net.sourceforge.cilib.pso
Class LFPSO

java.lang.Object
  net.sourceforge.cilib.algorithm.Algorithm
      net.sourceforge.cilib.algorithm.population.PopulationBasedAlgorithm
          net.sourceforge.cilib.algorithm.population.SinglePopulationBasedAlgorithm
              net.sourceforge.cilib.pso.PSO
                  net.sourceforge.cilib.pso.LFPSO

All Implemented Interfaces:

Serializable, Runnable, GradientOptimisationAlgorithm, ParticipatingAlgorithm, Cloneable

public class LFPSO
extends PSO
implements GradientOptimisationAlgorithm

An implementation of the LeapFrog PSO algorithm, a modified Particle Swarm Optimiser based upon the improved leapfrog dynamic method for unconstrained minimization.

References:

• J.A. Snyman, "A new and dynamic method for unconstrained minimization", Applied Mathematical Modelling, 1982, Vol. 6, December.
• J.A. Snyman, "An improved version of the original leapfrog dynamic method for unconstained minimization", Applied Mathematical Modelling, 1983, Vol. 7, June.

Author:

barlad TODO:: Need Global best update strategies

See Also:

Serialized Form

Field Summary

Fields inherited from class net.sourceforge.cilib.algorithm.population.SinglePopulationBasedAlgorithm

initialisationStrategy

Fields inherited from class net.sourceforge.cilib.algorithm.Algorithm

optimisationProblem

Constructor Summary

LFPSO()
Creates a new instance of LFPSO.

Method Summary

int	getGradientEvaluations() Returns the number of times the gradient of the function was evaluated.
GradientOptimisationProblem	getGradientOptimisationProblem() Accessor for the optimisation problem to be solved.
void	setGradientOptimisationProblem(GradientOptimisationProblem problem) Sets the optimisation problem to be solved.
void	setPrototypeParticle(Particle particle)
void	setVelocityUpdate(VelocityUpdateStrategy vu)

Methods inherited from class net.sourceforge.cilib.pso.PSO

algorithmIteration, getBestSolution, getClone, getContribution, getContributionFitness, getIterationStrategy, getSolutions, getTopology, performInitialisation, reset, setIterationStrategy, setTopology, updateContributionFitness

Methods inherited from class net.sourceforge.cilib.algorithm.population.SinglePopulationBasedAlgorithm

accept, getInitialisationStrategy, setInitialisationStrategy

Methods inherited from class net.sourceforge.cilib.algorithm.Algorithm

addAlgorithmListener, addStoppingCondition, get, getAlgorithmList, getIterations, getOptimisationProblem, getPercentageComplete, getStoppingConditions, initialise, isFinished, performIteration, performUninitialisation, removeAlgorithmListener, removeStoppingCondition, run, setOptimisationProblem, terminate

Methods inherited from class java.lang.Object

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

Constructor Detail

LFPSO

public LFPSO()

Creates a new instance of LFPSO. All fields are initialised to reasonable defaults. Note that the GradientOptimisationProblem is initially null and must be set before Algorithm.initialise() is called.

Method Detail

setPrototypeParticle

public void setPrototypeParticle(Particle particle)

setVelocityUpdate

public void setVelocityUpdate(VelocityUpdateStrategy vu)

getGradientEvaluations

public int getGradientEvaluations()

Returns the number of times the gradient of the function was evaluated. Not implemented yet.

Specified by:

getGradientEvaluations in interface GradientOptimisationAlgorithm

Returns:

The number of gradient evaluations.

getGradientOptimisationProblem

public GradientOptimisationProblem getGradientOptimisationProblem()

Description copied from interface: GradientOptimisationAlgorithm

Accessor for the optimisation problem to be solved.

Specified by:

getGradientOptimisationProblem in interface GradientOptimisationAlgorithm

Returns:

The OptimisationProblemAdapter to be solved.

setGradientOptimisationProblem

public void setGradientOptimisationProblem(GradientOptimisationProblem problem)

Description copied from interface: GradientOptimisationAlgorithm

Sets the optimisation problem to be solved.

Specified by:

setGradientOptimisationProblem in interface GradientOptimisationAlgorithm

Parameters:

problem - The OptimisationProblemAdapter to be solved.