论文部分内容阅读
电动出租车的示范运营对于电动汽车的推广具有引导意义,然而大规模电动出租车的接入将对电网运营和规划造成很大影响。为了研究区域内电动出租车运营的最优管理策略,引入多代理技术,采用了Q-Learning算法描述电动出租车的决策行为,利用JADE仿真工具建立了基于多代理技术的电动出租车运营实时仿真系统。通过实际应用分析表明,该系统通过主体之间以及主体与环境之间的交互,能有效地模拟电动出租车的动态行为及运营策略,为研究电动汽车规划、运营等问题提供参考。
The demonstration operation of electric taxis is instructive for the promotion of electric vehicles, however access to large-scale electric taxis will have a significant impact on grid operations and planning. In order to study the optimal management strategy of electric taxi operation in the region, multi-agent technology is introduced, Q-Learning algorithm is used to describe the decision-making behavior of electric taxi, and real-time simulation of electric taxi operation based on multi-agent technology is established by using JADE simulation tool system. The practical application shows that the system can effectively simulate the dynamic behavior and operational strategies of electric taxi through the interaction between the main body and the main body and the environment, so as to provide reference for the research on the planning and operation of electric vehicles.