Go to www.awrcorp.com
Back to search page Click to download printable version of this guide.

4.3.7.3. Differential Evolution Algorithm

The differential evolution (DE)[1] algorithm comes from a class of algorithms based upon evolutionary principles. To start the process, an initial "population" of random vectors {pk,0} is created that all satisfy the parameter constraints. At each iteration (called a "generation") of the process, new vectors are obtained from the previous set using the following concepts::

In addition to the basic DE algorithm (named DE/rand/l), several schemes are implemented that determine how the subsequent generation is constructed ( r1, r2, r3, and r4 are randomly chosen integers).

Scheme Name Expression
DE/rand/1
DE/best/1
DE/best/2
DE/rand-to-best/1

Analyst exposes several parameters for DE:



[1] R. Storn and K. Price, "Differential evolution - a simple and efficient heuristic for global optimization over continuous spaces." J. Global Optim., 11, 1997, pp. 341-359.

Please send email to awr.support@ni.com if you would like to provide feedback on this article. Please make sure to include the article link in the email.

Legal and Trademark Notice