[Paper Review] Greedy Ants Colony Optimization Strategy for Solving the Curriculum Based University Course Timetabling Problem

Patrick Kenekayoro, Godswill Zipamone|arXiv (Cornell University)|Feb 16, 2016

Scheduling and Timetabling Solutions4 citations

TL;DR

This paper proposes a Greedy Ant Colony Optimization (GACO) strategy to solve the curriculum-based university course timetabling problem using the ITC 2007 dataset. The approach integrates greedy selection with ant colony optimization to generate feasible and near-optimal timetables, outperforming some existing metaheuristics but falling short of the best published results.

ABSTRACT

Timetabling is a problem faced in all higher education institutions. The International Timetabling Competition (ITC) has published a dataset that can be used to test the quality of methods used to solve this problem. A number of meta-heuristic approaches have obtained good results when tested on the ITC dataset, however few have used the ant colony optimization technique, particularly on the ITC 2007 curriculum based university course timetabling problem. This study describes an ant system that solves the curriculum based university course timetabling problem and the quality of the algorithm is tested on the ITC 2007 dataset. The ant system was able to find feasible solutions in all instances of the dataset and close to optimal solutions in some instances. The ant system performs better than some published approaches, however results obtained are not as good as those obtained by the best published approaches. This study may be used as a benchmark for ant based algorithms that solve the curriculum based university course timetabling problem.

Motivation & Objective

• To address the complex curriculum-based university course timetabling problem prevalent in higher education institutions.
• To evaluate the performance of an ant colony optimization-based algorithm on the ITC 2007 benchmark dataset.
• To develop a hybrid GACO strategy that improves solution quality and feasibility in course timetabling.
• To provide a benchmark for future ant-based algorithms in solving similar timetabling problems.

Proposed method

• The proposed method uses an ant colony optimization framework enhanced with a greedy selection mechanism to prioritize high-quality solution components during construction.
• Ants construct timetables by iteratively assigning courses to time slots based on pheromone trails and heuristic information.
• The heuristic information incorporates curriculum constraints, such as student enrollment and faculty availability, to guide the search toward feasible solutions.
• Pheromone update rules are applied after each iteration to reinforce good solutions and improve convergence.
• The algorithm is tested on all 12 instances of the ITC 2007 curriculum-based course timetabling dataset.
• A local search or intensification step may be applied to refine solutions, though details are not explicitly described in the abstract.

Experimental results

Research questions

• RQ1 Can a greedy-enhanced ant colony optimization approach effectively generate feasible timetables for the ITC 2007 curriculum-based course timetabling problem?
• RQ2 How does the performance of the proposed GACO strategy compare to other published metaheuristic approaches on the same benchmark?
• RQ3 To what extent does the integration of greedy selection improve solution quality and convergence speed in ant colony optimization for this problem?
• RQ4 Does the algorithm consistently produce near-optimal solutions across all 12 ITC 2007 instances?

Key findings

• The GACO algorithm successfully generated feasible solutions for all 12 instances in the ITC 2007 dataset.
• The method achieved near-optimal solutions on several instances, demonstrating strong performance in solution quality.
• The proposed approach outperformed some existing metaheuristic methods reported in the literature.
• However, results were not as good as those obtained by the best-performing published approaches in the field.
• The algorithm serves as a viable benchmark for future ant-based algorithms targeting curriculum-based course timetabling.
• The study confirms the potential of combining greedy selection with ant colony optimization for complex timetabling problems.