A Novel and Robust Evolution Algorithm for Optimizing Complicated Functions

TL;DR

This paper introduces a divergence differential evolution algorithm (DDEA) with a new mutation operator, enhancing robustness and multi-solution detection in noisy environments, demonstrated through optimization and tracking tasks.

Contribution

The paper presents a novel mutation operator and combines it with divergence and assimilation operators to create DDEA, improving performance over traditional differential evolution algorithms.

Findings

DDEA outperforms DEA in optimizing Michalewicz Function.

DDEA effectively tracks rain-induced attenuation changes.

DDEA shows promise for MIMO channel optimization at millimeter waves.

Abstract

In this paper, a novel mutation operator of differential evolution algorithm is proposed. A new algorithm called divergence differential evolution algorithm (DDEA) is developed by combining the new mutation operator with divergence operator and assimilation operator (divergence operator divides population, and, assimilation operator combines population), which can detect multiple solutions and robustness in noisy environment. The new algorithm is applied to optimize Michalewicz Function and to track changing of rain-induced-attenuation process. The results based on DDEA are compared with those based on Differential Evolution Algorithm (DEA). It shows that DDEA algorithm gets better results than DEA does in the same premise. The new algorithm is significant for optimizing and tracking the characteristics of MIMO (Multiple Input Multiple Output) channel at millimeter waves.