4 Genetic Algorithm

Summary

This chapter describes the genetic algorithm (GA), which is a well‐known evolutionary algorithm. First, a brief literature review of the GA is presented, followed by a description of the natural process that inspires the algorithm and how it is mapped to the GA. The steps of the standard GA are described in depth. A pseudocode of the GA closes this chapter.

4.1 Introduction

One of the best‐known evolutionary algorithms is the genetic algorithm (GA) developed by Holland (1975) and popularized by Goldberg (1989). There are several varieties of GAs (Brindle, 1981; Baker, 1985, 1987; Goldberg et al., 1991). The elitist version, which allows the best individual(s) from a generation to carry over to the next one, was introduced by De Jong (1975). Other versions are the modified GA (modGA) (Michalewicz, 1996), messy GAs (Goldberg et al., 1990), GAs with varying population size (GAsVaPS) (Michalewicz, 1996), genetic implementor (GENITOR) (Whitley, 1989), and breeder GAs (BGA) (Muhlenbein and Schlierkamp, 1993). Several authors have implemented the GA in water resources optimization (East and Hall, 1994; Gen and Cheng, 1997). Furuta et al. (1996) presented a decision‐making supporting system based on the GA for the aesthetic design of dams. Pillay et al. (1997) applied genetic algorithms to the problem of parameter determination of induction motors. Wardlaw and Sharif (1999) employed the GA to solve four‐ and ten‐reservoir problems. Several researchers ...

Get Meta-heuristic and Evolutionary Algorithms for Engineering Optimization now with O’Reilly online learning.

O’Reilly members experience live online training, plus books, videos, and digital content from 200+ publishers.