|SCHETTINI TOMMASO||Cycle: XXXIII |
Section: Systems and Control
Tutor: PIRODDI LUIGI
Advisor: MALUCELLI FEDERICO Major Research topic
:Joint optimization and data-analysis approaches for the real-time management of automated transit lines.Abstract:
With the recent growth of urban populations, efficiently managing transit systems has become a top priority to local authorities. The widespread adoption of automated transit systems, coupled with the increased availability of passenger demand-related information opens several avenues of innovative management of transit systems.
In particular, from the control standpoint, automatic systems provide several advantages to the system and pose interesting new optimization challenges on how to fully harness their benefits. The lack of a driver completely removes the need for personnel scheduling and rostering, which has traditionally been a very complex and delicate aspect of operating transit services. Thus, automated systems are allowed far more freedom in their control strategies, making it possible to employ more flexible timetables, which furthermore can more easily be changed dynamically to accommodate for the needs of the line.
Possibilities which, if used correctly, can yield noticeable performance improvements for the end-user.
In the thesis, we will explore the implications of the additional degrees of freedom afforded by driverless systems. We explore the design of more efficient timetabling approaches, which will ultimately utilize passenger data to propose demand-driven schedules.
To this end we propose the following innovative goals:
- Introduce an alternative control paradigm for automated lines which explicitly account for the additional degrees of freedom introduced by driverless systems for the scheduling of metro lines.
- Propose models and algorithms to efficiently devise optimal timetables under the proposed paradigm.
- Employing machine learning methodologies for the estimation of passenger demand in transit networks.
- Combine the previously developed timetabling approaches with the demand estimation in the transit network into a unified approach, to obtain an efficient demand-driven and dynamic timetabling approach.
- Validating the models and algorithms using data obtained for the M5 line of Milan, and proposing alternative strategies for its management.