Robust Multi-Objective Optimization for Bicycle Rebalancing in Shared Mobility Systems

2026-04-09

AI Summary

This study addresses the nighttime supply–demand imbalance in bike-sharing systems caused by demand uncertainty by proposing a tri-objective robust rebalancing optimization approach that simultaneously minimizes total vehicle travel distance, expected unmet demand, and robust unmet demand under high-demand scenarios. Building upon the NSGA-II framework, the authors design a multi-objective evolutionary algorithm incorporating a permutation-partition encoding scheme and a bias-based best-improvement migration operator. Solution feasibility is evaluated via a backtracking simulation mechanism that accounts for truck capacity and station inventory constraints. Experiments on the Bicing system in Barcelona, comprising 460 stations, demonstrate that the resulting Pareto front is well-distributed and closely approximates the reference front, significantly outperforming a greedy baseline method that yields only extreme solutions.

Abstract

Dock-based bike-sharing systems exhibit spatial imbalances between bicycle supply and user demand, often addressed through overnight truck-based rebalancing. This work studies static overnight rebalancing under demand uncertainty modeled as a tri-objective optimization problem. The objectives minimize total travel distance, expected unmet demand, and a robustness-oriented unmet demand measure over high-demand scenarios. Route plans are evaluated via a recourse simulation that enforces truck loads and station capacity constraints across multiple demand realizations. The robustness objective supports selecting plans that reduce peak-demand service degradation. Trade-off solutions are approximated with Non-dominated Sorting Genetic Algorithm II using a permutation--partition encoding and domain-specific relocation operators, including a biased best-improvement move for station relocation. Experiments on the real Barcelona Bicing system with 460 stations show well-distributed Pareto sets and substantial contributions to the reference non-dominated set. Greedy constructive baselines mainly yield extreme solutions and are often dominated.

Problem

• bicycle rebalancing
• shared mobility systems
• demand uncertainty
• multi-objective optimization
• robustness

Innovation

• robust multi-objective optimization
• bike-sharing rebalancing
• NSGA-II
• recourse simulation
• domain-specific operators