Association Based Immune Network for Multimodal Function Optimization


For the problem of serious resources waste, indeterminate direction of local search and degeneration in the original opt-aiNet, a novel association based immune network is proposed for multimodal function optimization. The hexabasic model mimics natural phenomenon in immune system such as clonal selection, affinity maturation, immune network, immune memory and immune association. The antibody population scale is semi-fixed reducing the time and space required to execute it. The information of the antibody population and the memory cells population is effective utilized to point out the direction of local search, to regulate the ratio between local search and global search, and to enhance the affinity of new antibodies. The elitist selection mechanism is adopted to ensure the convergence and stability of our algorithm respectively. The experiments on 10 benchmark functions show that when compared with opt-aiNet method, the new algorithm is capable of improving the search performance significantly in global convergence, convergence speed, computational cost, search ability, solution quality and algorithm stability.