Download as docx, pdf, or txt
Download as docx, pdf, or txt
You are on page 1of 7

Chapter 4-: Genetic Algorithms

Genetic Algorithms

31

Chapter-4 Genetic Algorithms


4.1 INTRODUCTION
The Genetic algorithms (GAs) are search methods based on principles of natural selection and genetics (David Goldberg, 1989). They represent an intelligent exploitation of a random search used to solve optimization problems. Although randomized, there is no randomization in GA, they exploit the historical information to direct the search into the region (search space) of better performance. GAs are designed to simulate processes in natural systems for evolution those follow the principles laid down by Charles Darwin of "survival of the fittest". In nature, competition among individuals (weaker /stronger) results in the fittest individuals dominating over the weaker ones.
4.1.1 Definition

The genetic algorithm is a probabilistic search algorithm that iteratively transforms a set (called a population) within search space, each with an associated fitness value, into a new population of offspring objects using the Darwinian principle of natural selection as shown in fig 4.1 and using operations that are survived after genetic operations, such as crossover and mutation.

Reproduction

Competition

Survive
Fig4.1: Darwinian Paradigm

Selection

Genetic Algorithms

32

Search Space

A population of individuals is maintained within search space for a GA, each representing a possible solution to a given problem. Each individual is coded as a finite length vector of components, or variables, in terms of some alphabet, usually the binary alphabet . To continue the genetic analogy these individuals are

likened to chromosomes and the variables are analogous to genes. Thus a chromosome (solution) is composed of several genes (variables) as shown in figure 4.2.

1 0 1 0 0 0 1 1 1 0 1 1 0 1

GENE

1 0 1 0 0 0 1 1 1 0 1 1 0 1

Chromosome
Fig4.2: Chromosome representation

The GA maintains a population of n chromosomes (solutions) with associated fitness values. Parents are selected to mate, on the basis of their fitness, producing offspring via a reproductive plan. Consequently highly fit solutions are given more opportunities to reproduce, so that offspring inherit characteristics from each parent (Melanie Mitchell, 1998).

POPULATION

Genetic Algorithms

33

Fitness Function The most important element of GA is Fitness function. In GA, the fitness function assigns a score to each chromosome in current population. The fitness of a chromosome depends on how well that chromosome solves the problem at hand. e.g.  (11)

Here the solutions are values of , which can be encoded as bit of strings representing real numbers. The fitness calculation translate a given bit string into real number y and then evaluates the function at that value. The fitness of the string is the function value at that point (Melanie Mitchell, 1998). GA Operators After an initial population is generated randomly, the algorithm evolves the through three operators (Melanie Mitchell, 1998): Selection which equates to survival of the fittest in this we give preference to better individuals, allowing them to pass on their gene to the next generation. Crossover which represents mating between the individuals. In this two individuals are chosen from the population using selection operator and a crossover site along the bit is chosen as shown in figure 4.3. e.g. P1= 000000000000000 and P2=11111111111111 and the crossover point is 4 then P1= 111100000000000 and P2=00001111111111. This is the next generation of the population (Mitsuo Gen et al., 2000).

Genetic Algorithms

34

Parent 1

Parent 2

Child 1

Child 2

Crossover with 4 points

Fig4.3: Crossover Operation

Mutation which introduces random modifications. In this the bits of an individual are flipped with some low probability as shown in figure 4.4.

Before Mutation

After Mutation

Fig4.4: Mutation Operation

Genetic Algorithms

35

4.1.2 1. 2. 3.

Basic Genetic Algorithm START : Create random population of n chromosomes FITNESS : Evaluate fitness f(y) of each chromosome in the population NEW POPULATION i. ii. iii. iv. SELECTION : Based on f(y)

RECOMBINATION : Cross-over chromosomes MUTATION : Mutate chromosomes

ACCEPTATION : Reject or accept new one

4. 5. 6.

REPLACE : Replace old with new population: the new generation TEST LOOP : Test problem criterium : Continue step 1 4 until criterium is satisfied

Genetic Algorithms

36

Start
Take the initial population and assign the score to each member of population by computing their fitness

Select randomly population within given range of fitness

No
>=Fitness Limit

Reproduction

Yes Produce the children by Mutation or Crossover

No
< Generation Limit

Yes No
< Time Limit

Yes

Stop
Fig4.5: Flow of Genetic Algorithm

You might also like