Artificial immune system based on hybrid and external memory for mathematical function optimization

Artificial immune system (AIS) is one of the nature-inspired algorithm for optimization problem. In AIS, clonal selection algorithm (CSA) is able to improve global searching ability. However, the CSA convergence and accuracy can be further improved because the hypermutation in CSA itself cannot always guarantee a better solution. Alternatively, Genetic Algorithms (GAs) and Particle Swarm Optimization (PSO) have been used efficiently in solving complex optimization problems, but they have a tendency to converge prematurely. Thus, a hybrid PSO-AIS and a new external memory CSA based scheme called EMCSA are proposed. In hybrid PSO-AIS, the good features of PSO and AIS are combined in order to reduce any limitation. Alternatively, EMCSA captures all the best antibodies into the memory in order to enhance global searching capability. In this preliminary study, the results show that the performance of hybrid PSO-AIS compares favourably with other algorithms while EMCSA produced moderate results in most of the simulations.