PROJECT TITLE :

A Cluster and Gradient-Based Artificial Immune System Applied in Optimization Scenarios

ABSTRACT :

The main objective of this paper is to use artificial immune systems (AIS) in optimization problems. For this purpose, 2 major immunological principles presented within the literature are revisited: hypermutation, which is responsible for native search, and receptor edition, used to explore totally different areas in the solution space. This paper presents 3 major modifications divided into two different goals. The first goal is to speed up the convergence of each individual. This is completed through a brand new hypermutation approach that uses the numerical data provided by the optimization system to drive the cloning method to fascinating directions into the solution area. The second goal regards the reduction of the computational effort necessary to simulate the full population. This is accomplished by adding to the AIS algorithm 2 a lot of options of the natural immune system: maturation management and memory cells. The maturation control analyzes the antibodies and, during the convergence method, eliminates possible redundancies, represented by people driving to the identical local optimum. The last proposed improvement is the employment of memory cells in dynamic-optimization scenarios. In such situations, a repertoire of successful cases is used to forecast part of the initial population. Combining these ideas together decreases the number of antibodies, generations, and clones, consequently dashing up the convergence process. Applications illustrate the performance of the proposed methodology.