Dynamic Rebalancing Optimization for Bike-Sharing System Using Priority-Based MOEA/D Algorithm

As an indispensable part of public transportation systems, the bike-sharing system (BSS) can improve road resource utilization and alleviate traffic congestion, significantly improving urban mobility. The disproportion between demand supply creates a giant gap for maintaining smooth functioning system. To address issue, this paper proposes dynamic optimization rebalancing model docked which aims at minimizing operation cost while maximizing user satisfaction. is evaluated using both historical predicted data so that second time service each station could be avoided within horizon. A time-window based satisfaction modeling put forward to evaluate Multiobjective evolutionary algorithm on decomposition (MOEA/D) under rolling horizon strategy adopted solve model. algorithmic performance, local search priority applied. Numerical experiments real-world were implemented demonstrate proposed advantage improved algorithm. results indicate, outperforms nondominated sorting genetic II (NSGA-II) MOEA/D without priority-based search. Solutions with higher profit discovered help heuristic priority. experiment also revealed slight increase 7.02% (Yen29.2) in yield significant growth 1233.7% (Yen288.7) profit.