectively solve complex optimization problems that the traditional optimization algorithms cannot deal with.This paper uses improved particle swarm optimization (IPSO) as the core algorithm to obtain the driving strategy which increases the search speed and search ability and reduces the occurrence of the premature phenomenon. Generally speaking, the energy-efficient operation technique includes two levels, which optimize driving strategy and timetable among successive stations, respectively. In this paper, we will continue to optimize the timetable after getting the energy-efficient driving strategy. The first optimization is to use IPSO algorithm to search for the best energy-efficient driving strategy. On the base of the former optimization, we will obtain energy curve of E-T of each running interval. After comparison with energy consumption of unit time of each interval, we should distribute the reserve time to each interval efficiently. This paper combines two energy-saving methods into a global energy-saving optimization which has a better energy-saving effect.This paper presents some numerical examples based on the operation data from the Beijing Yizhuang subway line. By comparing the results of the train operation,14.77%of energy would be saved in latter stage on the base of the energy-saving driving strategy that implies that the algorithm is energy-effective to be used in the automatic train operation system. And the results show a good effect of energy saving.