Base Station Placement in WLANs - Multiobjective Optimization Methodology: A Jumping Gene Approach - page 186

Table 8.3
Parameter.Settings.for.Different.MOEAs

Parameter Value/Type

Population Size
MOGA,.NPGA2,.NSGA2,.SPEA2,.JG 100

PAES 1

MICROGA 4

Maximum Generations or Iterations
MOGA,.NPGA2,.NSGA2,.SPEA2,.JG

500

PAES 50,000

MICROGA 12,500

Crossover.type Uniform.crossover

Crossover.rate 0.8

Mutation.rate 0.04

Other Settings for JG
Jumping.rate

0.01

Number.of.transposons 3

Length of transposons 1

Other Settings for SPEA2 or PAES
Archive.size.(SPEA2,.PAES)

100

Depth (PAES) 4

Other Settings for MICROGA
Size.of.external.memory 100

Size.of.population.memory 80

Percentage.of.nonreplaceable.memory 0.25

Replacement.cycle Every.25.iterations

Number.of.subdivisions.of.the.adaptive.grid 25

Number of iterations to achieve nominal convergence 4

Source: . Data.from.Chan,.T..M.,.Man,.K..F.,.Tang,.K..S.,.Kwong,.S.,.A.jumping-genes.

paradigm. for. optimizing. factory. WLAN. network, IEEE Transactions on
IndustrialInformatics ,.3(1),.33-43,.2007.

8.7.3 Diversity evaluation using extreme
Nondominated Solution generation

Figures 8.4 . and. 8.5 .depict.the.total.number.of.extreme.nondominated.solu-
tions. found. by. various. MOEAs. for. scenarios. a. and. b,. respectively.. In. each.
scenario,.nondominated.solutions.obtained.by.50.simulation.runs.were.con-
sidered,.and.the.scaling.factor.chosen.for.both.scenarios.was.0.01..As.shown.
in.the.figures,.the.total.number.of.extreme.nondominated.solutions.obtained.
by.the.JG.were.the.largest.for.both.scenarios.