amocell3.java

这是多目标进化算法包

/**
 * aMOCell3.java
 * @author Juan J. Durillo
 * @version 1.0
 */
package jmetal.metaheuristics.mocell;

import jmetal.base.*;
import java.util.Comparator;
import jmetal.base.archive.CrowdingArchive;
import jmetal.base.operator.comparator.*;
import jmetal.util.*;

/**
 * This class representing an asychronous version of MOCell algorithm in 
 * which all neighbors are considerated in the replace
 */
public class aMOCell3 extends Algorithm{

  /**
   * Stores the problem to solve
   */
  private Problem problem_;     

  /** 
   * Constructor
   * @param problem Problem to solve
   */  
  public aMOCell3(Problem problem){
    problem_ = problem;
  } //aMOCell3



  /**   
   * Runs of the aMOCell3 algorithm.
   * @return a <code>SolutionSet</code> that is a set of non dominated solutions
   * as a result of the algorithm execution  
   * @throws JMException 
   */     
  public SolutionSet execute() throws JMException {
    int populationSize, archiveSize, maxEvaluations, evaluations, feedBack;
    Operator mutationOperator, crossoverOperator, selectionOperator;
    SolutionSet currentSolutionSet;
    CrowdingArchive archive;
    SolutionSet [] neighbors;    
    Neighborhood neighborhood;
    Distance distance = new Distance();


    //Read the params
    populationSize    = ((Integer)getInputParameter("populationSize")).intValue();
    archiveSize       = ((Integer)getInputParameter("archiveSize")).intValue();
    maxEvaluations    = ((Integer)getInputParameter("maxEvaluations")).intValue();                
    feedBack          = ((Integer)getInputParameter("feedBack")).intValue();


    //Read the operators
    mutationOperator  = operators_.get("mutation");
    crossoverOperator = operators_.get("crossover");
    selectionOperator = operators_.get("selection");        

    //Init the variables
    //init the population and the archive
    currentSolutionSet  = new SolutionSet(populationSize);        
    archive            = new CrowdingArchive(archiveSize,problem_.getNumberOfObjectives());                
    evaluations        = 0;                        
    neighborhood       = new Neighborhood(populationSize);
    neighbors          = new SolutionSet[populationSize];

    //Create the initial population
    for (int i = 0; i < populationSize; i++){
      Solution solution = new Solution(problem_);
      problem_.evaluate(solution);           
      problem_.evaluateConstraints(solution);
      currentSolutionSet.add(solution);
      solution.setLocation(i);
      evaluations++;
    }        

    while (evaluations < maxEvaluations){                                 
      for (int ind = 0; ind < currentSolutionSet.size(); ind++){
        Solution individual = new Solution(currentSolutionSet.get(ind));

        Solution [] parents = new Solution[2];
        Solution [] offSpring;

        //neighbors[ind] = neighborhood.getFourNeighbors(currentSolutionSet,ind);
        neighbors[ind] = neighborhood.getEightNeighbors(currentSolutionSet,ind);                                                           
        neighbors[ind].add(individual);

        //parents
        parents[0] = (Solution)selectionOperator.execute(neighbors[ind]);
        parents[1] = (Solution)selectionOperator.execute(neighbors[ind]);

        //Create a new solution, using genetic operators mutation and crossover
        offSpring = (Solution [])crossoverOperator.execute(parents);               
        mutationOperator.execute(offSpring[0]);

        //->Evaluate solution and constraints
        problem_.evaluate(offSpring[0]);
        problem_.evaluateConstraints(offSpring[0]);
        evaluations++;                    

        neighbors[ind].add(offSpring[0]);               
        offSpring[0].setLocation(-1);
        Ranking rank = new Ranking(neighbors[ind]);
        for (int j = 0; j < rank.getNumberOfSubfronts(); j++){
          (distance).crowdingDistanceAssignment(rank.getSubfront(j),problem_.getNumberOfObjectives());
        }
        neighbors[ind].sort(new CrowdingComparator()); 
        Solution worst = neighbors[ind].get(neighbors[ind].size()-1);

        if (worst.getLocation() == -1) {//The worst is the offspring
          archive.add(new Solution(offSpring[0]));
        } else {
          offSpring[0].setLocation(worst.getLocation());
          currentSolutionSet.replace(offSpring[0].getLocation(),offSpring[0]);
          archive.add(new Solution(offSpring[0]));
        }                                          
      }

      //Store a portion of the archive into the population
      (distance).crowdingDistanceAssignment(archive,problem_.getNumberOfObjectives());                      
      for (int j = 0; j < feedBack; j++){
        if (archive.size() > j){
          int r = PseudoRandom.randInt(0,currentSolutionSet.size()-1);
          if (r < currentSolutionSet.size()){
            Solution individual = archive.get(j);
            individual.setLocation(r);
            currentSolutionSet.replace(r,new Solution(individual));
          }
        }
      }                      
    }
    return archive;
  } // execute
} // aMOCell3