Artificial Immune System for Solving Constrained Global Optimization Problems

The artificial immune system (AIS) is a computational intelligence approach based on information regarding a biological immune system. This study combines the metaphor of clonal selection and idiotypic network theories to design an AIS method. Although contradicting each other, these two theories are useful in developing a function optimization tool. The AIS approach comprises idiotypic network selection, somatic hypermuation, receptor editing and bone marrow operators. The idiotypic network selection operator controls the number of good solutions. The somatic hypermuation and receptor editing operators explore a search space of solutions to an optimization problem. The bone marrow operator generates diverse solutions to maintain the population of solutions. The performance of the proposed AIS method is measured by using it to solve a set of constrained global optimization (CGO) problems. The best AIS solution is compared with the known global optimum. Numerical results show that the proposed method converged to the global optimal solution to each tested CGO problem