Improved Clonal Selection Algorithm Combined with Ant Colony Optimization

Shangce GAO  Wei WANG  Hongwei DAI  Fangjia LI  Zheng TANG  

IEICE TRANSACTIONS on Information and Systems   Vol.E91-D   No.6   pp.1813-1823
Publication Date: 2008/06/01
Online ISSN: 1745-1361
DOI: 10.1093/ietisy/e91-d.6.1813
Print ISSN: 0916-8532
Type of Manuscript: PAPER
Category: Biocybernetics, Neurocomputing
clonal selection algorithm,  ant colony optimization,  traveling salesman problem,  hybridization,  

Full Text: PDF(682KB)>>
Buy this Article

Both the clonal selection algorithm (CSA) and the ant colony optimization (ACO) are inspired by natural phenomena and are effective tools for solving complex problems. CSA can exploit and explore the solution space parallely and effectively. However, it can not use enough environment feedback information and thus has to do a large redundancy repeat during search. On the other hand, ACO is based on the concept of indirect cooperative foraging process via secreting pheromones. Its positive feedback ability is nice but its convergence speed is slow because of the little initial pheromones. In this paper, we propose a pheromone-linker to combine these two algorithms. The proposed hybrid clonal selection and ant colony optimization (CSA-ACO) reasonably utilizes the superiorities of both algorithms and also overcomes their inherent disadvantages. Simulation results based on the traveling salesman problems have demonstrated the merit of the proposed algorithm over some traditional techniques.