Optimization Methods

<< Click to Display Table of Contents >>

Navigation:  Chapter 3 - GeneHunter Excel Interface Reference >

Optimization Methods

Previous pageReturn to chapter overviewNext page

Classic GeneHunter

The Classic GeneHunter optimization method solves problems by creating a population of possible solutions to the problem.  The individuals in this population will carry chromosomes which are the values of variables of the problem.  Each possible solutions is ranked by how well it solves the problem, i.e., less time to complete a manufacturing process, better adherence to problem specifications, maximizing net profit, etc., the better the solution.  Just as the ability of an animal to swim in a swamp is a measure of that animal's fitness to survive, the time required to manufacture circuit boards is a measure of the fitness of scheduling the manufacturing process.  The formula for the amount of time required to finish the circuit boards is called a "fitness function,” which we want to minimize.  For more information, refer to the book by David Goldberg in the references.



Evolution Strategy

Evolution Strategy is a variant of genetic algorithms that use real numbers instead of integers in chromosomes, and therefore do not cross segments of a chromosome, but instead cross whole chromosomes. The individuals represent potential solutions to a problem. The individuals are tested by a fitness function and the results are used to determine if the individual will be included in the next generation of potential solutions. For more information refer to the book by Z. Michalewicz in the references.

Evolution Strategy works on problems that use continuous or integer chromosomes.  Evolution Strategy does not work with problems that use enumerated chromosomes.