Dynamic Optimization for Smart Bike-Sharing: Demand-Driven Rebalancing
Bibliographic record
Abstract
Bike-sharing systems are an important mode of transportation allowing people to rent bikes for short trips and return them to any station across the city. However, the dynamic nature of user arrivals at bike-sharing stations often leads to imbalances between bike supply and demand, resulting in unsatisfied user requests and negatively impacting the overall popularity of bike-sharing systems. Additionally, a key opera- tional challenge is the efficient deployment and scheduling of rebalancing vehicles, as effective rebalancing policies can significantly reduce supply-demand mismatches and improve system cost-effectiveness. Another critical issue is the accurate prediction of bike pickup and drop-off demand at each station. Reliable demand forecasts enable operators to develop more robust and proactive rebalancing strategies. To address these challenges, this thesis introduces a dynamic rebalancing model that minimizes unsatisfied users by forming dynamic rebalancing groups and optimally allocating rebalancing vehicles based on demand fluctuations. The problem is formulated as a two-stage stochastic programming model. In the first stage, the model determines the optimal number of vehicles to deploy. In the second stage, stations are assigned to each rebalancing group based on their rebalancing needs, considering travel distance limits in each period. To address the computational challenge, we propose two approaches: the Integer L-shaped Decomposition based algorithms and a heuristic algorithm that helps the Integer L-shaped Decomposition to find the solution faster. Next, we develop machine learning-based prediction models to predict station-level bike pickup and drop-off demand, with a focus on the downtown Toronto case study. These models capture the time, weather, and temporal dependencies of station-level demand. Using the predicted demand rates, we run simulations and apply the pro- posed optimization models to determine the optimal rebalancing policy that minimizes the total cost of rebalancing and user dissatisfaction. The results demonstrate that the proposed rebalancing strategy reduces the total system cost compared to benchmark approaches. Moreover, our proposed heuristic algorithm decreases the model’s computational time by 51% relative to the Integer L-shaped decomposition method.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.001 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.004 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".