/**
* Update the speed of each particle
*
* @throws JMException
*/
private void computeSpeed(int iter, int miter) throws JMException, IOException {
double r1, r2, W, C1, C2;
double wmax, wmin, deltaMax, deltaMin;
XReal bestGlobal;
for (int i = 0; i < swarmSize_; i++) {
XReal particle = new XReal(particles_.get(i));
XReal bestParticle = new XReal(best_[i]);
// Select a global best_ for calculate the speed of particle i, bestGlobal
Solution one, two;
int pos1 = PseudoRandom.randInt(0, leaders_.size() - 1);
int pos2 = PseudoRandom.randInt(0, leaders_.size() - 1);
one = leaders_.get(pos1);
two = leaders_.get(pos2);
if (crowdingDistanceComparator_.compare(one, two) < 1) {
bestGlobal = new XReal(one);
} else {
bestGlobal = new XReal(two);
// Params for velocity equation
}
r1 = PseudoRandom.randDouble(r1Min_, r1Max_);
r2 = PseudoRandom.randDouble(r2Min_, r2Max_);
C1 = PseudoRandom.randDouble(C1Min_, C1Max_);
C2 = PseudoRandom.randDouble(C2Min_, C2Max_);
W = PseudoRandom.randDouble(WMin_, WMax_);
//
wmax = WMax_;
wmin = WMin_;
for (int var = 0; var < particle.getNumberOfDecisionVariables(); var++) {
// Computing the velocity of this particle
speed_[i][var] =
velocityConstriction(
constrictionCoefficient(C1, C2)
* (inertiaWeight(iter, miter, wmax, wmin) * speed_[i][var]
+ C1 * r1 * (bestParticle.getValue(var) - particle.getValue(var))
+ C2 * r2 * (bestGlobal.getValue(var) - particle.getValue(var))),
deltaMax_, // [var],
deltaMin_, // [var],
var,
i);
}
}
} // computeSpeed
/**
* Runs of the SMPSO 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, ClassNotFoundException {
initParams();
success_ = false;
// ->Step 1 (and 3) Create the initial population and evaluate
for (int i = 0; i < swarmSize_; i++) {
Solution particle = new Solution(problem_);
particles_.add(particle);
parallelEvaluator_.addSolutionForEvaluation(particle);
}
parallelEvaluator_.parallelEvaluation();
// -> Step2. Initialize the speed_ of each particle to 0
for (int i = 0; i < swarmSize_; i++) {
for (int j = 0; j < problem_.getNumberOfVariables(); j++) {
speed_[i][j] = 0.0;
}
}
// Step4 and 5
for (int i = 0; i < particles_.size(); i++) {
Solution particle = new Solution(particles_.get(i));
leaders_.add(particle);
}
// -> Step 6. Initialize the memory of each particle
for (int i = 0; i < particles_.size(); i++) {
Solution particle = new Solution(particles_.get(i));
best_[i] = particle;
}
// Crowding the leaders_
distance_.crowdingDistanceAssignment(leaders_, problem_.getNumberOfObjectives());
// -> Step 7. Iterations ..
while (iteration_ < maxIterations_) {
try {
// Compute the speed_
computeSpeed(iteration_, maxIterations_);
} catch (IOException ex) {
Logger.getLogger(SMPSODDSteadyState.class.getName()).log(Level.SEVERE, null, ex);
}
// Compute the new positions for the particles_
computeNewPositions();
// Mutate the particles_
mopsoMutation(iteration_, maxIterations_);
for (int i = 0; i < particles_.size(); i++) {
Solution particle = particles_.get(i);
parallelEvaluator_.addSolutionForEvaluation(particle);
}
parallelEvaluator_.parallelEvaluation();
// Actualize the archive
for (int i = 0; i < particles_.size(); i++) {
Solution particle = new Solution(particles_.get(i));
leaders_.add(particle);
}
// Actualize the memory of this particle
for (int i = 0; i < particles_.size(); i++) {
int flag = dominance_.compare(particles_.get(i), best_[i]);
if (flag != 1) { // the new particle is best_ than the older remeber
Solution particle = new Solution(particles_.get(i));
best_[i] = particle;
}
}
// Assign crowding distance to the leaders_
distance_.crowdingDistanceAssignment(leaders_, problem_.getNumberOfObjectives());
iteration_++;
}
parallelEvaluator_.stopEvaluator();
return this.leaders_;
} // execute
