Improved clonal selection algorithm based on the directional update strategy

Abstract

At present, many cloning selection algorithms have been studied, and improvements have been made to the cloning, mutation and selection steps. However, there is a lack of research on the optimization of the updating operation steps. The clonal selection algorithm is traditionally updated through a random complement of antibodies, which is a blind and uncertain process. The added antibodies may gather near a local optimal solution, resulting in the need for more iterations to obtain the global optimal solution. To solve this problem, our improved algorithm introduces a crowding degree factor in the antibody updating stage to determine whether there is crowding between antibodies. By eliminating antibodies with high crowding potential and poor affinity, the improved algorithm guides the antibodies to update in the direction of the global optimal solution and ensures stable convergence with fewer iterations. Experimental results show that the overall performance of the improved algorithm is 1% higher than that of the clonal selection algorithm and 2.2% higher than that of the genetic algorithm, indicating that the improved algorithm is effective. The improved algorithm is also transplanted to other improved clonal selection algorithms, and the overall performance is improved by 0.97%, indicating that the improved algorithm can be a beneficial supplement to other improved clonal selection algorithms.