Bitte verwenden Sie diesen Link, um diese Publikation zu zitieren, oder auf sie als Internetquelle zu verweisen: https://hdl.handle.net/10419/308620 
Erscheinungsjahr: 
2023
Quellenangabe: 
[Journal:] Annals of Operations Research [ISSN:] 1572-9338 [Volume:] 328 [Issue:] 2 [Publisher:] Springer US [Place:] New York, NY [Year:] 2023 [Pages:] 1313-1348
Verlag: 
Springer US, New York, NY
Zusammenfassung: 
Course timetables are the organizational foundation of a university's educational program. While students and lecturers perceive timetable quality individually according to their preferences, there are also collective criteria derived normatively such as balanced workloads or idle time avoidance. A recent challenge and opportunity in curriculum-based timetabling consists of customizing timetables with respect to individual student preferences and with respect to integrating online courses as part of modern course programs or in reaction to flexibility requirements as posed in pandemic situations. Curricula consisting of (large) lectures and (small) tutorials further open the possibility for optimizing not only the lecture and tutorial plan for all students but also the assignments of individual students to tutorial slots. In this paper, we develop a multi-level planning process for university timetabling: On the tactical level, a lecture and tutorial plan is determined for a set of study programs; on the operational level, individual timetables are generated for each student interlacing the lecture plan through a selection of tutorials from the tutorial plan favoring individual preferences. We utilize this mathematical-programming-based planning process as part of a matheuristic which implements a genetic algorithm in order to improve lecture plans, tutorial plans, and individual timetables so as to find an overall university program with well-balanced timetable performance criteria. Since the evaluation of the fitness function amounts to invoking the entire planning process, we additionally provide a proxy in the form of an artificial neural network metamodel. Computational results exhibit the procedure's capability of generating high quality schedules.
Schlagwörter: 
University timetabling
Matheuristic
Student scheduling
Multi-criteria decision making
Artificial neural network meta-model
Persistent Identifier der Erstveröffentlichung: 
Creative-Commons-Lizenz: 
cc-by Logo
Dokumentart: 
Article
Dokumentversion: 
Published Version

Datei(en):
Datei
Größe





Publikationen in EconStor sind urheberrechtlich geschützt.