Package org.uma.evolver.algorithm.base.smsemoa

Class DoubleSMSEMOA

java.lang.Object

org.uma.evolver.algorithm.base.smsemoa.BaseSMSEMOA<org.uma.jmetal.solution.doublesolution.DoubleSolution>

org.uma.evolver.algorithm.base.smsemoa.DoubleSMSEMOA

All Implemented Interfaces:

BaseLevelAlgorithm<org.uma.jmetal.solution.doublesolution.DoubleSolution>

public class DoubleSMSEMOA
extends BaseSMSEMOA<org.uma.jmetal.solution.doublesolution.DoubleSolution>

Configurable implementation of the SMS-EMOA (S-Metric Selection Evolutionary Multi-Objective Algorithm) for double-valued (real-coded) problems.

This class provides a highly customizable version of SMS-EMOA, supporting:

• Various selection strategies (e.g., tournament, random)
• Multiple crossover operators (e.g., SBX, BLX-Alpha, whole arithmetic)
• Different mutation approaches (e.g., uniform, polynomial, non-uniform)
• Optional external archive integration
• Hypervolume-based selection for maintaining diversity

Usage example:

 DoubleSMSEMOA algorithm = new DoubleSMSEMOA(problem, 100, 25000);
 algorithm.parse(args);
 EvolutionaryAlgorithm<DoubleSolution> smsemoa = algorithm.build();
 smsemoa.run();
 

Non-configurable parameters such as the number of problem variables and, depending on the mutation operator, the maximum number of iterations or perturbation value, are set automatically based on the problem and algorithm configuration.

See Also:

• BaseSMSEMOA
• MutationParameter
• SMS-EMOA: Multiobjective selection based on dominated hypervolume

Field Summary

Fields inherited from class org.uma.evolver.algorithm.base.smsemoa.BaseSMSEMOA

maximumNumberOfEvaluations, parameterSpace, populationSize, problem, ranking

Constructor Summary

Constructors

Constructor	Description
DoubleSMSEMOA(int populationSize, ParameterSpace parameterSpace)	Constructs a DoubleSMSEMOA instance with the given population size and parameter space.
DoubleSMSEMOA(org.uma.jmetal.problem.Problem<org.uma.jmetal.solution.doublesolution.DoubleSolution> problem, int populationSize, int maximumNumberOfEvaluations, ParameterSpace parameterSpace)	Constructs a DoubleSMSEMOA instance with the given problem, population size, maximum number of evaluations, and parameter space.

Method Summary

Modifier and Type	Method	Description
BaseLevelAlgorithm<org.uma.jmetal.solution.doublesolution.DoubleSolution>	createInstance(org.uma.jmetal.problem.Problem<org.uma.jmetal.solution.doublesolution.DoubleSolution> problem, int maximumNumberOfEvaluations)	Creates a new instance of DoubleSMSEMOA for the given problem and maximum number of evaluations.
protected void	setNonConfigurableParameters()	Configures non-configurable parameters that depend on the problem or algorithm configuration.

Methods inherited from class org.uma.evolver.algorithm.base.smsemoa.BaseSMSEMOA

build, createEvaluation, createExternalArchive, createInitialSolutions, createReplacement, createSelection, createTermination, createVariation, parameterSpace

Methods inherited from class java.lang.Object

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

Methods inherited from interface org.uma.evolver.algorithm.base.BaseLevelAlgorithm

parse

Constructor Details

DoubleSMSEMOA

public DoubleSMSEMOA(int populationSize,
 ParameterSpace parameterSpace)

Constructs a DoubleSMSEMOA instance with the given population size and parameter space.

This constructor is typically used when the problem and maximum number of evaluations will be set later via the createInstance method.

Parameters:

populationSize - the population size to use (must be > 0)

parameterSpace - the parameter space containing the algorithm configuration

Throws:

IllegalArgumentException - if populationSize is less than or equal to 0

DoubleSMSEMOA

public DoubleSMSEMOA(org.uma.jmetal.problem.Problem<org.uma.jmetal.solution.doublesolution.DoubleSolution> problem,
 int populationSize,
 int maximumNumberOfEvaluations,
 ParameterSpace parameterSpace)

Constructs a DoubleSMSEMOA instance with the given problem, population size, maximum number of evaluations, and parameter space.

Parameters:

problem - the problem to solve (must not be null)

populationSize - the population size to use (must be > 0)

maximumNumberOfEvaluations - the maximum number of evaluations (must be > 0)

parameterSpace - the parameter space containing the algorithm configuration

Throws:

IllegalArgumentException - if populationSize or maximumNumberOfEvaluations is less than or equal to 0

NullPointerException - if problem or parameterSpace is null

Method Details

createInstance

public BaseLevelAlgorithm<org.uma.jmetal.solution.doublesolution.DoubleSolution> createInstance(org.uma.jmetal.problem.Problem<org.uma.jmetal.solution.doublesolution.DoubleSolution> problem,
 int maximumNumberOfEvaluations)

Creates a new instance of DoubleSMSEMOA for the given problem and maximum number of evaluations.

This method creates a new instance using the current configuration but with the specified problem and evaluation budget. The parameter space is cloned to ensure independent instances.

Parameters:

problem - the problem to solve (must not be null)

maximumNumberOfEvaluations - the evaluation budget (must be > 0)

Returns:

a new configured instance of DoubleSMSEMOA

Throws:

IllegalArgumentException - if maximumNumberOfEvaluations is less than or equal to 0

NullPointerException - if problem is null

setNonConfigurableParameters

protected void setNonConfigurableParameters()

Configures non-configurable parameters that depend on the problem or algorithm configuration.

This method is automatically called during the build process and sets up various parameters that cannot be directly configured through the parameter space, including:

• The number of problem variables for the mutation operator
• The maximum number of iterations for non-uniform mutation (if used)
• The perturbation value for uniform mutation (if used)
• The offspring population size for variation operators

Specified by:

setNonConfigurableParameters in class BaseSMSEMOA<org.uma.jmetal.solution.doublesolution.DoubleSolution>

Throws:

IllegalStateException - if the required parameters are not properly configured

NullPointerException - if the problem or required parameters are not set