【海韵讲座】2017年第39期-Site Optimization and Inventory Rebalancing in Bike Sharing Systems
讲座题目: Site Optimization and Inventory Rebalancing in Bike Sharing Systems
主讲人: Dr. Chen, Rutgers Business School
Bike sharing systems aim at providing the missing links in the public transportation systems, and hence become increasingly popular in urban areas. A key to success for a bike sharing system is to balance the demand (bike pickup and drop-off requests) and supply (available bikes and docks). However, it is a challenging task, since the bike station demand is influenced by multiple factors of surrounding environment and complex transportation networks. To this end, we first develop an accurate forecasting model for predicting bike station demand, by extracting fine-grained discriminative features from human mobility data, point of interests (POI), and station network structures. Then, based on the learned patterns of station demand and balance, an optimization model is built to choose the optimal set of stations from a large number of candidates, such that the station usage is maximized and the number of unbalanced stations is minimized. Finally, given the chosen station designs, we optimize the effectiveness of station rebalancing operations, i.e., restoring the number of bikes in each station to its target inventory level, taking into account the available trucks and their capacities and time windows. To solve the large-scale rebalancing model, an Adaptive Capacity Constrained K-centers Clustering (AdaCCKC) algorithm is developed to effectively decompose the capacitated multi-vehicle routing problem into smaller subproblems. Real data from the New York City Citi Bike system was used in experimental tests, which verified the advantages of the proposed framework for optimizing bike sharing system designs and operations.
Dr. Chen is an Assistant Profession of Supply Chain Management in Rutgers Business School - Newark and New Brunswick, at Rutgers, The State University of New Jersey. His research interest lies in supply chain operations planning and scheduling, interface of supply chain operations and finance, and intermodal transportation. He also works on simulation and randomized global optimization methodologies, and uses business analytics in solving practical problems in smart grid and healthcare operations. His work has appeared in journals, books and patents, including Operations Research, Manufacturing & Service Operations Management, Interfaces, Automatica, IEEE Transactions on Automatic Control, IEEE Transactions on Smart Grid, etc. Dr. Chen received his Ph.D. degree in Industrial Engineering from the University of Wisconsin-Madison, and the M.S. and B.S. degree from Tsinghua University, Beijing, China. Prior to joining Rutgers Business School, he was a Scientist at GE Global Research, NY, solving various problems from GE businesses, collaborators and customers, such as GE Energy, GE Aviation, Lockheed Martin and electric utility companies.