Evolutionary Computation Algorithms

The following classes are available (all discussions assume CIlib version 0.5, and therefor assumes the same directory structure as used in CIlib):

• Genetic Evolutionary Algorithm [ Show ]
  
• Differential Evolution [ Hide ]
  

  Find below the XML specification for a Differential Evolution Algorithm (section 13.1).

  <simulator>
    <algorithms>
      <algorithm id="da" class="ec.EC">
        <iterationStrategy class="ec.iterationstrategies.DifferentialEvolutionIterationStrategy">
          <crossoverProbability class="controlparameter.ConstantControlParameter" parameter="0.6" />
          <scaleParameter class="controlparameter.ConstantControlParameter" parameter="0.5" />
        </iterationStrategy>
        <initialisationStrategy class="algorithm.initialisation.ClonedPopulationInitialisationStrategy">
          <prototypeEntity class="ec.Individual" />
          <entityNumber value="30" />
        </initialisationStrategy>
      </algorithm>
    </algorithms>
    <problems>
      <problem id="griewank" class="problem.FunctionMinimisationProblem">
        <function class="functions.continuous.Griewank" domain="R(-600, 600)^30" />
      </problem>
    </problems>
    <measurements id="measurements" class="simulator.MeasurementSuite" resolution="1" samples="30">
      <addMeasurement class="measurement.single.Fitness" />
      <addMeasurement class="measurement.single.Diversity" />
      <addMeasurement class="measurement.single.FitnessEvaluations" />
    </measurements>
    <simulations>
      <simulation>
        <algorithm idref="da">
          <addStoppingCondition class="stoppingcondition.MaximumIterations" maximumIterations=" 1000 " />
        </algorithm>
        <problem idref="griewank" />
        <measurements idref="measurements" file="data/griewank.de.p_50.cross_0.6.scale_0.5.txt" />
      </simulation>
    </simulations>
  </simulator>
  

  Click here to download this file.

  The XML file above provides a specification for a simulation which executes a Basic Differential Evolution Algorithm (Algorithm 13.1 on page 240) on the griewank function (page 556, Equation A.15). Using the simulator provided with CIlib and running the command ./simulator.sh xml/de.xml for Linux users or simulator.bat xml\de.xml for Windows users, the simulation as specified in the above XML will be executed, and the results of the simulations are written to data/griewank.de.p_50.cross_0.6.scale_0.5.txt.