A matheuristic for the driver scheduling problem with staff cars

Shyam Sundar Govinda Raja Perumal, Jesper Larsen, Richard Martin Lusby, Morten Riis, Kasper Sørensen

    Research output: Contribution to conferenceConference abstract for conferenceResearchpeer-review

    191 Downloads (Pure)


    In the public bus transport industry, it is estimated that the cost of a driver schedule accounts for approximately 60% of a transport company’s operational expenses. Hence, it is important for transport companies to minimize the overall cost of driver schedules. A duty is defined as the work of a driver for a day and the driver scheduling problem (DSP) is concerned with finding an optimal set of driver duties to cover a set of timetabled bus trips. Numerous labor regulations and other practical conditions enforce drivers to travel within the city network to designated bus stops to start/end duty, to take a break or to takeover a bus from another driver. This paper focuses on the driver scheduling problem with staff cars (DSPSC), where staff cars can be utilized by the drivers to fulfill their travel activities. However, staff cars should always be returned to the depot and can perform multiple round trips during the day. The problem is restricted by the number of cars available at the depot. We present a matheuristic for solving the DSPSC and the proposed method is tested on instances from Danish and Swedish companies. A comparison with a state-of-the-art mixed integer programming (MIP) solver indicates that the matheuristic provides better solutions, with comparable computation times, for 6 out of 10 large instances. For instances that have more than 6 staff cars and 1200 bus trips, the improvement is 13-15% on average.
    Original languageEnglish
    Publication date2018
    Publication statusPublished - 2018
    Event29th European Conference On Operational Research - Valencia, Spain
    Duration: 8 Jul 201811 Jul 2018
    Conference number: 29


    Conference29th European Conference On Operational Research
    Internet address

    Fingerprint Dive into the research topics of 'A matheuristic for the driver scheduling problem with staff cars'. Together they form a unique fingerprint.

    Cite this