Using weight aggregation in tabu search for multiobjective exams timetabling problem

Abstract

En
Exams timetabling is a difficult task in many educational institutions. We can distinct two major sets of constraints when defining exams timetabling problems, categorized in soft and hard constraints. Guaranteing that any student as a non overlapping exams schedule and that necessary requirements like rooms and teacher are available are consider hard constraints. An evenly distributed schedule, a short duration of the overall exams period can be regarded as soft constraints. To handle soft constraints under the hard constraints verification we adopted a multiobjective optimization approach. This problem is NP-hard for which we have developed an heuristic tabu search method to find a solution. Tabu search comprises an iterative local search defined as a neighborhood inspection of a certain point in the search space. To find an improved solution we have to evaluate points in this neighborhood which can be considered a multiple attribute decision problem. In this context we have used multicriteria methods in order to rank the solutions.