Introduction to Genetic Algorithm with a Simple Analogy

Abstract

Genetic Algorithm (GA), which is now considered as a well-established and one of the most widely applied optimization techniques, started its journey when Von Neumann first forwarded the theory of self-reproducing automata during fifties (Fellenius W: Calculation of the stability of earth dams. Trans, of 2nd congress on Large Dams, vol 4, pp 445--459, 1936). However, implementation of this ideas came into application during eighties (Baker R: Determination of the critical slip surface in slope stability computations. Int J Numer Anal Methods Geomech 4:333--359, 1980; Bishop AW: The use of slip circle in the stability analysis of slopes. Geotechnique London 5:7--17, 1955; Chen Z-Y, Shao C-M: Evolution of minimum factor of safety in slope stability analysis. Canadian Geotech J Ottawa 25:735--748, 1988; Celestino TB, Duncan JM: Simplified search for noncircular slip surface. In: Proceedings of the 10th international conference on SMFE, pp 391--394, 1981). Because of the obvious advantage of using GA in optimizing even complex non-linear functions, it has now been used by many researchers for solving varieties of optimization problems. Basically GA is a computerized search optimization algorithms based on the principles of survival of the fittest, first laid down by Charles Darwin. Concept of GA has so far been presented by different researchers in different forms, mostly in a mathematical framework. The terms like gene, chromosome, cross over, mutation and generation, which are basically derived from biological origin, many a time, become confusing to readers of other disciplines and also it become difficult to appreciate how these processes will lead to an optimal solution. Therefore, in this article, the basic philosophy of GA is presented by highlighting how it works and how the natural biological processes can help in obtaining the most optimal or at least near optimal solution through a simple analogy.