Introduction

Abstract

The biological organisms that populate our planet today are widely considered as the product of an evolutionary process. A process that over the course of time, allowed the adaptation of the ancestors of these organisms so that they were better enabled to survive in their environment. Coupled with this passage of time, the world and the dynamics of the predators and prey of these organisms have also transformed and evolved, resulting in an environment that is permanently undergoing change. Natural evolution has enabled a rich and diverse range of organisms to survive and prosper under these circumstances. It is this process that is the inspiration behind the field of Evolutionary Computation (EC). However, despite natural evolution being set in a fundamentally dynamic environment, the majority of research in EC has been dedicated to overcoming issues encountered in solving static problems and optimising algorithms for these problems. Considering that most real-world problems, like biological organisms, are set in dynamic environments and that these algorithms face issues like premature convergence when operating under such circumstances, the long term future and mainstream adoption of EC is jeopardised unless the issues involved in conducting evolution in dynamic environments are identified and addressed.