CONVERGENCE TENDENCY OF GENETIC ALGORITHMS AND ARTIFICIAL IMMUNE SYSTEM IN SOLVING CONTINUOUS OPTIMIZATION FUNCTIONS

ABSTRACT By the advances in the Evolution Algorithms (EAs) and the intelligent optimization methods we witness the big revolutions in solving the optimization problems. The application of the evolution algorithms are not only not limited to the combined optimization problems, but also are vast in domain to the continuous optimization problems. In this paper we analyze and study the Genetic Algorithm (GA) and the Artificial Immune System (AIS) algorithm which are capable in escaping the local optimization and also fastening reaching the global optimization and to show the efficiency of the GA and AIS the application of them in Solving Continuous Optimization Functions (SCOFs) are studied. Because of the multi variables and the multi-dimensional spaces in SCOFs the use of the classic optimization methods, is generally non-efficient and high cost. In other words the use of the classic optimization methods for SCOFs generally leads to a local optimized solution. A possible solution for SCOFs is to use the EAs which are high in probability of succeeding reaching the local optimized solution. The results in paper show that GA is more efficient than AIS in reaching the optimized solution in SCOFs. KEYWORDS Evolution Algorithms, Genetic Algorithm, Artificial Immune System, Solving Continuous Optimization Functions, Optimizatio