A Novel Immune Clonal Algorithm for MO Problems

• Published in: IEEE transactions on evolutionary computation Vol. 16; no. 1; pp. 35 - 50
• Main Authors: Shang, Ronghua, Jiao, Licheng, Liu, Fang, Ma, Wenping
• Format: Journal Article
• Language: English
• Published: New York, NY IEEE 01-02-2012; Institute of Electrical and Electronics Engineers; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Applied sciences; Artificial immune system (AIS); Artificial intelligence; Cloning; Computer science; control theory; systems; Convergence; Decision theory. Utility theory; Exact sciences and technology; Heuristic algorithms; Immune system; Learning and adaptive systems; Measurement; multiobjective optimization (MO); Operational research and scientific management; Operational research. Management science; Optimization; pareto-optimal front; performance metric; Vectors; Artificial life; pareto-optimal front; Pareto optimum; Evolutionary algorithm; Multiobjective programming; Dominance; Updating; Artificial immune system (AIS); Convergence speed; performance metric; Immune algorithm; Optimal solution; Size effect; Problem solving; Clonal selection; Population size; Population dynamics; Metric; Artificial intelligence; Clone; Mathematical programming; Immune system; multiobjective optimization (MO)
• ISSN: 1089-778X; 1941-0026
• DOI: 10.1109/TEVC.2010.2046328

Research on multiobjective optimization (MO) becomes one of the hot points of intelligent computation. Compared with evolutionary algorithm, the artificial immune system used for solving MO problems (MOPs) has shown many good performances in improving the convergence speed and maintaining the diversity of the antibody population. However, the simple clonal selection computation has some difficulties in handling some more complex MOPs. In this paper, the simple clonal selection strategy is improved and a novel immune clonal algorithm (NICA) is proposed. The improvements in NICA are mainly focus on four aspects. 1) Antibodies in the antibody population are divided into dominated ones and nondominated ones, which is suitable for the characteristic of one multiobjective optimization problem has a series Pareto-optimal solutions. 2) The entire cloning is adopted instead of different antibodies having different clonal rate. 3) The clonal selection is based on the Pareto-dominance and one antibody is selected or not depending on whether it is a nondominated one, which is different from the traditional clonal selection manner. 4) The antibody population updating operation after the clonal selection is adopted, which makes antibody population under a certain size and guarantees the convergence of the algorithm. The influences of the main parameters are analyzed empirically. Compared with the existed algorithms, simulation results on MOPs and constrained MOPs show that NICA in most problems is able to And much better spread of solutions and better convergence near the true Pareto-optimal front.