Towards Accessible Shared Autonomous Electric Mobility With Dynamic Deadlines
Towards Accessible Shared Autonomous Electric Mobility With Dynamic Deadlines
复制标题
DOI：
10.1109/tmc.2022.3213125
复制
发表时间：
2024-01
影响因子：
7.9
通讯作者：
Guang Wang;Zhou Qin;Shuai Wang;Huijun Sun;Zheng Dong;Desheng Zhang
中科院分区：
文献类型：
--
作者：
Guang Wang;Zhou Qin;Shuai Wang;Huijun Sun;Zheng Dong;Desheng Zhang
近年来，共享自动驾驶电动汽车因其在节省能源消耗、提高出行可达性、减少空气污染、缓解交通拥堵等方面的潜力而引起了人们的广泛关注。虽然提供了便捷、低成本和环保的出行方式，但实现高效的共享自动驾驶电动汽车仍然存在一些障碍，例如如何及时实现共享自动驾驶电动汽车的可达性。为了克服这些障碍，在本文中，我们设计了 Safari，这是一种高效的共享自主电动汽车车队管理系统，具有基于动态期限的联合重新定位和充电功能，以提高用户体验和运营利润。我们的 Safari 不仅考虑了用户对车辆重新定位的高度动态需求（即重新定位到哪里），还考虑了许多实际因素，例如充电调度的时变充电定价（即在哪里充电）。为了有效地执行这两个任务，在 Safari 中，我们设计了一种基于动态截止日期的深度强化学习算法，该算法通过使用预测结合误差补偿机制来生成动态截止日期，以自适应地学习最佳决策，从而实时满足高度动态和不平衡的用户需求。更重要的是，我们用10个月的真实共享电动汽车数据来实现和评估Safari系统，大量的实验结果表明，我们的Safari实现了100%的可达性，并有效降低了26.2%的充电成本，减少了31.8%的车辆移动，从而节省了能源，同时运行时间开销很小。此外，研究结果还表明，Safari在其长期扩张和演进过程中，具有实现高效、可访问的共享自动驾驶电动出行的巨大潜力。
Shared autonomous electric mobility has attracted significant interest in recent years due to its potential to save energy consumption, enhance mobility accessibility, reduce air pollution, mitigate traffic congestion, etc. Although providing convenient, low-cost, and environmentally-friendly mobility, there are still some roadblocks to achieve efficient shared autonomous electric mobility, e.g., how to enable the accessibility of shared autonomous electric vehicles in time. To overcome these roadblocks, in this article, we design Safari, an efficient Shared Autonomous electric vehicle Fleet mAnagement system with joint Repositioning and chargIng based on dynamic deadlines to improve both user experience and operating profits. Our Safari considers not only the highly dynamic user demand for vehicle repositioning (i.e., where to relocate) but also many practical factors like the time-varying charging pricing for charging scheduling (i.e., where to charge). To perform the two tasks efficiently, in Safari, we design a dynamic deadline-based deep reinforcement learning algorithm, which generates dynamic deadlines via usage prediction combined with an error compensation mechanism to adaptively learn the optimal decisions for satisfying highly dynamic and unbalanced user demand in real time. More importantly, we implement and evaluate the Safari system with 10-month real-world shared electric vehicle data, and the extensive experimental results show that our Safari achieves 100% of accessibility and effectively reduces 26.2% of charging costs and reduces 31.8% of vehicle movements for energy saving with a small runtime overhead at the same time. Furthermore, the results also show Safari has a great potential to achieve efficient and accessible shared autonomous electric mobility during its long-term expansion and evolution process.