Real-time train driver rescheduling by actor-agent techniques

Passenger railway operations are based on an extensive planning process for generating the timetable, the rolling stock circulation, and the crew duties for train drivers and conductors. In particular, crew scheduling is a complex process. After the planning process has been completed, the plans are carried out in the real-time operations. Preferably, the plans are carried out as scheduled. However, in case of delays of trains or large disruptions of the railway system, the timetable, the rolling stock circulation and the crew duties may not be feasible anymore and must be rescheduled. This paper presents a method based on multi-agent techniques to solve the train driver rescheduling problem in case of a large disruption. It assumes that the timetable and the rolling stock have been rescheduled already based on an incident scenario. In the crew rescheduling model, each train driver is represented by a driver-agent. A driver-agent whose duty has become infeasible by the disruption starts a recursive task exchange process with the other driver-agents in order to solve this infeasibility. The task exchange process is supported by a route-analyzer-agent, which determines whether a proposed task exchange is feasible, conditionally feasible, or not feasible. The task exchange process is guided by several cost parameters, and the aim is to find a feasible set of duties at minimal total cost. The train driver rescheduling method was tested on several realistic disruption instances of Netherlands Railways (NS), the main operator of passenger trains in the E.J.W. Abbink ( ) · P.J. Fioole · L.G. Kroon Netherlands Railways, NSR Logistics Innovation, P.O. Box 2025, 3500 HA, Utrecht, Netherlands e-mail: [email protected] D.G.A. Mobach · E.H.T. van der Heijden · N.J.E. Wijngaards D-CIS Lab, Thales Research & Technology NL, P.O. Box 90, 2600 AB, Delft, Netherlands L.G. Kroon Rotterdam School of Management, Erasmus University Rotterdam, P.O. Box 1738, 3000 DR, Rotterdam, Netherlands 250 E.J.W. Abbink et al. Netherlands. In general the rescheduling method finds an appropriate set of rescheduled duties in a short amount of time. This research was carried out in close cooperation by NS and the D-CIS Lab. 1 NS train driver rescheduling The railway operations of Netherlands Railways (Nederlandse Spoorwegen or NS) are based on an extensive planning process, consisting of three phases: timetable planning, rolling stock scheduling, and crew scheduling. The crew scheduling process supplies each train with a train driver and with sufficient conductors. In the past years, NS has successfully applied novel Operations Research models to significantly improve the planning process for which NS received the Edelman Award 2008 of INFORMS, see Kroon et al. (2008). After the planning process, the daily plans are carried out in the real-time operations. Preferably, the plans are carried out exactly as scheduled. However, in the real-time operations, the plans have to be updated continuously in order to deal with delays of trains and larger disruptions of the railway system. A disruption may be due to an accident, or a breakdown of infrastructure or rolling stock. On the Dutch rail network (more than 5000 daily trains), on average 3 disruptions of a route occur per day. Delays occur even more frequently: On average 450 trains experience one or more delays (>3 minutes) per day. These delays lead to about 10 cancelled train services per day. The current methods and techniques are very useful for generating the initial daily schedules, yet their calculation time usually takes multiple hours, making them unfit for direct application in real-time rescheduling purposes. In this paper we focus on an actor-agent based approach for real-time rescheduling of train drivers. The crew scheduling process at NS is very complex, see Abbink et al. (2005). NS train drivers operate from 29 crew bases. Each day a driver carries out a number of tasks, which means that he/she operates a train on a trip from a certain start location and start time to a certain end location and end time. The trips of the trains are defined by the timetable. Train drivers can use positioning trips to travel to the starting location of driving tasks. In addition, stand-by tasks are defined and assigned to stand-by train drivers: these can be used to resolve rescheduling problems. The tasks of the train drivers have been organized in a number of duties, where each duty represents the consecutive tasks to be carried out by a single driver on a single day. Each duty starts in a crew base, and a hard constraint is that the duty ends at the same crew base within a limited period of time. Also several other constraints must be satisfied by the duties, such as the presence of a meal break at an appropriate time and location, and an average working time per crew base of at most 8 hours. Initially in the planning process, duties are anonymous, which means that the allocation of drivers to duties is still needed. The latter is handled by the creation of crew rosters, which describe the sequence of duties that are carried out by the individual drivers on consecutive days. The total number of train drivers is about 3000. Each day, about 1000 duties are carried out by the drivers. Furthermore, at any moment in time, the number of active duties at that moment is about 300. Due to cancellations and delays of trains or rescheduling of the rolling stock a number of duties of train drivers may become Real-time train driver rescheduling by actor-agent techniques 251 infeasible. An infeasibility of a duty is due to a time conflict (often caused by delays) and/or a location conflict (often caused by cancelled train services). In both cases, a conflict occurs between two consecutive tasks in the duty. Dispatchers are responsible for rescheduling tasks among train drivers so that the trains are staffed adequately. Dispatchers are organized into five regions, where they are responsible for rescheduling train drivers who currently reside in their region. Often dispatchers need to perform task-rescheduling actions, which they can handle given the available time and resources. Typically, about five minutes are spent to resolve a single inconsistent duty. Frequently, rescheduling problems are left ‘open ended’ for later resolution by other dispatchers (often in another region). In larger disruptions some trains simply cannot be driven as dispatchers are busy rescheduling train-drivers, causing additional delays for passengers. The main objectives of the train-driver rescheduling research system described in this result-oriented paper are to explore the effectiveness and suitability of a decentralized, actor-agent based approach to crew rescheduling. Another objective is to determine whether multi-agent technology is sufficiently mature to be used in a real-world decision support system. This paper is structured as follows. Section 2 describes the main actor-agent design paradigm and elements of the rescheduling system. Section 3 describes the implementation of the rescheduling research system, followed by a description of results in Sect. 4. This paper is concluded by a discussion and comparison with related work in Sect. 5.