public SBXCrossoverOffspring(double crossoverProbability, double distributionIndexForCrossover)
{
Dictionary <string, object> parameters;
this.crossoverProbability = crossoverProbability;
this.distributionIndexForCrossover = distributionIndexForCrossover;
// Crossover operator
parameters = new Dictionary <string, object>();
parameters.Add("probability", crossoverProbability);
parameters.Add("distributionIndex", distributionIndexForCrossover);
crossover = CrossoverFactory.GetCrossoverOperator("SBXCrossover", parameters);
selection = SelectionFactory.GetSelectionOperator("BinaryTournament", null);
Id = "SBXCrossover";
}
public Operator GetCrossover2()
{
string filepath = DirPath + "/Parameter.txt";
Dictionary <string, object> parameters = new Dictionary <string, object>();
string[] line7 = { Co + " " + Ra, Co2 + " " + (1 - double.Parse(Ra)) };
string[] line8 = { "gamma " + Gamma };
File.AppendAllLines(filepath, line7);
File.AppendAllLines(filepath, line8);
switch (Co2)
{
case "SBXCrossover":
parameters.Add("probability", double.Parse(poc));
parameters.Add("distributionIndex", double.Parse(dioc));
crossover2 = CrossoverFactory.GetCrossoverOperator("SBXCrossover", parameters);
break;
case "DifferentialEvolutionCrossover":
parameters.Add("CR", double.Parse(cr));
parameters.Add("F", double.Parse(f));
parameters.Add("K", double.Parse(k));
crossover2 = CrossoverFactory.GetCrossoverOperator("DifferentialEvolutionCrossover", parameters);
break;
case "ACOR":
parameters.Add("zeta", double.Parse(zeta));
crossover2 = CrossoverFactory.GetCrossoverOperator("ACOR", parameters);
break;
case null:
parameters.Add("probability", double.Parse(poc));
parameters.Add("distributionIndex", double.Parse(dioc));
parameters.Add("zeta", double.Parse(zeta));
crossover2 = CrossoverFactory.GetCrossoverOperator("null", parameters);
break;
default:
break;
}
return(crossover2);
}
public Operator[] GetCrossover()
{
string filepath = DirPath + "/Parameter.txt";
string[] line6 = { "ACOR " + ACORa, "SBXCrossover " + SBXRa, "DECrossover " + DERa };
string[] line3 = { "probabilityOfCrossover " + poc, "distributionIndexOfCrossover " + dioc };
string[] line4 = { "CR " + cr, "F " + f, "K " + k };
string[] line5 = { "zeta " + zeta, "q " + q };
Dictionary <string, object> parameters = new Dictionary <string, object>();
parameters.Add("probability", double.Parse(poc));
parameters.Add("distributionIndex", double.Parse(dioc));
crossover[1] = CrossoverFactory.GetCrossoverOperator("SBXCrossover", parameters);
parameters = new Dictionary <string, object>();
parameters.Add("CR", double.Parse(cr));
parameters.Add("F", double.Parse(f));
parameters.Add("K", double.Parse(k));
crossover[0] = CrossoverFactory.GetCrossoverOperator("DifferentialEvolutionCrossover", parameters);
parameters = new Dictionary <string, object>();
parameters.Add("zeta", double.Parse(zeta));
crossover[2] = CrossoverFactory.GetCrossoverOperator("ACOR", parameters);
File.AppendAllLines(filepath, line6);
if (DERa != "0.0")
{
File.AppendAllLines(filepath, line4);
}
if (SBXRa != "0.0")
{
File.AppendAllLines(filepath, line3);
}
if (ACORa != "0.0")
{
File.AppendAllLines(filepath, line5);
}
return(crossover);
}
/// <summary>
/// Usage:
/// - NSGAIImTSP
/// </summary>
/// <param name="args">Command line arguments.</param>
public static void Main(string[] args)
{
Problem problem; // The problem to solve
Algorithm algorithm; // The algorithm to use
Operator crossover; // Crossover operator
Operator mutation; // Mutation operator
Operator selection; // Selection operator
Dictionary <string, object> parameters; // Operator parameters
QualityIndicator indicators; // Object to get quality indicators
// Logger object and file to store log messages
var logger = Logger.Log;
var appenders = logger.Logger.Repository.GetAppenders();
var fileAppender = appenders[0] as log4net.Appender.FileAppender;
fileAppender.File = "NSGAIImTSP.log";
fileAppender.ActivateOptions();
indicators = null;
problem = new MTSP("Permutation", "kroA150.tsp", "kroB150.tsp");
algorithm = new JMetalCSharp.Metaheuristics.NSGAII.NSGAII(problem);
//algorithm = new ssNSGAII(problem);
// Algorithm parameters
algorithm.SetInputParameter("populationSize", 100);
algorithm.SetInputParameter("maxEvaluations", 10000000);
/* Crossver operator */
parameters = new Dictionary <string, object>();
parameters.Add("probability", 0.95);
//crossover = CrossoverFactory.getCrossoverOperator("TwoPointsCrossover", parameters);
crossover = CrossoverFactory.GetCrossoverOperator("PMXCrossover", parameters);
/* Mutation operator */
parameters = new Dictionary <string, object>();
parameters.Add("probability", 0.2);
mutation = MutationFactory.GetMutationOperator("SwapMutation", parameters);
/* Selection Operator */
parameters = null;
selection = SelectionFactory.GetSelectionOperator("BinaryTournament", parameters);
// Add the operators to the algorithm
algorithm.AddOperator("crossover", crossover);
algorithm.AddOperator("mutation", mutation);
algorithm.AddOperator("selection", selection);
// Add the indicator object to the algorithm
algorithm.SetInputParameter("indicators", indicators);
// Execute the Algorithm
long initTime = Environment.TickCount;
SolutionSet population = algorithm.Execute();
long estimatedTime = Environment.TickCount - initTime;
// Result messages
logger.Info("Total execution time: " + estimatedTime + "ms");
logger.Info("Variables values have been writen to file VAR");
population.PrintVariablesToFile("VAR");
logger.Info("Objectives values have been writen to file FUN");
population.PrintObjectivesToFile("FUN");
if (indicators != null)
{
logger.Info("Quality indicators");
logger.Info("Hypervolume: " + indicators.GetHypervolume(population));
logger.Info("GD : " + indicators.GetGD(population));
logger.Info("IGD : " + indicators.GetIGD(population));
logger.Info("Spread : " + indicators.GetSpread(population));
logger.Info("Epsilon : " + indicators.GetEpsilon(population));
int evaluations = (int)algorithm.GetOutputParameter("evaluations");
logger.Info("Speed : " + evaluations + " evaluations");
}
}
/// <summary>
///Usage: three choices
/// - AbYSS
/// - AbYSS problemName
/// - AbYSS problemName paretoFrontFile
/// </summary>
/// <param name="args">Command line arguments.</param>
public static void Main(string[] args)
{
Problem problem; // The problem to solve
Algorithm algorithm; // The algorithm to use
Operator crossover; // Crossover operator
Operator mutation; // Mutation operator
Operator improvement; // Operator for improvement
Dictionary <string, object> parameters; // Operator parameters
QualityIndicator indicators; // Object to get quality indicators
// Logger object and file to store log messages
var logger = Logger.Log;
var appenders = logger.Logger.Repository.GetAppenders();
var fileAppender = appenders[0] as log4net.Appender.FileAppender;
fileAppender.File = "AbYSS.log";
fileAppender.ActivateOptions();
indicators = null;
if (args.Length == 1)
{
object[] param = { "Real" };
problem = ProblemFactory.GetProblem(args[0], param);
}
else if (args.Length == 2)
{
object[] param = { "Real" };
problem = ProblemFactory.GetProblem(args[0], param);
indicators = new QualityIndicator(problem, args[1]);
}
else
{ // Default problem
problem = new Kursawe("Real", 3);
//problem = new Kursawe("BinaryReal", 3);
//problem = new Water("Real");
//problem = new ZDT4("ArrayReal", 10);
//problem = new ConstrEx("Real");
//problem = new DTLZ1("Real");
//problem = new OKA2("Real") ;
}
// STEP 2. Select the algorithm (AbYSS)
algorithm = new JMetalCSharp.Metaheuristics.AbYSS.AbYSS(problem);
// STEP 3. Set the input parameters required by the metaheuristic
algorithm.SetInputParameter("populationSize", 20);
algorithm.SetInputParameter("refSet1Size", 10);
algorithm.SetInputParameter("refSet2Size", 10);
algorithm.SetInputParameter("archiveSize", 100);
algorithm.SetInputParameter("maxEvaluations", 25000);
// STEP 4. Specify and configure the crossover operator, used in the
// solution combination method of the scatter search
parameters = new Dictionary <string, object>();
parameters.Add("probability", 0.9);
parameters.Add("distributionIndex", 20.0);
crossover = CrossoverFactory.GetCrossoverOperator("SBXCrossover", parameters);
// STEP 5. Specify and configure the improvement method. We use by default
// a polynomial mutation in this method.
parameters = new Dictionary <string, object>();
parameters.Add("probability", 1.0 / problem.NumberOfVariables);
parameters.Add("distributionIndex", 20.0);
mutation = MutationFactory.GetMutationOperator("PolynomialMutation", parameters);
parameters = new Dictionary <string, object>();
parameters.Add("improvementRounds", 1);
parameters.Add("problem", problem);
parameters.Add("mutation", mutation);
improvement = new MutationLocalSearch(parameters);
// STEP 6. Add the operators to the algorithm
algorithm.AddOperator("crossover", crossover);
algorithm.AddOperator("improvement", improvement);
long initTime = Environment.TickCount;
// STEP 7. Run the algorithm
SolutionSet population = algorithm.Execute();
long estimatedTime = Environment.TickCount - initTime;
// STEP 8. Print the results
logger.Info("Total execution time: " + estimatedTime + "ms");
logger.Info("Variables values have been writen to file VAR");
population.PrintVariablesToFile("VAR");
logger.Info("Objectives values have been writen to file FUN");
population.PrintObjectivesToFile("FUN");
Console.WriteLine("Total execution time: " + estimatedTime + "ms");
Console.ReadLine();
if (indicators != null)
{
logger.Info("Quality indicators");
logger.Info("Hypervolume: " + indicators.GetHypervolume(population));
logger.Info("GD : " + indicators.GetGD(population));
logger.Info("IGD : " + indicators.GetIGD(population));
logger.Info("Spread : " + indicators.GetSpread(population));
logger.Info("Epsilon : " + indicators.GetEpsilon(population));
}
}
/// <summary>
/// Usage: three options
/// - NSGAII
/// - NSGAII problemName
/// - NSGAII problemName paretoFrontFile
/// </summary>
/// <param name="args"></param>
public NSGAIIRunner(string[] args, Problem p, string Path, MOO comp)
{
Problem problem = p; // The problem to solve
Algorithm algorithm; // The algorithm to use
Operator crossover; // Crossover operator
Operator mutation; // Mutation operator
Operator selection; // Selection operator
this.comp = comp;
Dictionary <string, object> parameters; // Operator parameters
QualityIndicator indicators; // Object to get quality indicators
// Logger object and file to store log messages
//var logger = Logger.Log;
//var appenders = logger.Logger.Repository.GetAppenders();
//var fileAppender = appenders[0] as log4net.Appender.FileAppender;
//fileAppender.File = "NSGAII.log";
//fileAppender.ActivateOptions();
indicators = null;
//if (args.Length == 1)
//{
// object[] param = { "Real" };
// problem = ProblemFactory.GetProblem(args[0], param);
//}
//else if (args.Length == 2)
//{
// object[] param = { "Real" };
// problem = ProblemFactory.GetProblem(args[0], param);
// indicators = new QualityIndicator(problem, args[1]);
//}
//else
//{ // Default problem
// //problem = ;
// //problem = new Kursawe("BinaryReal", 3);
// //problem = new Water("Real");
// //problem = new ZDT3("ArrayReal", 30);
// //problem = new ConstrEx("Real");
// //problem = new DTLZ1("Real");
// //problem = new OKA2("Real") ;
//}
algorithm = new NSGAII(problem, comp);
//algorithm = new ssNSGAII(problem);
// Algorithm parameters
algorithm.SetInputParameter("populationSize", comp.popSize);
algorithm.SetInputParameter("maxEvaluations", comp.maxEvals);
comp.LogAddMessage("Population Size = " + comp.popSize);
comp.LogAddMessage("Max Evaluations = " + comp.maxEvals);
// Mutation and Crossover for Real codification
parameters = new Dictionary <string, object>();
parameters.Add("probability", 0.9);
parameters.Add("distributionIndex", 20.0);
crossover = CrossoverFactory.GetCrossoverOperator("SBXCrossover", parameters);
comp.LogAddMessage("Crossover Type = " + "SBXCrossover");
comp.LogAddMessage("Crossover Probability = " + 0.9);
comp.LogAddMessage("Crossover Distribution Index = " + 20);
parameters = new Dictionary <string, object>();
parameters.Add("probability", 1.0 / problem.NumberOfVariables);
parameters.Add("distributionIndex", 20.0);
mutation = MutationFactory.GetMutationOperator("PolynomialMutation", parameters);
comp.LogAddMessage("Mutation Type = " + "Polynomial Mutation");
comp.LogAddMessage("Mutation Probability = " + (1 / problem.NumberOfVariables));
comp.LogAddMessage("Mutation Distribution Index = " + 20);
// Selection Operator
parameters = null;
selection = SelectionFactory.GetSelectionOperator("BinaryTournament2", parameters);
comp.LogAddMessage("Selection Type = " + "Binary Tournament 2");
// Add the operators to the algorithm
algorithm.AddOperator("crossover", crossover);
algorithm.AddOperator("mutation", mutation);
algorithm.AddOperator("selection", selection);
// Add the indicator object to the algorithm
algorithm.SetInputParameter("indicators", indicators);
// Execute the Algorithm
long initTime = Environment.TickCount;
SolutionSet population = algorithm.Execute();
long estimatedTime = Environment.TickCount - initTime;
comp.LogAddMessage("Total Execution Time = " + estimatedTime + "ms");
// Result messages
//logger.Info("Total execution time: " + estimatedTime + "ms");
//logger.Info("Variables values have been writen to file VAR");
//population.PrintVariablesToFile(@"C:\Users\Jonathas\Desktop\text.txt");
population.PrintVariablesToFile(@"" + comp.fileName + "VAR-" + comp.fileName);
//logger.Info("Objectives values have been writen to file FUN");
population.PrintObjectivesToFile(@"" + comp.fileName + "OBJ-" + comp.fileName);
// Saving all solutions to file
//Console.WriteLine("Time: " + estimatedTime);
//Console.ReadLine();
if (indicators != null)
{
//logger.Info("Quality indicators");
//logger.Info("Hypervolume: " + indicators.GetHypervolume(population));
//logger.Info("GD : " + indicators.GetGD(population));
//logger.Info("IGD : " + indicators.GetIGD(population));
//logger.Info("Spread : " + indicators.GetSpread(population));
//logger.Info("Epsilon : " + indicators.GetEpsilon(population));
int evaluations = (int)algorithm.GetOutputParameter("evaluations");
//logger.Info("Speed : " + evaluations + " evaluations");
}
}
/// <summary>
/// Usage: three options
/// - SPEA2
/// - SPEA2 problemName
/// - SPEA2 problemName ParetoFrontFile
/// </summary>
/// <param name="args">Command line arguments. The first (optional) argument specifies the problem to solve.</param>
public static void Main(string[] args)
{
Problem problem; // The problem to solve
Algorithm algorithm; // The algorithm to use
Operator crossover; // Crossover operator
Operator mutation; // Mutation operator
Operator selection; // Selection operator
QualityIndicator indicators; // Object to get quality indicators
Dictionary <string, object> parameters; // Operator parameters
// Logger object and file to store log messages
var logger = Logger.Log;
var appenders = logger.Logger.Repository.GetAppenders();
var fileAppender = appenders[0] as log4net.Appender.FileAppender;
fileAppender.File = "SPEA2.log";
fileAppender.ActivateOptions();
indicators = null;
if (args.Length == 1)
{
object[] param = { "Real" };
problem = ProblemFactory.GetProblem(args[0], param);
}
else if (args.Length == 2)
{
object[] param = { "Real" };
problem = ProblemFactory.GetProblem(args[0], param);
indicators = new QualityIndicator(problem, args[1]);
}
else
{ // Default problem
problem = new Kursawe("Real", 3);
//problem = new Water("Real");
//problem = new ZDT1("ArrayReal", 1000);
//problem = new ZDT4("BinaryReal");
//problem = new WFG1("Real");
//problem = new DTLZ1("Real");
//problem = new OKA2("Real") ;
}
algorithm = new JMetalCSharp.Metaheuristics.SPEA2.SPEA2(problem);
// Algorithm parameters
algorithm.SetInputParameter("populationSize", 100);
algorithm.SetInputParameter("archiveSize", 100);
algorithm.SetInputParameter("maxEvaluations", 25000);
// Mutation and Crossover for Real codification
parameters = new Dictionary <string, object>();
parameters.Add("probability", 0.9);
parameters.Add("distributionIndex", 20.0);
crossover = CrossoverFactory.GetCrossoverOperator("SBXCrossover", parameters);
parameters = new Dictionary <string, object>();
parameters.Add("probability", 1.0 / problem.NumberOfVariables);
parameters.Add("distributionIndex", 20.0);
mutation = MutationFactory.GetMutationOperator("PolynomialMutation", parameters);
// Selection operator
parameters = null;
selection = SelectionFactory.GetSelectionOperator("BinaryTournament", parameters);
// Add the operators to the algorithm
algorithm.AddOperator("crossover", crossover);
algorithm.AddOperator("mutation", mutation);
algorithm.AddOperator("selection", selection);
// Execute the algorithm
long initTime = Environment.TickCount;
SolutionSet population = algorithm.Execute();
long estimatedTime = Environment.TickCount - initTime;
// Result messages
logger.Info("Total execution time: " + estimatedTime + "ms");
logger.Info("Objectives values have been writen to file FUN");
population.PrintObjectivesToFile("FUN");
logger.Info("Variables values have been writen to file VAR");
population.PrintVariablesToFile("VAR");
if (indicators != null)
{
logger.Info("Quality indicators");
logger.Info("Hypervolume: " + indicators.GetHypervolume(population));
logger.Info("GD : " + indicators.GetGD(population));
logger.Info("IGD : " + indicators.GetIGD(population));
logger.Info("Spread : " + indicators.GetSpread(population));
logger.Info("Epsilon : " + indicators.GetEpsilon(population));
}
Console.WriteLine("Total execution time: " + estimatedTime + "ms");
Console.ReadLine();
}
public Operator GetCrossover()
{
if (Co2 != "")
{
DirPath = "Result/" + Al + "_" + Co + "_" + Co2 + "/" + Pb + "_" + St;
}
else
{
DirPath = "Result/" + Al + "_" + Co + "/" + Pb + "_" + St;
}
if (Directory.Exists(DirPath))
{
Console.WriteLine("The directory {0} already exists.", DirPath);
}
else
{
Directory.CreateDirectory(DirPath);
Console.WriteLine("The directory {0} was created.", DirPath);
}
string filepath = DirPath + "/Parameter.txt";
string[] line3 = { "probabilityOfCrossover " + poc, "distributionIndexOfCrossover " + dioc };
string[] line4 = { "CR " + cr, "F " + f, "K " + k };
string[] line5 = { "zeta " + zeta, "q " + q };
Dictionary <string, object> parameters = new Dictionary <string, object>();
switch (Co)
{
case "SBXCrossover":
parameters.Add("probability", double.Parse(poc));
parameters.Add("distributionIndex", double.Parse(dioc));
crossover = CrossoverFactory.GetCrossoverOperator("SBXCrossover", parameters);
File.AppendAllLines(filepath, line3);
break;
case "DifferentialEvolutionCrossover":
parameters.Add("CR", double.Parse(cr));
parameters.Add("F", double.Parse(f));
parameters.Add("K", double.Parse(k));
crossover = CrossoverFactory.GetCrossoverOperator("DifferentialEvolutionCrossover", parameters);
File.AppendAllLines(filepath, line4);
break;
case "ACOR":
parameters.Add("zeta", double.Parse(zeta));
crossover = CrossoverFactory.GetCrossoverOperator("ACOR", parameters);
File.AppendAllLines(filepath, line5);
break;
case null:
parameters.Add("probability", double.Parse(poc));
parameters.Add("distributionIndex", double.Parse(dioc));
parameters.Add("zeta", double.Parse(zeta));
crossover = CrossoverFactory.GetCrossoverOperator("null", parameters);
File.AppendAllLines(filepath, line3);
File.AppendAllLines(filepath, line5);
break;
default:
break;
}
return(crossover);
}
static void Main()
{
Application.EnableVisualStyles();
Application.SetCompatibleTextRenderingDefault(false);
Application.Run(new LoadConfig());
// VariabilityModel model = new VariabilityModel("Model1");
// InfluenceModel infModel = new InfluenceModel(model, new NFProperty("Test"));
// BettyFileParser bfp = new BettyFileParser(model, infModel);
String[] file = System.IO.File.ReadAllLines(@"C:\Users\Tom\Desktop\Masterarbeit\SPLConqueror\SPLConqueror\BettyConqueror\FeatureModel0.afm");
// bfp.readConfiguration(file);
//ILArray<float> A = ILMath.tosingle()
//ILArray<float> A = ILMath.tosingle(ILMath.rand(3, 100));
// RDotNet.NativeLibrary.UnmanagedDll.SetDllDirectory(@"C:\Program Files\R\R-3.2.0\bin\i386\R.dll");
engine = REngine.GetInstance();
NumericVector group1 = engine.CreateNumericVector(new double[] { 30.02, 29.99, 30.11, 29.97, 30.01, 29.99 });
engine.SetSymbol("group1", group1);
// e.Evaluate("hist(group1)");
// e.Evaluate("hist(group1)");
Problem problem;
Operator crossover; // Crossover operator
Operator mutation; // Mutation operator
Operator selection; // Selection operator
var logger = Logger.Log;
// var appenders = logger.Logger.Repository.GetAppenders();
// var fileAppender = appenders[0] as log4net.Appender.FileAppender;
// fileAppender.File = "NSGAII.log";
//.ActivateOptions();
Dictionary <string, object> parameters; // Operator parameters
QualityIndicator indicators; // Object to get quality indicators
problem = new GeneratorProblem("Real", 30);
NSGAII algorithm = new NSGAII(problem);
indicators = null;
algorithm.SetInputParameter("populationSize", 200);
algorithm.SetInputParameter("maxEvaluations", 25000);
// Mutation and Crossover for Real codification
parameters = new Dictionary <string, object>();
parameters.Add("probability", 0.9);
parameters.Add("distributionIndex", 20.0);
crossover = CrossoverFactory.GetCrossoverOperator("SBXCrossover", parameters);
parameters = new Dictionary <string, object>();
parameters.Add("probability", 1.0 / problem.NumberOfVariables);
parameters.Add("distributionIndex", 20.0);
mutation = MutationFactory.GetMutationOperator("PolynomialMutation", parameters);
// Selection Operator
parameters = null;
selection = SelectionFactory.GetSelectionOperator("BinaryTournament2", parameters);
// Add the operators to the algorithm
algorithm.AddOperator("crossover", crossover);
algorithm.AddOperator("mutation", mutation);
algorithm.AddOperator("selection", selection);
// Add the indicator object to the algorithm
algorithm.SetInputParameter("indicators", indicators);
// Execute the Algorithm
long initTime = Environment.TickCount;
//SolutionSet population = algorithm.Execute();
long estimatedTime = Environment.TickCount - initTime;
logger.Info("Variables values have been writen to file VAR");
//population.PrintVariablesToFile("VAR");
logger.Info("Objectives values have been writen to file FUN");
// population.PrintObjectivesToFile("FUN");
Console.WriteLine("Time: " + estimatedTime);
Console.ReadLine();
//Application.Run(new Form1(e, group1, new double[] { 30.02, 29.99, 30.11, 29.97, 30.01, 29.99, 1.3, 1.7, 9.4, 11.1 }));
}
/// <summary>
///Usage: three choices
/// - GDE3
/// - GDE3 problemName
/// - GDE3 problemName paretoFrontFile
/// </summary>
/// <param name="args">Command line arguments.</param>
public static void Main(string[] args)
{
Problem problem; // The problem to solve
Algorithm algorithm; // The algorithm to use
Operator selection;
Operator crossover;
Dictionary <string, object> parameters; // Operator parameters
QualityIndicator indicators; // Object to get quality indicators
// Logger object and file to store log messages
var logger = Logger.Log;
var appenders = logger.Logger.Repository.GetAppenders();
var fileAppender = appenders[0] as log4net.Appender.FileAppender;
fileAppender.File = "GDE3.log";
fileAppender.ActivateOptions();
indicators = null;
if (args.Length == 1)
{
object[] param = { "Real" };
problem = ProblemFactory.GetProblem(args[0], param);
}
else if (args.Length == 2)
{
object[] param = { "Real" };
problem = ProblemFactory.GetProblem(args[0], param);
indicators = new QualityIndicator(problem, args[1]);
}
else
{ // Default problem
problem = new Kursawe("Real", 3);
//problem = new Water("Real");
//problem = new ZDT1("ArrayReal", 100);
//problem = new ConstrEx("Real");
//problem = new DTLZ1("Real");
//problem = new OKA2("Real") ;
}
algorithm = new JMetalCSharp.Metaheuristics.GDE3.GDE3(problem);
// Algorithm parameters
algorithm.SetInputParameter("populationSize", 100);
algorithm.SetInputParameter("maxIterations", 250);
// Crossover operator
parameters = new Dictionary <string, object>();
parameters.Add("CR", 0.5);
parameters.Add("F", 0.5);
crossover = CrossoverFactory.GetCrossoverOperator("DifferentialEvolutionCrossover", parameters);
// Add the operators to the algorithm
parameters = null;
selection = SelectionFactory.GetSelectionOperator("DifferentialEvolutionSelection", parameters);
algorithm.AddOperator("crossover", crossover);
algorithm.AddOperator("selection", selection);
// Execute the Algorithm
long initTime = Environment.TickCount;
SolutionSet population = algorithm.Execute();
long estimatedTime = Environment.TickCount - initTime;
// Result messages
logger.Info("Total execution time: " + estimatedTime + "ms");
logger.Info("Objectives values have been writen to file FUN");
population.PrintObjectivesToFile("FUN");
logger.Info("Variables values have been writen to file VAR");
population.PrintVariablesToFile("VAR");
if (indicators != null)
{
logger.Info("Quality indicators");
logger.Info("Hypervolume: " + indicators.GetHypervolume(population));
logger.Info("GD : " + indicators.GetGD(population));
logger.Info("IGD : " + indicators.GetIGD(population));
logger.Info("Spread : " + indicators.GetSpread(population));
logger.Info("Epsilon : " + indicators.GetEpsilon(population));
}
Console.WriteLine("Total execution time gde: moead" + estimatedTime + "ms");
Console.ReadLine();
}
/// <summary>
/// Usage: three options
/// - PMOEAD
/// - PMOEAD problemName
/// - PMOEAD problemName ParetoFrontFile
/// - PMOEAD problemName numberOfThreads dataDirectory
/// </summary>
/// <param name="args">Command line arguments. The first (optional) argument specifies the problem to solve.</param>
public static void Main(string[] args)
{
Problem problem; // The problem to solve
Algorithm algorithm; // The algorithm to use
Operator crossover; // Crossover operator
Operator mutation; // Mutation operator
QualityIndicator indicators; // Object to get quality indicators
Dictionary <string, object> parameters; // Operator parameters
int numberOfThreads = 4;
string dataDirectory = "";
// Logger object and file to store log messages
var logger = Logger.Log;
var appenders = logger.Logger.Repository.GetAppenders();
var fileAppender = appenders[0] as log4net.Appender.FileAppender;
fileAppender.File = "PMOEAD.log";
fileAppender.ActivateOptions();
indicators = null;
if (args.Length == 1)
{ // args[0] = problem name
object[] paramsList = { "Real" };
problem = ProblemFactory.GetProblem(args[0], paramsList);
}
else if (args.Length == 2)
{ // args[0] = problem name, [1] = pareto front file
object[] paramsList = { "Real" };
problem = ProblemFactory.GetProblem(args[0], paramsList);
indicators = new QualityIndicator(problem, args[1]);
}
else if (args.Length == 3)
{ // args[0] = problem name, [1] = threads, [2] = data directory
object[] paramsList = { "Real" };
problem = ProblemFactory.GetProblem(args[0], paramsList);
numberOfThreads = int.Parse(args[1]);
dataDirectory = args[2];
}
else
{ // Problem + number of threads + data directory
problem = new Kursawe("Real", 3);
//problem = new Kursawe("BinaryReal", 3);
//problem = new Water("Real");
//problem = new ZDT1("ArrayReal", 100);
//problem = new ConstrEx("Real");
//problem = new DTLZ1("Real");
//problem = new OKA2("Real") ;
}
algorithm = new JMetalCSharp.Metaheuristics.MOEAD.PMOEAD(problem);
// Algorithm parameters
algorithm.SetInputParameter("populationSize", 300);
algorithm.SetInputParameter("maxEvaluations", 150000);
algorithm.SetInputParameter("numberOfThreads", numberOfThreads);
// Directory with the files containing the weight vectors used in
// Q. Zhang, W. Liu, and H Li, The Performance of a New Version of MOEA/D
// on CEC09 Unconstrained MOP Test Instances Working Report CES-491, School
// of CS & EE, University of Essex, 02/2009.
// http://dces.essex.ac.uk/staff/qzhang/MOEAcompetition/CEC09final/code/ZhangMOEADcode/moead0305.rar
algorithm.SetInputParameter("dataDirectory", "Data/Parameters/Weight");
algorithm.SetInputParameter("T", 20);
algorithm.SetInputParameter("delta", 0.9);
algorithm.SetInputParameter("nr", 2);
// Crossover operator
parameters = new Dictionary <string, object>();
parameters.Add("CR", 1.0);
parameters.Add("F", 0.5);
crossover = CrossoverFactory.GetCrossoverOperator("DifferentialEvolutionCrossover", parameters);
// Mutation operator
parameters = new Dictionary <string, object>();
parameters.Add("probability", 1.0 / problem.NumberOfVariables);
parameters.Add("distributionIndex", 20.0);
mutation = MutationFactory.GetMutationOperator("PolynomialMutation", parameters);
algorithm.AddOperator("crossover", crossover);
algorithm.AddOperator("mutation", mutation);
// Execute the Algorithm
long initTime = Environment.TickCount;
SolutionSet population = algorithm.Execute();
long estimatedTime = Environment.TickCount - initTime;
// Result messages
logger.Info("Total execution time: " + estimatedTime + " ms");
logger.Info("Objectives values have been writen to file FUN");
population.PrintObjectivesToFile("FUN");
logger.Info("Variables values have been writen to file VAR");
population.PrintVariablesToFile("VAR");
Console.ReadLine();
if (indicators != null)
{
logger.Info("Quality indicators");
logger.Info("Hypervolume: " + indicators.GetHypervolume(population));
logger.Info("GD : " + indicators.GetGD(population));
logger.Info("IGD : " + indicators.GetIGD(population));
logger.Info("Spread : " + indicators.GetSpread(population));
}
}