Fons Vermeulen - Disruption Management at NS, Crew re-scheduling using Multi Agent System techniques

afstudeercolloquium

Disruption management is an important topic in railway management and control. The Dutch railways (NS) addresses this problem and stresses the importance of getting back to stable operations in as little time and costs as possible, especially in case of major incidents and disruptions. This research deals with a specific part of the problem, namely the planning of personnel on a newly generated train timetable. The current study employs Multi-Agent System (MAS) techniques, specifically Multiple Ant Colony Systems (MACS), to tackle the scheduling problem. Here it is shown that a MACS in itself is not enough to solve the scheduling problem, heuristics are necessary to reach solutions of acceptable quality. In a MACS multiple ant colonies cooperate to form a crew schedule for m employees. This translates to initializing a MACS with m ACSs, containing an equal number of ants r, thus giving us r solutions (each consisting of m employee schedules) at the end of each iteration. Here one solution will be a valid set of m employee schedules . The results of our system were generated with the aid of a dataset supplied by the NS and subsequently compared to their best solution. Moreover, the results were also compared to a purely random choosing of tasks and a greedy algorithm. The quality of the NS solution was not equalled, but our system performed far better than random and greedy algorithms.