A learning and optimization framework for collaborative urban delivery problems with alliances

• Main Authors: YANG, Jingfeng, LAU, Hoong Chuin
• 格式: text
• 語言: English
• 出版: Institutional Knowledge at Singapore Management University 2021
• 主題: Alliances; Collaboration; Machine Learning; Pickup-and-delivery; Tabu Search; Artificial Intelligence and Robotics; Operations Research, Systems Engineering and Industrial Engineering
• 在線閱讀: https://ink.library.smu.edu.sg/sis_research/6231; https://ink.library.smu.edu.sg/context/sis_research/article/7234/viewcontent/ICCL_2021_Learning_and_Optimization_Framework_Alliance.pdf
• 機構: Singapore Management University

The emergence of e-Commerce imposes a tremendous strain on urban logistics which in turn raises concerns on environmental sustainability if not performed efficiently. While large logistics service providers (LSPs) can perform fulfillment sustainably as they operate extensive logistic networks, last-mile logistics are typically performed by small LSPs who need to form alliances to reduce delivery costs and improve efficiency, and to compete with large players. In this paper, we consider a multi-alliance multi-depot pickup and delivery problem with time windows (MAD-PDPTW) and formulate it as a mixed-integer programming (MIP) model. To cope with large-scale problem instances, we propose a two-stage approach of deciding how LSP requests are distributed to alliances, followed by vehicle routing within each alliance. For the former, we propose machine learning models to learn the values of delivery costs from past delivery data, which serve as a surrogate for deciding how requests are assigned. For the latter, we propose a tabu search heuristic. Experimental results on a standard dataset and a real case in Singapore show that our proposed learning-based optimization framework is efficient and effective in outperforming the direct use of tabu search in most instances. Using our approach, we demonstrate that substantial savings in costs and hence improvement in sustainability can be achieved when these LSPs form alliances and requests are optimally assigned to these alliances.