Thesis (BS Computer Science) -- University of the Philippines Mindanao, 2010

Most real-world optimization are faced with constraints which must be satisfied with an acceptable solution. There are lot of proven methods that can solve many of these optimization problems such as Evolutionary Programming(EP), Genetic Algorithm (GA) and Particle Swarm Optimization (PSO). These methods are also called heuristics. A new metaheuristic study of Karaboga (2005), which is called Artificial Bee Colony (ABC) algorithm, is originally designed to solve unconstrained problems. The algorithm, as Karaboga (20050 describes it, is simple and flexible. Since most of the problems are subjected to constraints, in this study the original ABC algorithm was incorporated with a constraint handling method called penalty function. Hence, a modified Artificial Bee Colony algorithm is introduced to solve constrained problems. To test the feasibility of the modified algorithm, it was applied to a one dimensional cutting stock problem. Based on the study conducted, the ABC algorithm integrated with a constraint handling method returned good results to all the rest problems presented in the study. These results were compared to a study made by Lacsama (2008) called Modified shuffle frog leaping algorithm (MSFLA). The modified ABC gave better results than MSFLA for some of the test problems. The modified ABC algorithm also performed relatively fast in obtaining the best solutions for each of the test problem