PROJECT TITLE :

Spatial-Temporal Inventory Rebalancing for Bike Sharing Systems With Worker Recruitment

ABSTRACT:

In most cases, bike-sharing systems experience outages because of an inadequate number of bikes or an excessive number of bikes. We have a proposition to hire staff members in order to rebalance the station loads. We tackle the difficult problem of rebalancing by breaking it down into temporal and spatial domains. The temporal domain is cut up into a number of slices, each of which has a predetermined amount of time. Within each slice, we assign an overflow station and an underflow station to a worker in such a way as to minimize the cost, which is an NP-hard problem. The author suggests using a three-approximation algorithm. We continue our research into the worker shortage case and modify the matching algorithm to take into account the total number of users who remain dissatisfied. The configuration dynamic in the sequence of slices is then captured by determining the rebalancing target for each rebalancing operation. This process is repeated until the configuration dynamic has been fully captured. We investigate heuristic approaches with the goal of reducing the overall number of bike maneuvers as much as possible. In addition to this, we apply Clustering methodologies in order to extend our scheme to dockless BSSs. Our algorithms are tested through simulation using both real-world and simulated datasets. The findings of the experiments indicate that our strategies have the potential to cut down on the typical total detour taken by each slice. When there is a shortage of workers, taking into account the number of users who are dissatisfied may improve the long-term performance of rebalancing. In addition, we discover that our strategy is able to keep worker satisfaction over multiple time slices, which demonstrates that our rebalancing strategy can be maintained for the long term.