2414. A dynamic optimization model for flexible modular buses in urban transit systems
Invited abstract in session MA-57: Public Transportation, stream Transportation.
Monday, 8:30-10:00Room: Liberty 1.12
Authors (first author is the speaker)
| 1. | Carlo Filippi
|
| Dept. of Economics and Management, University of Brescia | |
| 2. | Gianfranco Guastaroba
|
| Department of Economics and Management, University of Brescia | |
| 3. | Lorenzo Peirano
|
| University of Brescia | |
| 4. | M. Grazia Speranza
|
| Dept. of Quantitative Methods, University of Brescia |
Abstract
Urban transit systems usually operate according to fixed-route and fixed-schedule schemes by employing fixed-capacity vehicles, even though mobility demand is unevenly spread out in both space and time. Modular buses are an emerging technology in which modules of relatively small capacity can be dynamically docked together to form greater capacity buses and can therefore make the transit system capable of adapting the capacity to the actual mobility demand. A module can be shifted from one line to another at pre-defined intersections and can be relocated when empty, if beneficial. We call these two operations sharing and rebalancing, respectively.
We develop a dynamic, time-indexed optimization model to manage modular buses in a network of bus lines. In a given time horizon, e.g. the rush hours in the morning, transport demand is modelled as a set of origin-destination pairs located at the stops of the bus network, associated with a number of riders and a time of departure. The model establishes the flow of modules along the lines that allow satisfying the demand for transport using a minimum number of modules, leveraging module sharing and rebalancing, and can be used in a rolling-horizon fashion.
Preliminary computational experiments conducted within a Kernel Search framework demonstrate the practical solvability of the proposed model and highlight its advantages compared to a static model previously developed.
Keywords
- Transportation
- Optimization Modeling
- Metaheuristics
Status: accepted
Back to the list of papers