Conference Proceeding Article
Bike Sharing Systems (BSSs) experience a significant loss incustomer demand due to starvation (empty base stations precluding bike pickup)or congestion (full base stations precluding bike return). Therefore, BSSsoperators reposition bikes between stations with the help of carrier vehicles. Dueto unpredictable and dynamically changing nature of the demand, myopicreasoning typically provides a below par performance. We propose an online androbust repositioning approach to minimise the loss in customer demand whileconsidering the possible uncertainty in future demand. Specifically, we developa scenario generation approach based on an iterative two player game to computea strategy of repositioning by assuming that the environment can generate aworse demand scenario (out of the feasible demand scenarios) against thecurrent repositioning solution. Extensive computational results from asimulation built on real world data set of bike sharing company demonstratethat our approach can significantly reduce the expected lost demand over theexisting benchmark approaches.
Bike Sharing Systems, Robustness, Fictitious Play
Artificial Intelligence and Robotics | Computer Sciences
Intelligent Systems and Decision Analytics
Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence
City or Country
Palo Alto, California USA
SUPRIYO GHOSH; TRICK, Michael; and Pradeep VARAKANTHAM.
Robust Repositioning to Counter Unpredictable Demand in Bike Sharing Systems. (2016). Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence. Research Collection School Of Information Systems.
Available at: http://ink.library.smu.edu.sg/sis_research/3456
Creative Commons License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License.