4 Genetic algorithms
GA is a stochastic search methodology that obtains the most efficient solution(s) in a given space for a complex problem. GAs practically imitate natural species evolution on computers. They act as a set of solutions known as individuals of a population that mate, reproduce, etc. Ultimately, after a number of generations, the fittest individual solution survives (survival of the fittest). GA’s first appearance was during 1950s by biologists who tried to simulate the genetic species evolution using computers. They were formulated in detail by John Holland in the early 1970s [15] and were refined by Goldberg [16]. The following points give a generic view of how GAs operate (see Fig. 4):