Publication Type

Conference Proceeding Article

Publication Date

7-2016

Abstract

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.

Keywords

Bike Sharing Systems, Robustness, Fictitious Play

Discipline

Artificial Intelligence and Robotics | Computer Sciences

Research Areas

Intelligent Systems and Decision Analytics

Publication

Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence

Publisher

AAAI Press

City or Country

Palo Alto, California USA

Copyright Owner and License

LARC

Creative Commons License

Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License.

Additional URL

1

Share

COinS