University course timetabling using a new hybrid genetic algorithm

Abstract

The university course timetabling problem (UCTP) is a classical, old and famous problem in the field of optimization problems. The purpose of UCTP is to schedule a number of events (courses) in proper timeslots and suitable rooms. In this problem, there are some hard and soft constraints. A feasible timetable must satisfy all hard constraints. In addition, each soft constraint violation causes a penalty. As far as UCTP is an NP-complete problem, it is reasonable to use population-based metaheuristic algorithms and evolutionary algorithms (EA). Although various methods have been presented the best results are referred to as hybrid evolutionary algorithms (HEA) and metaheuristics. The proposed method is a hybrid genetic algorithm (HGA). In our innovative HGA, the initial population which comes from heuristics is stored into red-black tree data structure. After that, our HGA creates new offsprings from previous individuals by its operators. Moreover, to improve local exploitation, we used hill climbing. The results were compared with other available ones using the 11 datasets of Socha et al. The results were promising and showed that the proposed HGA method is a good method to solve UCTP.