Resource Management in WCDMA - Multiobjective Optimization Methodology: A Jumping Gene Approach - page 172

11550

11500

reference
solution

11450

MOGA

11400
11350

NPGA2

NSGA2

11300

SPEA2

11250

JG

11200
11150

11100

0 0.5 1 1.5 2 2.5 3 3.5 4 4.5

Total Power

Figure 7.6 (CONTiNueD)

. 3.. Total. number. of. connecting. users. is. 50,. and. no. JG. transposition. is.

implemented;.and

. 4.. Total. number. of. connecting. users. is. 50,. and. JG. transposition. is.

implemented.

Note. that. the. parameters. of. the. JG. for. this. test. were. the. same. as. in.
Table 7.5 .. The. mean. and. standard. deviation. of. running. times. are. shown.
in. Table 7.12 .. The.average.differences.between.conigurations.1.and.3.and.
configurations.2.and.4.were.261.56.ms.and.277.62.ms,.respectively,.indicat-
ing.that.the.runtime.increased.with.the.total.number.of.connecting.users,.
as.expected.
In. addition,. the. average. differences. between. conigurations. 1. and. 2. and.
configurations.3.and.4.were.30.42.ms.and.46.48.ms,.respectively,.indicating.
about.a.10%.increment.of.the.runtime.when.the.JG.transposition.was.imple-
mented.. The. runtime. only. slightly. increased. as. the. transposition. rate. was.
indeed.small..The.small.standard.deviations.also.implied.that.the.runtime.
of.the.JG.was.quite.stable.
Undoubtedly,.it.is.hoped.that.the.JG.can.obtain.better.performance.by.
performing.more.generations.when.a.faster.processor.is.adopted..In.real.
implementation,.the.JG.can.be.forced.to.give.optimal.power.and.rate.val-
ues.for.each.connecting.user.when.the.maximum.allowed.time.is.reached,.
no.matter.how.the.total.number.of.connecting.users.varies.