Resources Relocation Support Strategy Based on a Modified Genetic Algorithm for Bike-Sharing Systems

In recent decades, special attention has been given to the adverse effects of traffic congestion. Bike-sharing systems, as a part of the broader category of shared transportation systems, are seen as viable solutions to these problems. Even if the quality of service in bike-sharing service systems were permanently improved, there would still be some issues that needed new and more efficient solutions. One of these refers to the rebalancing operations that follow the bike depletion phenomenon that affects most stations during shorter or longer time periods. Current work develops a two-step method to perform effective rebalancing operations in bike-sharing. The core elements of the method are a fuzzy logic-controlled genetic algorithm for bike station prioritization and an inference mechanism aiming to do the assignment between the stations and trucks. The solution was tested on traffic data collected from the Citi Bike New York bike-sharing system. The proposed method shows overall superior performance compared to other algorithms that are specific to capacitated vehicle routing problems: standard genetic algorithm, ant colony optimization, Tabu search algorithm, and improved performance compared to Harris Hawks optimization for some scenarios. Since the algorithm is independent of past traffic measurements, it applies to any other potential bike-sharing system.

Automated summary

In recent years, the adverse effects of traffic congestion have received special attention, and bike-sharing systems have been considered as viable solutions to these problems. However, even if the quality of bike-sharing service systems is improved, there are still challenges in terms of effective rebalancing operations. A two-step method is proposed to address these challenges, utilizing a fuzzy logic-controlled genetic algorithm for bike station prioritization and an inference mechanism for station-truck assignment. The proposed method shows superior performance compared to other algorithms and is applicable to any potential bike-sharing system.