Parameter Description Files for the MOEAFramework algorithms and for the Borg MOEA

The parameter description files, describe the parameters for each MOEA along with their feasible ranges.  The file first lists the name of the parameter, followed by its lower and upper bounds.  To enable the description files you can copy the following text into a text editor and save it as AMALGAM_Params.txt, for instance, to have the AMALGAM description file.  Each MOEA needs to have its separate description file.

AMALGAM:

populationSize 10 1000
maxEvaluations 1000 10000
sbx.rate 0.0 1.0
sbx.distributionIndex 0.0 500.0
pm.rate 0.0 1.0
pm.distributionIndex 0.0 500.0
de.F 0.0 1.0
de.K 0.0 1.0
metro.jumpRate 0.5 5.0
pso.c1 0.0 2.0 
pso.c2 0.0 2.0 
pso.chi 0.0 1.0

Borg MOEA:

initialPopulationSize 10 1000
maxEvaluations 1000 10000
injectionRate 0.1 1.0
sbx.rate 0.0 1.0
sbx.distributionIndex 0.0 500.0
pm.rate 0.0 1.0
pm.distributionIndex 0.0 500.0
de.crossoverRate 0.0 1.0
de.stepSize 0.0 1.0
um.rate 0.0 1.0
pcx.parents 2.0 10.0
pcx.offspring 1.0 10.0
pcx.eta 0.0 1.0
pcx.zeta 0.0 1.0
undx.parents 2.0 10.0
undx.offspring 1.0 10.0
undx.eta 0.0 1.0
undx.zeta 0.0 1.0
spx.parents 2.0 10.0
spx.offspring 1.0 10.0
spx.epsilon 0.0 1.0

ε-MOEA:

populationSize 10 1000
maxEvaluations 1000 10000
sbx.rate 0.0 1.0
sbx.distributionIndex 0.0 500.0
pm.rate 0.0 1.0
pm.distributionIndex 0.0 500.0

ε-NSGAII:

populationSize 10 1000
maxEvaluations 1000 10000
injectionRate 0.1 1.0
sbx.rate 0.0 1.0
sbx.distributionIndex 0.0 500.0
pm.rate 0.0 1.0
pm.distributionIndex 0.0 500.0

GDE3:

populationSize 10 1000
maxEvaluations 1000 10000
de.crossoverRate 0.0 1.0
de.stepSize 0.0 1.0

HypE:

populationSize 10 1000
maxEvaluations 1000 10000
sbx.rate 0.0 1.0
sbx.distributionIndex 0.0 500.0
pm.rate 0.0 1.0
pm.distributionIndex 0.0 500.0

IBEA:

populationSize 10 1000
archiveSize 10 1000
maxEvaluations 1000 10000
sbx.rate 0.0 1.0
sbx.distributionIndex 0.0 500.0
pm.rate 0.0 1.0
pm.distributionIndex 0.0 500.0

MOEAD:

populationSize 10 1000
maxEvaluations 1000 10000
neighborhoodSize 0.0 0.2
delta 0.0 1.0
eta 0.0 0.02
de.crossoverRate 0.0 1.0
de.stepSize 0.0 1.0
pm.rate 0.0 1.0
pm.distributionIndex 0.0 500.0

NSGAII:

populationSize 10 1000
maxEvaluations 1000 10000
sbx.rate 0.0 1.0
sbx.distributionIndex 0.0 500.0
pm.rate 0.0 1.0
pm.distributionIndex 0.0 500.0

OMOPSO:

populationSize 10 1000
archiveSize 10 1000
maxEvaluations 1000 10000
perturbationIndex 0.0 1.0

SPEA:

populationSize 10 1000
archiveSize 10 1000
maxEvaluations 1000 10000
sbx.rate 0.0 1.0
sbx.distributionIndex 0.0 500.0
pm.rate 0.0 1.0
pm.distributionIndex 0.0 500.0

The previous parameter description files were retrieved from the diagnostics study in Reed, P.M., Hadka, D., Herman, J., Kasprzyk, J., and Kollat, J., “Evolutionary Multiobjective Optimization in Water Resources: The Past, Present, and Future.” (Editor Invited Submission to 35th Anniversary Special Issue), Advances in Water Resources, v51, 438-456, 2013.  In their study they used 10,000 NFE as the lower bound and the upper bounds varies depending on the problem.  You can also vary the maxEvaluations parameter and adjust it according to the problem’s difficulty.

Advertisements

2 thoughts on “Parameter Description Files for the MOEAFramework algorithms and for the Borg MOEA

  1. Pingback: MOEA diagnostics for a simple test case (Part 1/3) | Water Programming: A Collaborative Research Blog

  2. Pingback: Water Programming Blog Guide (Part I) – Water Programming: A Collaborative Research Blog

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s