Deployment Optimization for Shared e-Mobility Systems With Multi-Agent Deep Neural Search

• Published in: IEEE transactions on intelligent transportation systems 2022-03, Vol.23 (3), p.2549-2560
• Main Authors: Luo, Man, Du, Bowen, Klemmer, Konstantin, Zhu, Hongming, Wen, Hongkai
• Format: Article
• Language: English
• Subjects: Closed loops; Control systems design; Controllers; Data models; deep reinforcement learning; deployment optimization; electric vehicles; Multiagent systems; Optimization; Performance evaluation; Planning; Profitability; Public transportation; Reinforcement learning; Search problems; Shared mobility systems; Simulation; Systems analysis; Urban areas; Urban planning
• ISSN: 1524-9050; 1558-0016
• DOI: 10.1109/TITS.2021.3125745

Shared e-mobility services have been widely tested and piloted in cities across the globe, and already woven into the fabric of modern urban planning. This paper studies a practical yet important problem in those systems: how to deploy and manage their infrastructure across space and time, so that the services are ubiquitous to the users while sustainable in profitability. However, in real-world systems evaluating the performance of different deployment strategies and then finding the optimal plan is prohibitively expensive, as it is often infeasible to conduct many iterations of trial-and-error. We tackle this by designing a high-fidelity simulation environment, which abstracts the key operation details of the shared e-mobility systems at fine-granularity, and is calibrated using data collected from the real-world. This allows us to try out arbitrary deployment plans to learn the optimal given specific context, before actually implementing any in the real-world systems. In particular, we propose a novel multi-agent neural search approach, in which we design a hierarchical controller to produce tentative deployment plans. The generated deployment plans are then tested using a multi-simulation paradigm, i.e., evaluated in parallel, where the results are used to train the controller with deep reinforcement learning. With this closed loop, the controller can be steered to have higher probability of generating better deployment plans in future iterations. The proposed approach has been evaluated extensively in our simulation environment, and experimental results show that it outperforms baselines e.g., human knowledge, and state-of-the-art heuristic-based optimization approaches in both service coverage and net revenue.