The Spirit of Evolutionary Algorithms

Abstract

Evolutionary algorithms (EAs), which are based on a powerful principle of evolution: survival of the fittest, and which model some natural phenomena: genetic inheritance and Darwinian strife for survival, constitute an interesting category of modern heuristic search. During the last two decades there has been a growing interest in these algorithms; today, many complex software systems include at least some evolutionary component.

However, the process of building an evolutionary program is still art rather than science; often it is based on the intuition and experience of the designer. In this introductory article we present some important ideas behind the construction of evolutionary algorithms. These ideas are illustrated by three test cases: the transportation problem, a particular nonlinear parameter optimization problem, and the traveling salesman problem. We conclude the paper with a brief discussion on how an evolutionary algorithm can be tuned to the problem while solving it, which may increase further efficiency of the algorithm in a significant way.