Dynamic Relocation of Shared Bicycle Network for Resilient Transit Network in Disruptive Scenarios

This research presents a disruption-aware dynamic fleet deployment model (DFDM), which involves real-time detection and demand prediction component to support optimization-driven relocation strategy of micromobility resources during transit disruptions. The study investigates the role of shared micro-mobility, such as bicycles, in alleviating the impacts of unpredicted disruptions in public transit systems. The DFDM utilizes machine learning techniques such as CNN-LSTM for disruption detection and stacked LSTM for demand prediction. The system’s effectiveness is tested using a realistic disruption scenario in an example network. The framework optimizes fleet distribution through two cooperating optimization models, minimizing commuter delays and relocation costs. A simulation environment in MATLAB evaluates the performance of the DFDM under different conditions, with key performance indicators focusing on delay reduction, fleet efficiency, and resource repositioning costs. This research enhances urban transportation resilience by integrating micro-mobility into transit recovery strategies.