Logistical Planning for Electric Vehicles Under Time-Dependent Stochastic Traffic

作     者：Bi, Xiaowen Tang, Wallace K. S. 

作者机构：City Univ Hong Kong Dept Elect Engn Kowloon Hong Kong Peoples R China 

出 版 物：《IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS》 (IEEE智能运输系统汇刊)

年 卷 期：2019年第20卷第10期

页      面：3771-3781页

核心收录：

学科分类：0808[工学-电气工程] 08[工学] 0814[工学-土木工程] 0823[工学-交通运输工程] 

主　　题：Logistical planning electric vehicles (EVs) time-dependent stochastic traffic approximate dynamic programming 

摘      要：For the benefit of global environmental preservation, electric vehicles (EVs) have been gradually accepted by people in the past few years. However, the technical problem of limited drivable range and long charging duration is still a major hurdle for the popularization of EVs, especially for commercial usage. In this paper, a dynamic electric vehicle routing problem (D-EVRP) model is designed for planning the itinerary for goods delivery by the utilization of EVs in logistics industry. To reflect the real situation, the D-EVRP considers a time-dependent stochastic traffic condition and captures the discharging/charging pattern of an EV using an analytical battery model. Its aim is to minimize the overall service duration, subject to a variety of the state-of-art constraints common in EV routing problems. Furthermore, to address the D-EVRP, a hybrid rollout algorithm (HRA), which incorporates a dedicated pre-planning strategy and a rollout algorithm, is also proposed. The effectiveness of the HRA and benefits of incorporating the analytical battery model are justified by extensive simulations using the real-world D-EVRP instances.