org.moeaframework.algorithm.pso
Class AbstractPSOAlgorithm

java.lang.Object
  org.moeaframework.algorithm.AbstractAlgorithm
      org.moeaframework.algorithm.pso.AbstractPSOAlgorithm

All Implemented Interfaces:

Algorithm

Direct Known Subclasses:

OMOPSO, SMPSO

public abstract class AbstractPSOAlgorithm
extends AbstractAlgorithm

Abstract multi-objective particle swarm optimizer (MOPSO).

Field Summary

protected NondominatedPopulation	archive The archive of non-dominated solutions; or null of no external archive is sued.
protected DominanceComparator	dominanceComparator Comparator for updating the local best particles.
protected DominanceComparator	leaderComparator Comparator for selecting leaders.
protected FitnessBasedArchive	leaders The leaders.
protected int	leaderSize The number of leaders.
protected Solution[]	localBestParticles The local best particles.
protected Variation	mutation Mutation operator, or null if no mutation is defined.
protected Solution[]	particles The particles.
protected int	swarmSize The number of particles.
protected double[][]	velocities The speed / velocity of each particle.

Fields inherited from class org.moeaframework.algorithm.AbstractAlgorithm

initialized, numberOfEvaluations, problem, terminated

Constructor Summary

AbstractPSOAlgorithm(Problem problem, int swarmSize, int leaderSize, DominanceComparator leaderComparator, DominanceComparator dominanceComparator, FitnessBasedArchive leaders, NondominatedPopulation archive, Variation mutation)
Constructs a new abstract PSO algorithm.

Method Summary

NondominatedPopulation	getResult() Returns the current best-known result.
protected void	initialize() Performs any initialization that is required by this algorithm.
protected void	iterate() Performs one iteration of the algorithm.
protected void	mutate() Applies the mutation operator to all particles.
protected void	mutate(int i) Applies the mutation operator to an individual particle.
protected Solution	selectLeader() Randomly select a leader.
protected void	updateLocalBest() Updates the local best particles.
protected void	updatePosition(int i) Update the position of an individual particle.
protected void	updatePositions() Update the positions of all particles.
protected void	updateVelocities() Update the speeds of all particles.
protected void	updateVelocity(int i) Update the speed of an individual particle.

Methods inherited from class org.moeaframework.algorithm.AbstractAlgorithm

evaluate, evaluateAll, evaluateAll, finalize, getNumberOfEvaluations, getProblem, getState, isInitialized, isTerminated, setState, step, terminate

Methods inherited from class java.lang.Object

clone, equals, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Field Detail

swarmSize

protected int swarmSize

The number of particles.

leaderSize

protected int leaderSize

The number of leaders.

particles

protected Solution[] particles

The particles.

localBestParticles

protected Solution[] localBestParticles

The local best particles.

leaders

protected FitnessBasedArchive leaders

The leaders.

archive

protected NondominatedPopulation archive

The archive of non-dominated solutions; or null of no external archive is sued.

velocities

protected double[][] velocities

The speed / velocity of each particle.

leaderComparator

protected DominanceComparator leaderComparator

Comparator for selecting leaders.

dominanceComparator

protected DominanceComparator dominanceComparator

Comparator for updating the local best particles.

mutation

protected Variation mutation

Mutation operator, or null if no mutation is defined.

Constructor Detail

AbstractPSOAlgorithm

public AbstractPSOAlgorithm(Problem problem,
                            int swarmSize,
                            int leaderSize,
                            DominanceComparator leaderComparator,
                            DominanceComparator dominanceComparator,
                            FitnessBasedArchive leaders,
                            NondominatedPopulation archive,
                            Variation mutation)

Constructs a new abstract PSO algorithm.

Parameters:

problem - the problem

swarmSize - the number of particles

leaderSize - the number of leaders

leaderComparator - comparator for selecting leaders

dominanceComparator - comparator for updating the local best particles

leaders - non-dominated population for storing the leaders

archive - non-dominated population for storing the external archive; or null if no external archive is defined

mutation - mutation operator, or null if no mutation is defined

Method Detail

updateVelocities

protected void updateVelocities()

Update the speeds of all particles.

updateVelocity

protected void updateVelocity(int i)

Update the speed of an individual particle.

Parameters:

i - the index of the particle

updatePositions

protected void updatePositions()

Update the positions of all particles.

updatePosition

protected void updatePosition(int i)

Update the position of an individual particle.

Parameters:

i - the index of the particle

selectLeader

protected Solution selectLeader()

Randomly select a leader.

Returns:

the selected leader

updateLocalBest

protected void updateLocalBest()

Updates the local best particles.

mutate

protected void mutate()

Applies the mutation operator to all particles.

mutate

protected void mutate(int i)

Applies the mutation operator to an individual particle.

Parameters:

i - the index of the particle

getResult

public NondominatedPopulation getResult()

Description copied from interface: Algorithm

Returns the current best-known result.

Returns:

the current best-known result

initialize

protected void initialize()

Description copied from class: AbstractAlgorithm

Performs any initialization that is required by this algorithm. This method is called automatically by the first invocation of AbstractAlgorithm.step(), but may also be called manually prior to any invocations of step. Implementations should always invoke super.initialize() to ensure the hierarchy is initialized correctly.

Overrides:

initialize in class AbstractAlgorithm

iterate

protected void iterate()

Description copied from class: AbstractAlgorithm

Performs one iteration of the algorithm. This method should be overridden by implementations to perform each logical iteration of the algorithm.

Specified by:

iterate in class AbstractAlgorithm