In nature, individuals that are best suited to the environment will win the competition for scanty resources. An individual` s survival capacity is determined by various features that characterize it. The features in turn are determined by the individual` s genetic content.

Since only the fittest individuals survive and reproduce, the genes of weaker individuals die out gradually. If the environment doesn’t change during the process, we can imagine that finally it will converge to a state that every individual has the fittest (or the best) genes.

Inspired by this natural evolution process, the use of analogies of natural behavior led to the development of Genetic Algorithms (GAs). GA has 4 main elements: an encoding element that will be replicated, operators to affect the individuals of a population, a fitness function that indicates how good an individual is, and a selection mechanism. Each individual of the population represents a possible solution to a given problem. Each individual is assigned a fitness score based on the fitness function. A selection mechanism selects highly fit individuals to reproduce the offspring by “cross breeding” (crossover) and mutation techniques.

GA is not guaranteed to reach the global optimum, but it is generally good for finding an acceptable solution during an acceptable amount of time. It is mainly design to solve optimization problems. It is so robust that it can be applied to a wide range of problem areas. It also has good performance when solving some difficult problems with no existing specialized techniques can perform well. 

The Genetic Algorithm
How GAs Work?
Components of Genetic Algorithm
Genetic Operators

* This is a part of the Literature Review for my undergraduate thesis on Optimal Capacitor Allocation. Bibliography can be found HERE