/// <summary>
/// Returns a permutation vector between the 0 and (length - 1)
/// </summary>
/// <param name="length"></param>
/// <returns></returns>
public int[] IntPermutation(int length)
{
int[] aux = new int[length];
int[] result = new int[length];
// First, create an array from 0 to length - 1.
// Also is needed to create an random array of size length
for (int i = 0; i < length; i++)
{
result[i] = i;
aux[i] = JMetalRandom.Next(0, length - 1);
}
// Sort the random array with effect in result, and then we obtain a
// permutation array between 0 and length - 1
for (int i = 0; i < length; i++)
{
for (int j = i + 1; j < length; j++)
{
if (aux[i] > aux[j])
{
int tmp;
tmp = aux[i];
aux[i] = aux[j];
aux[j] = tmp;
tmp = result[i];
result[i] = result[j];
result[j] = tmp;
}
}
}
return(result);
}
/// <summary>
/// Perform the mutation operation
/// </summary>
/// <param name="probability">Mutation probability</param>
/// <param name="solution">The solution to mutate</param>
private void DoMutation(double probability, Solution solution)
{
XReal x = new XReal(solution);
for (int var = 0; var < solution.Variable.Length; var++)
{
if (JMetalRandom.NextDouble() < probability)
{
double rand = JMetalRandom.NextDouble();
double tmp;
if (rand <= 0.5)
{
tmp = Delta(x.GetUpperBound(var) - x.GetValue(var), perturbation.Value);
tmp += x.GetValue(var);
}
else
{
tmp = Delta(x.GetLowerBound(var) - x.GetValue(var), perturbation.Value);
tmp += x.GetValue(var);
}
if (tmp < x.GetLowerBound(var))
{
tmp = x.GetLowerBound(var);
}
else if (tmp > x.GetUpperBound(var))
{
tmp = x.GetUpperBound(var);
}
x.SetValue(var, tmp);
}
}
}
public override Solution GetOffspring(SolutionSet solutionSet, int index)
{
Solution[] parents = new Solution[3];
Solution offSpring = null;
try
{
int r1, r2;
do
{
r1 = JMetalRandom.Next(0, solutionSet.Size() - 1);
} while (r1 == index);
do
{
r2 = JMetalRandom.Next(0, solutionSet.Size() - 1);
} while (r2 == index || r2 == r1);
parents[0] = solutionSet.Get(r1);
parents[1] = solutionSet.Get(r2);
parents[2] = solutionSet.Get(index);
offSpring = (Solution)crossover.Execute(new object[] { solutionSet.Get(index), parents });
}
catch (Exception ex)
{
Logger.Log.Error("Exception in " + this.GetType().FullName + ".GetOffSpring()", ex);
Console.Error.WriteLine("Exception in " + this.GetType().FullName + ".GetOffSpring()");
}
//Create a new solution, using DE
return(offSpring);
}
/// <summary>
///
/// </summary>
/// <param name="list">the set of the indexes of selected mating parents</param>
/// <param name="cid">the id of current subproblem</param>
/// <param name="size">the number of selected mating parents</param>
/// <param name="type">1 - neighborhood; otherwise - whole population</param>
private void MatingSelection(List <int> list, int cid, int size, int type)
{
int ss;
int r;
int p;
ss = neighborhood[cid].Length;
while (list.Count < size)
{
if (type == 1)
{
r = JMetalRandom.Next(0, ss - 1);
p = neighborhood[cid][r];
}
else
{
p = JMetalRandom.Next(0, populationSize - 1);
}
bool flag = true;
for (int i = 0; i < list.Count; i++)
{
if (list[i] == p) // p is in the list
{
flag = false;
break;
}
}
if (flag)
{
list.Add(p);
}
}
}
/// <summary>
/// Executes the operation
/// </summary>
/// <param name="obj">An object containing the population and the position (index) of the current individual</param>
/// <returns>An object containing the three selected parents</returns>
public override object Execute(object obj)
{
object[] parameters = (object[])obj;
SolutionSet population = (SolutionSet)parameters[0];
int index = (int)parameters[1];
Solution[] parents = new Solution[3];
int r1, r2, r3;
if (population.Size() < 4)
{
throw new Exception("DifferentialEvolutionSelection: the population has less than four solutions");
}
do
{
r1 = (int)(JMetalRandom.Next(0, population.Size() - 1));
} while (r1 == index);
do
{
r2 = (int)(JMetalRandom.Next(0, population.Size() - 1));
} while (r2 == index || r2 == r1);
do
{
r3 = (int)(JMetalRandom.Next(0, population.Size() - 1));
} while (r3 == index || r3 == r1 || r3 == r2);
parents[0] = population.Get(r1);
parents[1] = population.Get(r2);
parents[2] = population.Get(r3);
return(parents);
}
/// <summary>
/// Performs the operation
/// </summary>
/// <param name="obj">Object representing a SolutionSet. This solution set must be an instancen <code>AdaptiveGridArchive</code></param>
/// <returns>the selected solution</returns>
public override object Execute(object obj)
{
try
{
AdaptiveGridArchive archive = (AdaptiveGridArchive)obj;
int selected;
int hypercube1 = archive.Grid.RandomOccupiedHypercube();
int hypercube2 = archive.Grid.RandomOccupiedHypercube();
if (hypercube1 != hypercube2)
{
if (archive.Grid.GetLocationDensity(hypercube1) < archive.Grid.GetLocationDensity(hypercube2))
{
selected = hypercube1;
}
else if (archive.Grid.GetLocationDensity(hypercube2) <
archive.Grid.GetLocationDensity(hypercube1))
{
selected = hypercube2;
}
else
{
if (JMetalRandom.NextDouble() < 0.5)
{
selected = hypercube2;
}
else
{
selected = hypercube1;
}
}
}
else
{
selected = hypercube1;
}
int bas = JMetalRandom.Next(0, archive.Size() - 1);
int cnt = 0;
while (cnt < archive.Size())
{
Solution individual = archive.Get((bas + cnt) % archive.Size());
if (archive.Grid.Location(individual) != selected)
{
cnt++;
}
else
{
return(individual);
}
}
return(archive.Get((bas + cnt) % archive.Size()));
}
catch (InvalidCastException ex)
{
Logger.Log.Error("Exception in " + this.GetType().FullName + ".Execute()", ex);
throw new Exception("Exception in " + this.GetType().FullName + ".Execute()");
}
}
//double[] pro = new double[2];
/// <summary>
///
/// </summary>
/// <param name="cid">the id of current subproblem</param>
/// <param name="type">1 - minimum; otherwise - whole neighborhood probability</param>
public int ACOrSelection(int cid, int type)
{
int ss;
ss = neighborhood[cid].Length;
double r;
int p = neighborhood[cid][0];
Solution[] parents = new Solution[ss];
double[] fitness = new double[ss];
int indexOfmin = 0;
double sum = 0;
double[] pro = new double[ss];
double a1 = 0;
double a2 = 0;
if (type == 1)
{
for (int i = 0; i < ss; i++)
{
parents[i] = population.Get(neighborhood[cid][i]);
fitness[i] = FitnessFunction(parents[i], lambda[cid]);
if (fitness[i] < FitnessFunction(population.Get(p), lambda[cid]))
{
indexOfmin = i;
}
p = neighborhood[cid][indexOfmin];
}
}
else
{
for (int i = 0; i < ss; i++)
{
parents[i] = population.Get(neighborhood[cid][i]);
fitness[i] = 1 / FitnessFunction(parents[i], lambda[cid]);
sum = sum + fitness[i];
}
for (int j = 0; j < ss; j++)
{
pro[j] = fitness[j] / sum;
}
r = JMetalRandom.NextDouble();
for (int k = 0; k < pro.Length; k++)
{
a2 = a2 + pro[k];
if (r < a2 && r >= a1)
{
p = neighborhood[cid][k];
break;
}
a1 = a1 + pro[k];
}
}
return(p);
}
/// <summary>
/// Calculates the delta value used in NonUniform mutation operator
/// </summary>
/// <param name="y"></param>
/// <param name="bMutationParameter"></param>
/// <returns></returns>
private double Delta(double y, double bMutationParameter)
{
double rand = JMetalRandom.NextDouble();
int it, maxIt;
it = currentIteration.Value;
maxIt = maxIterations;
return(y * (1.0 - Math.Pow(rand, Math.Pow((1.0 - it / (double)maxIt), bMutationParameter))));
}
/// <summary>
/// DoMutation method
/// </summary>
/// <param name="realProbability"></param>
/// <param name="binaryProbability"></param>
/// <param name="solution"></param>
private void DoMutation(double realProbability, double binaryProbability, Solution solution)
{
double rnd, delta1, delta2, mut_pow, deltaq;
double y, yl, yu, val, xy;
XReal x = new XReal(solution);
Binary binaryVariable = (Binary)solution.Variable[1];
// Polynomial mutation applied to the array real
for (int var = 0; var < x.Size(); var++)
{
if (JMetalRandom.NextDouble() <= realProbability)
{
y = x.GetValue(var);
yl = x.GetLowerBound(var);
yu = x.GetUpperBound(var);
delta1 = (y - yl) / (yu - yl);
delta2 = (yu - y) / (yu - yl);
rnd = JMetalRandom.NextDouble();
mut_pow = 1.0 / (eta_m + 1.0);
if (rnd <= 0.5)
{
xy = 1.0 - delta1;
val = 2.0 * rnd + (1.0 - 2.0 * rnd) * (Math.Pow(xy, (distributionIndex + 1.0)));
deltaq = Math.Pow(val, mut_pow) - 1.0;
}
else
{
xy = 1.0 - delta2;
val = 2.0 * (1.0 - rnd) + 2.0 * (rnd - 0.5) * (Math.Pow(xy, (distributionIndex + 1.0)));
deltaq = 1.0 - (Math.Pow(val, mut_pow));
}
y = y + deltaq * (yu - yl);
if (y < yl)
{
y = yl;
}
if (y > yu)
{
y = yu;
}
x.SetValue(var, y);
}
}
// BitFlip mutation applied to the binary part
for (int i = 0; i < binaryVariable.NumberOfBits; i++)
{
if (JMetalRandom.NextDouble() < binaryProbability)
{
binaryVariable.Bits.Flip(i);
}
}
}
/// <summary>
/// Constructor
/// </summary>
/// <param name="size">Size of the array</param>
/// <param name="problem"></param>
public ArrayReal(int size, Problem problem)
{
this.problem = problem;
Size = size;
Array = new double[Size];
for (int i = 0; i < Size; i++)
{
double val = JMetalRandom.NextDouble() * (this.problem.UpperLimit[i] - this.problem.LowerLimit[i]) + this.problem.LowerLimit[i];
Array[i] = val;
}
}
/// <summary>
/// Constructor
/// </summary>
/// <param name="size">The size of the array</param>
/// <param name="lowerBounds">Lower bounds</param>
/// <param name="upperBounds">Upper bounds</param>
public ArrayInt(int size, double[] lowerBounds, double[] upperBounds)
{
Size = size;
Array = new int[Size];
LowerBound = new int[Size];
UpperBound = new int[Size];
for (int i = 0; i < Size; i++)
{
LowerBound[i] = (int)lowerBounds[i];
UpperBound[i] = (int)upperBounds[i];
Array[i] = JMetalRandom.Next(LowerBound[i], UpperBound[i]);
}
}
/// <summary>
///
/// </summary>
/// <param name="list">the set of the indexes of selected mating parents</param>
/// <param name="cid">the id of current subproblem</param>
/// <param name="type">1 - neighborhood; otherwise - whole population</param>
public int ACOrSelection2(int cid, int type, double[] pro)
{
double r;
int b = neighborhood[cid][0];
Solution[] parents = new Solution[t];
Solution[] parent = new Solution[populationSize];
double[] fitness = new double[t];
double[] fit = new double[populationSize];
Dictionary <int, double> tmp = new Dictionary <int, double>();
Dictionary <int, double> resultSort = new Dictionary <int, double>();
double a1 = 0;
double a2 = 0;
r = JMetalRandom.NextDouble();
for (int k = 0; k < pro.Length; k++)
{
a2 = a2 + pro[k];
if (r < a2 && r >= a1)
{
b = k;
break;
}
a1 = a1 + pro[k];
}
if (type == 1)
{
for (int i = 0; i < t; i++)
{
parents[i] = population.Get(neighborhood[cid][i]);
fitness[i] = FitnessFunction(parents[i], lambda[cid]);
tmp.Add(neighborhood[cid][i], fitness[i]);
}
}
else
{
for (int i = 0; i < populationSize; i++)
{
parent[i] = population.Get(i);
fit[i] = FitnessFunction(parent[i], lambda[cid]);
tmp.Add(i, fit[i]);
}
}
resultSort = tmp.OrderBy(Data => Data.Value).ToDictionary(keyvalue => keyvalue.Key, keyvalue => keyvalue.Value);
int[] person = resultSort.Keys.ToArray();
return(person[b]);
}
/// <summary>
/// Perform the mutation operation
/// </summary>
/// <param name="probability">Mutation probability</param>
/// <param name="solution">The solution to mutate</param>
private void DoMutation(Solution solution)
{
double rnd, delta1, delta2, mut_pow, deltaq;
double y, yl, yu, val, xy;
mutationProbability = mutationProbability - solution.NumberofReplace * 0.001;
if (mutationProbability <= 0.1)
{
mutationProbability = 0.1;
}
XReal x = new XReal(solution);
for (int var = 0; var < solution.NumberOfVariables(); var++)
{
if (JMetalRandom.NextDouble() <= mutationProbability)
{
y = x.GetValue(var);
yl = x.GetLowerBound(var);
yu = x.GetUpperBound(var);
delta1 = (y - yl) / (yu - yl);
delta2 = (yu - y) / (yu - yl);
rnd = JMetalRandom.NextDouble();
mut_pow = 1.0 / (eta_m + 1.0);
if (rnd <= 0.5)
{
xy = 1.0 - delta1;
val = 2.0 * rnd + (1.0 - 2.0 * rnd) * (Math.Pow(xy, (distributionIndex + 1.0)));
deltaq = Math.Pow(val, mut_pow) - 1.0;
}
else
{
xy = 1.0 - delta2;
val = 2.0 * (1.0 - rnd) + 2.0 * (rnd - 0.5) * (Math.Pow(xy, (distributionIndex + 1.0)));
deltaq = 1.0 - (Math.Pow(val, mut_pow));
}
y = y + deltaq * (yu - yl);
if (y < yl)
{
y = yl;
}
if (y > yu)
{
y = yu;
}
x.SetValue(var, y);
}
}
}
/// <summary>
/// /Update the speed of each particle
/// </summary>
/// <param name="iter"></param>
/// <param name="miter"></param>
private void ComputeSpeed(int iter, int miter)
{
double r1, r2, W, C1, C2;
double wmax, wmin;
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 = JMetalRandom.Next(0, Leaders.Size() - 1);
int pos2 = JMetalRandom.Next(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 = JMetalRandom.NextDouble(r1Min, r1Max);
r2 = JMetalRandom.NextDouble(r2Min, r2Max);
C1 = JMetalRandom.NextDouble(C1Min, C1Max);
C2 = JMetalRandom.NextDouble(C2Min, C2Max);
W = JMetalRandom.NextDouble(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,
deltaMin,
var,
i);
}
}
}
/// <summary>
/// Constructor
/// </summary>
/// <param name="size">Size of the array</param>
public ArrayInt(int size, Problem problem)
{
_problem = problem;
Size = size;
Array = new int[size];
LowerBound = new int[size];
UpperBound = new int[size];
for (int i = 0; i < Size; i++)
{
LowerBound[i] = (int)_problem.LowerLimit[i];
UpperBound[i] = (int)_problem.UpperLimit[i];
Array[i] = JMetalRandom.Next(LowerBound[i], UpperBound[i]);
}
}
/// <summary>
/// Returns a <code>Solution</code> using the diversification generation method
/// described in the scatter search template.
/// </summary>
/// <returns></returns>
public Solution DiversificationGeneration()
{
Solution solution;
solution = new Solution(this.Problem);
XReal wrapperSolution = new XReal(solution);
double value;
int range;
for (int i = 0; i < this.Problem.NumberOfVariables; i++)
{
sumOfReverseFrequencyValues[i] = 0;
for (int j = 0; j < numberOfSubranges; j++)
{
reverseFrequency[j][i] = sumOfFrequencyValues[i] - frequency[j][i];
sumOfReverseFrequencyValues[i] += reverseFrequency[j][i];
}
if (sumOfReverseFrequencyValues[i] == 0)
{
range = JMetalRandom.Next(0, numberOfSubranges - 1);
}
else
{
value = JMetalRandom.Next(0, sumOfReverseFrequencyValues[i] - 1);
range = 0;
while (value > reverseFrequency[range][i])
{
value -= reverseFrequency[range][i];
range++;
}
}
frequency[range][i]++;
sumOfFrequencyValues[i]++;
double low = this.Problem.LowerLimit[i] + range * (this.Problem.UpperLimit[i] -
this.Problem.LowerLimit[i]) / numberOfSubranges;
double high = low + (this.Problem.UpperLimit[i] -
this.Problem.LowerLimit[i]) / numberOfSubranges;
value = JMetalRandom.NextDouble(low, high);
wrapperSolution.SetValue(i, value);
}
return(solution);
}
/// <summary>
/// Perform the crossover operation
/// </summary>
/// <param name="probability">Crossover probability</param>
/// <param name="parent1">The first parent</param>
/// <param name="parent2">The second parent</param>
/// <returns>An array containing the two offsprings</returns>
public Solution[] DoCrossover(double?probability, Solution parent1, Solution parent2)
{
Solution[] offSpring = new Solution[2];
offSpring[0] = new Solution(parent1);
offSpring[1] = new Solution(parent2);
try
{
if (JMetalRandom.NextDouble() < probability)
{
for (int i = 0; i < parent1.Variable.Length; i++)
{
Binary p1 = (Binary)parent1.Variable[i];
Binary p2 = (Binary)parent2.Variable[i];
for (int bit = 0; bit < p1.NumberOfBits; bit++)
{
if (p1.Bits[bit] != p2.Bits[bit])
{
if (JMetalRandom.NextDouble() < 0.5)
{
((Binary)offSpring[0].Variable[i])
.Bits[bit] = p2.Bits[bit];
((Binary)offSpring[1].Variable[i])
.Bits[bit] = p1.Bits[bit];
}
}
}
}
//7. Decode the results
for (int i = 0; i < offSpring[0].Variable.Length; i++)
{
((Binary)offSpring[0].Variable[i]).Decode();
((Binary)offSpring[1].Variable[i]).Decode();
}
}
}
catch (InvalidCastException ex)
{
Logger.Log.Error("Error in " + this.GetType().FullName + ".DoCrossover()", ex);
Console.WriteLine("Error in " + this.GetType().FullName + ".DoCrossover()");
throw new Exception("Exception in " + this.GetType().FullName + ".DoCrossover()");
}
return(offSpring);
}
/// <summary>
/// This method executes the operator represented by the current object.
/// </summary>
/// <param name="obj">A Solution object.</param>
public override object Execute(object obj)
{
var solutionSet = obj as SolutionSet;
var solutions = solutionSet.SolutionsList;
var bestPerformance = solutions.OrderBy(s => s.Objective [0]).Last();
var bestArea = solutions.OrderBy(s => s.Objective [1]).First();
if (JMetalRandom.NextDouble() > 0.5)
{
return(DeepCopy(bestPerformance));
}
else
{
return(DeepCopy(bestArea));
}
}
/// <summary>
/// Perform the mutation operation
/// </summary>
/// <param name="probability">Mutation probability</param>
/// <param name="solution">The solution to mutate</param>
private void DoMutation(double probability, Solution solution)
{
XReal v = new XReal(solution);
try
{
if ((solution.Type.GetType() == typeof(BinarySolutionType)) ||
(solution.Type.GetType() == typeof(BinaryRealSolutionType)))
{
for (int i = 0; i < solution.Variable.Length; i++)
{
for (int j = 0; j < ((Binary)solution.Variable[i]).NumberOfBits; j++)
{
if (JMetalRandom.NextDouble() < probability)
{
((Binary)solution.Variable[i]).Bits.Flip(j);
}
}
}
for (int i = 0; i < solution.Variable.Length; i++)
{
((Binary)solution.Variable[i]).Decode();
}
}
else
{ // Integer representation
for (int i = 0; i < solution.Variable.Length; i++)
{
if (JMetalRandom.NextDouble() < probability)
{
int value = JMetalRandom.Next(
(int)v.GetLowerBound(i),
(int)v.GetUpperBound(i));
v.SetValue(i, value);
}
}
}
}
catch (Exception ex)
{
Logger.Log.Error("Error in " + this.GetType().FullName + ".DoMutation()", ex);
Console.WriteLine("Error in " + this.GetType().FullName + ".DoMutation()");
throw new Exception("Exception in " + this.GetType().FullName + ".DoMutation()");
}
}
/// <summary>
/// Performs the operation
/// </summary>
/// <param name="obj">Object representing a SolutionSet.</param>
/// <returns>An object representing an array with the selected parents</returns>
public override object Execute(object obj)
{
SolutionSet population = (SolutionSet)obj;
int pos1, pos2;
pos1 = JMetalRandom.Next(0, population.Size() - 1);
pos2 = JMetalRandom.Next(0, population.Size() - 1);
while ((pos1 == pos2) && (population.Size() > 1))
{
pos2 = JMetalRandom.Next(0, population.Size() - 1);
}
Solution[] parents = new Solution[2];
parents[0] = population.Get(pos1);
parents[1] = population.Get(pos2);
return(parents);
}
/// <summary>
/// Constructor
/// </summary>
/// <param name="numberOfBits">Length of the bit string</param>
public Binary(int numberOfBits)
{
this.NumberOfBits = numberOfBits;
this.Bits = new BitSet(numberOfBits);
for (int i = 0; i < numberOfBits; i++)
{
if (JMetalRandom.NextDouble() < 0.5)
{
this.Bits[i] = true;
}
else
{
this.Bits[i] = false;
}
}
}
private Solution DoMutation(double probability, Solution parent)
{
Solution current = new Solution(parent);
Solution child;
child = new Solution(current);
XReal xCurrent = new XReal(current);
XReal xChild = new XReal(child);
int numberOfVariables = xCurrent.GetNumberOfDecisionVariables();
randStdNormal = new double[numberOfVariables];
for (int j = 0; j < numberOfVariables; j++)
{
double value;
// value = xParent2.GetValue(j) + f * (xParent0.GetValue(j) - xParent1.GetValue(j));
double u1 = JMetalRandom.NextDouble(0, 1);
double u2 = JMetalRandom.NextDouble(0, 1);
if (JMetalRandom.NextDouble() <= probability)
{
randStdNormal[j] = Math.Sqrt(-2.0 * Math.Log(u1)) * Math.Sin(2.0 * Math.PI * u2); //random normal(0,1)
value = xCurrent.GetValue(j) + zeta * xCurrent.GetStdDev(j) * randStdNormal[j];
if (value < xChild.GetLowerBound(j))
{
value = xChild.GetLowerBound(j);
//value = JMetalRandom.NextDouble(xChild.GetLowerBound(j), xChild.GetUpperBound(j));
}
if (value > xChild.GetUpperBound(j))
{
value = xChild.GetUpperBound(j);
//value = JMetalRandom.NextDouble(xChild.GetLowerBound(j), xChild.GetUpperBound(j));
}
xChild.SetValue(j, value);
}
}
return(child);
}
/// <summary>
/// Performs the operation
/// </summary>
/// <param name="obj">Object representing a SolutionSet</param>
/// <returns>The selected solution</returns>
public override object Execute(object obj)
{
SolutionSet population = (SolutionSet)obj;
if (index == 0) //Create the permutation
{
a = (new PermutationUtility()).IntPermutation(population.Size());
}
Solution solution1, solution2;
solution1 = population.Get(a[index]);
solution2 = population.Get(a[index + 1]);
index = (index + 2) % population.Size();
int flag = dominance.Compare(solution1, solution2);
if (flag == -1)
{
return(solution1);
}
else if (flag == 1)
{
return(solution2);
}
else if (solution1.CrowdingDistance > solution2.CrowdingDistance)
{
return(solution1);
}
else if (solution2.CrowdingDistance > solution1.CrowdingDistance)
{
return(solution2);
}
else if (JMetalRandom.NextDouble() < 0.5)
{
return(solution1);
}
else
{
return(solution2);
}
}
/// <summary>
/// Performs the operation
/// </summary>
/// <param name="probability">Mutation probability</param>
/// <param name="solution">The solution to mutate</param>
private void DoMutation(double probability, Solution solution)
{
int[] permutation;
int permutationLength;
if (solution.Type.GetType() == typeof(PermutationSolutionType))
{
permutationLength = ((Permutation)solution.Variable[0]).Size;
permutation = ((Permutation)solution.Variable[0]).Vector;
if (JMetalRandom.NextDouble() < probability)
{
int pos1;
int pos2;
pos1 = JMetalRandom.Next(0, permutationLength - 1);
pos2 = JMetalRandom.Next(0, permutationLength - 1);
while (pos1 == pos2)
{
if (pos1 == (permutationLength - 1))
{
pos2 = JMetalRandom.Next(0, permutationLength - 2);
}
else
{
pos2 = JMetalRandom.Next(pos1, permutationLength - 1);
}
}
// swap
int temp = permutation[pos1];
permutation[pos1] = permutation[pos2];
permutation[pos2] = temp;
}
}
else
{
Logger.Log.Error("Exception in " + this.GetType().FullName + ".DoMutation()");
Console.WriteLine("Exception in " + this.GetType().FullName + ".DoMutation()");
throw new Exception("Exception in " + this.GetType().FullName + ".DoMutation()");
}
}
private List <int> TourSelection(int depth)
{
// selection based on utility
List <int> selected = new List <int>();
List <int> candidate = new List <int>();
for (int k = 0; k < Problem.NumberOfObjectives; k++)
{
selected.Add(k); // WARNING! HERE YOU HAVE TO USE THE WEIGHT PROVIDED BY QINGFU (NOT SORTED!!!!)
}
for (int n = Problem.NumberOfObjectives; n < populationSize; n++)
{
candidate.Add(n); // set of unselected weights
}
while (selected.Count < (int)(populationSize / 5.0))
{
int bestIdd = (int)(JMetalRandom.NextDouble() * candidate.Count);
int i2;
int bestSub = candidate[bestIdd];
int s2;
for (int i = 1; i < depth; i++)
{
i2 = (int)(JMetalRandom.NextDouble() * candidate.Count);
s2 = candidate[i2];
if (utility[s2] > utility[bestSub])
{
bestIdd = i2;
bestSub = s2;
}
}
selected.Add(bestSub);
candidate.Remove(bestIdd);
}
return(selected);
}
public static void RandomPermutation(int[] perm, int size)
{
int[] index = new int[size];
bool[] flag = new bool[size];
for (int n = 0; n < size; n++)
{
index[n] = n;
flag[n] = true;
}
int num = 0;
while (num < size)
{
int start = JMetalRandom.Next(0, size - 1);
while (true)
{
if (flag[start])
{
perm[num] = index[start];
flag[start] = false;
num++;
break;
}
if (start == (size - 1))
{
start = 0;
}
else
{
start++;
}
}
}
}
/// <summary>
/// Performs the operation
/// </summary>
/// <param name="obj">Object representing a SolutionSet</param>
/// <returns>The selected solution</returns>
public override object Execute(object obj)
{
SolutionSet solutionSet = (SolutionSet)obj;
Solution solution1, solution2;
solution1 = solutionSet.Get(JMetalRandom.Next(0, solutionSet.Size() - 1));
solution2 = solutionSet.Get(JMetalRandom.Next(0, solutionSet.Size() - 1));
if (solutionSet.Size() >= 2)
{
while (solution1 == solution2)
{
solution2 = solutionSet.Get(JMetalRandom.Next(0, solutionSet.Size() - 1));
}
}
int flag = comparator.Compare(solution1, solution2);
if (flag == -1)
{
return(solution1);
}
else if (flag == 1)
{
return(solution2);
}
else
if (JMetalRandom.NextDouble() < 0.5)
{
return(solution1);
}
else
{
return(solution2);
}
}
public override SolutionSet Execute()
{
QualityIndicator.QualityIndicator indicators = null; // QualityIndicator object
int requiredEvaluations = 0; // Use in the example of use of the
// indicators object (see below)
evaluations = 0;
iteration = 0;
JMetalCSharp.Utils.Utils.GetDoubleValueFromParameter(this.InputParameters, "q", ref q);
JMetalCSharp.Utils.Utils.GetIntValueFromParameter(this.InputParameters, "populationSize", ref populationSize);
JMetalCSharp.Utils.Utils.GetIntValueFromParameter(this.InputParameters, "iterationsNumber", ref iterationsNumber);
JMetalCSharp.Utils.Utils.GetStringValueFromParameter(this.InputParameters, "dataDirectory", ref dataDirectory);
JMetalCSharp.Utils.Utils.GetIndicatorsFromParameters(this.InputParameters, "indicators", ref indicators);
Logger.Log.Info("POPSIZE: " + populationSize);
Console.WriteLine("POPSIZE: " + populationSize);
population = new SolutionSet(populationSize);
indArray = new Solution[Problem.NumberOfObjectives];
JMetalCSharp.Utils.Utils.GetIntValueFromParameter(this.InputParameters, "T", ref t);
JMetalCSharp.Utils.Utils.GetIntValueFromParameter(this.InputParameters, "nr", ref nr);
JMetalCSharp.Utils.Utils.GetDoubleValueFromParameter(this.InputParameters, "delta", ref delta);
neighborhood = new int[populationSize][];
for (int i = 0; i < populationSize; i++)
{
neighborhood[i] = new int[t];
}
z = new double[Problem.NumberOfObjectives];
//znad = new double[Problem.NumberOfObjectives];
lambda = new double[populationSize][];
for (int i = 0; i < populationSize; i++)
{
lambda[i] = new double[Problem.NumberOfObjectives];
}
crossover = this.Operators["crossover"];
mutation = this.Operators["mutation"];
double[] pro_T = new double[t];
double[] pro_A = new double[populationSize];
pro_T = GerPro(t);
pro_A = GerPro(populationSize);
/*string dir = "Result/MOEAD_ACOR/ZDT4_Real/Record/Replace/3nd_Dynamic2_nr16";
* if (Directory.Exists(dir))
* {
* Console.WriteLine("The directory {0} already exists.", dir);
* }
* else
* {
* Directory.CreateDirectory(dir);
* Console.WriteLine("The directory {0} was created.", dir);
* }*/
//Step 1. Initialization
//Step 1.1 Compute euclidean distances between weight vectors and find T
InitUniformWeight();
InitNeighborhood();
//Step 1.2 Initialize population
InitPoputalion();
//Step 1.3 Initizlize z
InitIdealPoint();
//Step 2 Update
do
{
int[] permutation = new int[populationSize];
Utils.RandomPermutation(permutation, populationSize);
if (crossover.ToString() == "JMetalCSharp.Operators.Crossover.DifferentialEvolutionCrossover")
{
for (int i = 0; i < populationSize; i++)
{
int n = permutation[i]; // or int n = i;
int type;
double rnd = JMetalRandom.NextDouble();
// STEP 2.1. Mating selection based on probability
if (rnd < delta) // if (rnd < realb)
{
type = 1; // neighborhood
}
else
{
type = 2; // whole population
}
List <int> p = new List <int>();
MatingSelection(p, n, 2, type);
// STEP 2.2. Reproduction
Solution child;
Solution[] parents = new Solution[3];
parents[0] = population.Get(p[0]);
parents[1] = population.Get(p[1]);
parents[2] = population.Get(n);
// Apply DE crossover
child = (Solution)crossover.Execute(new object[] { population.Get(n), parents });
// Apply mutation
mutation.Execute(child);
// Evaluation
Problem.Evaluate(child);
evaluations++;
// STEP 2.3. Repair. Not necessary
// STEP 2.4. Update z_
UpdateReference(child);
// STEP 2.5. Update of solutions
UpdateProblem(child, n, type);
}
}
else if (crossover.ToString() == "JMetalCSharp.Operators.Crossover.ACOR")
{
Solution[] parents = new Solution[2];
int t = 0;
for (int i = 0; i < populationSize; i++)
{
int n = permutation[i];
// or int n = i;
int type;
double rnd = JMetalRandom.NextDouble();
// STEP 2.1. ACOR selection based on probability
if (rnd < delta) // if (rnd < realb)
{
type = 1; // minmum
//parents[0] = population.Get(ACOrSelection2(n, type, pro_T));
}
else
{
type = 2; // whole neighborhood probability
//parents[0] = population.Get(ACOrSelection2(n, type, pro_A));
}
GetStdDev(neighborhood);
//GetStdDev1(neighborhood, type);
//List<int> p = new List<int>();
//MatingSelection(p, n, 1, type);
// STEP 2.2. Reproduction
Solution child;
parents[0] = population.Get(ACOrSelection(n, type));
parents[1] = population.Get(n);
//parents[0] = population.Get(p[0]);
// Apply ACOR crossover
child = (Solution)crossover.Execute(parents);
child.NumberofReplace = t;
// // Apply mutation
mutation.Execute(child);
// Evaluation
Problem.Evaluate(child);
evaluations++;
// STEP 2.3. Repair. Not necessary
// STEP 2.4. Update z_
UpdateReference(child);
// STEP 2.5. Update of solutions
t = UpdateProblemWithReplace(child, n, 1);
}
}
else
{
// Create the offSpring solutionSet
SolutionSet offspringPopulation = new SolutionSet(populationSize);
Solution[] parents = new Solution[2];
for (int i = 0; i < (populationSize / 2); i++)
{
int n = permutation[i]; // or int n = i;
int type;
double rnd = JMetalRandom.NextDouble();
// STEP 2.1. Mating selection based on probability
if (rnd < delta) // if (rnd < realb)
{
type = 1; // neighborhood
}
else
{
type = 2; // whole population
}
List <int> p = new List <int>();
MatingSelection(p, n, 2, type);
parents[0] = population.Get(p[0]);
parents[1] = population.Get(p[1]);
if (iteration < iterationsNumber)
{
//obtain parents
Solution[] offSpring = (Solution[])crossover.Execute(parents);
//Solution child;
mutation.Execute(offSpring[0]);
mutation.Execute(offSpring[1]);
/*if(rnd < 0.5)
* {
* child = offSpring[0];
* }
* else
* {
* child = offSpring[1];
* }*/
Problem.Evaluate(offSpring[0]);
Problem.Evaluate(offSpring[1]);
Problem.EvaluateConstraints(offSpring[0]);
Problem.EvaluateConstraints(offSpring[1]);
offspringPopulation.Add(offSpring[0]);
offspringPopulation.Add(offSpring[1]);
evaluations += 2;
// STEP 2.3. Repair. Not necessary
// STEP 2.4. Update z_
UpdateReference(offSpring[0]);
UpdateReference(offSpring[1]);
// STEP 2.5. Update of solutions
UpdateProblem(offSpring[0], n, type);
UpdateProblem(offSpring[1], n, type);
}
}
}
/*string filevar = dir + "/VAR" + iteration;
* string filefun = dir + "/FUN" + iteration;
* population.PrintVariablesToFile(filevar);
* population.PrintObjectivesToFile(filefun);*/
iteration++;
if ((indicators != null) && (requiredEvaluations == 0))
{
double HV = indicators.GetHypervolume(population);
if (HV >= (0.98 * indicators.TrueParetoFrontHypervolume))
{
requiredEvaluations = evaluations;
}
}
} while (iteration < iterationsNumber);
Logger.Log.Info("ITERATION: " + iteration);
Console.WriteLine("ITERATION: " + iteration);
// Return as output parameter the required evaluations
SetOutputParameter("evaluations", requiredEvaluations);
Result = population;
//return population;
// Return the first non-dominated front
Ranking rank = new Ranking(population);
//Result = rank.GetSubfront(0);
return(Result);
}
/// <summary>
/// Perform the crossover operation.
/// </summary>
/// <param name="probability">Crossover probability</param>
/// <param name="parent1">The first parent</param>
/// <param name="parent2">The second parent</param>
/// <returns>An array containing the two offsprings</returns>
private Solution[] DoCrossover(double probability, Solution parent1, Solution parent2)
{
Solution[] offSpring = new Solution[2];
offSpring[0] = new Solution(parent1);
offSpring[1] = new Solution(parent2);
int i;
double rand;
double y1, y2, yL, yu;
double c1, c2;
double alpha, beta, betaq;
double valueX1, valueX2;
XReal x1 = new XReal(parent1);
XReal x2 = new XReal(parent2);
XReal offs1 = new XReal(offSpring[0]);
XReal offs2 = new XReal(offSpring[1]);
int numberOfVariables = x1.GetNumberOfDecisionVariables();
if (JMetalRandom.NextDouble() <= probability)
{
for (i = 0; i < numberOfVariables; i++)
{
valueX1 = x1.GetValue(i);
valueX2 = x2.GetValue(i);
if (JMetalRandom.NextDouble() <= 0.5)
{
if (Math.Abs(valueX1 - valueX2) > EPS)
{
if (valueX1 < valueX2)
{
y1 = valueX1;
y2 = valueX2;
}
else
{
y1 = valueX2;
y2 = valueX1;
}
yL = x1.GetLowerBound(i);
yu = x1.GetUpperBound(i);
rand = JMetalRandom.NextDouble();
beta = 1.0 + (2.0 * (y1 - yL) / (y2 - y1));
alpha = 2.0 - Math.Pow(beta, -(distributionIndex + 1.0));
if (rand <= (1.0 / alpha))
{
betaq = Math.Pow((rand * alpha), (1.0 / (distributionIndex + 1.0)));
}
else
{
betaq = Math.Pow((1.0 / (2.0 - rand * alpha)), (1.0 / (distributionIndex + 1.0)));
}
c1 = 0.5 * ((y1 + y2) - betaq * (y2 - y1));
beta = 1.0 + (2.0 * (yu - y2) / (y2 - y1));
alpha = 2.0 - Math.Pow(beta, -(distributionIndex + 1.0));
if (rand <= (1.0 / alpha))
{
betaq = Math.Pow((rand * alpha), (1.0 / (distributionIndex + 1.0)));
}
else
{
betaq = Math.Pow((1.0 / (2.0 - rand * alpha)), (1.0 / (distributionIndex + 1.0)));
}
c2 = 0.5 * ((y1 + y2) + betaq * (y2 - y1));
if (c1 < yL)
{
c1 = yL;
}
if (c2 < yL)
{
c2 = yL;
}
if (c1 > yu)
{
c1 = yu;
}
if (c2 > yu)
{
c2 = yu;
}
if (JMetalRandom.NextDouble() <= 0.5)
{
offs1.SetValue(i, c2);
offs2.SetValue(i, c1);
}
else
{
offs1.SetValue(i, c1);
offs2.SetValue(i, c2);
}
}
else
{
offs1.SetValue(i, valueX1);
offs2.SetValue(i, valueX2);
}
}
else
{
offs1.SetValue(i, valueX2);
offs2.SetValue(i, valueX1);
}
}
}
return(offSpring);
}
/// <summary>
/// Perform the crossover operation.
/// </summary>
/// <param name="probability">Crossover probability</param>
/// <param name="parent1">The first parent</param>
/// <param name="parent2">The second parent</param>
/// <returns>An array containig the two offsprings</returns>
private Solution[] DoCrossover(double probability, Solution parent1, Solution parent2)
{
Solution[] offSpring = new Solution[2];
offSpring[0] = new Solution(parent1);
offSpring[1] = new Solution(parent2);
try
{
if (JMetalRandom.NextDouble() < probability)
{
if ((parent1.Type.GetType() == typeof(BinarySolutionType)) ||
(parent1.Type.GetType() == typeof(BinaryRealSolutionType)))
{
//1. Compute the total number of bits
int totalNumberOfBits = 0;
for (int i = 0; i < parent1.Variable.Length; i++)
{
totalNumberOfBits += ((Binary)parent1.Variable[i]).NumberOfBits;
}
//2. Calculate the point to make the crossover
int crossoverPoint = JMetalRandom.Next(0, totalNumberOfBits - 1);
//3. Compute the encodings.variable containing the crossoverPoint bit
int variable = 0;
int acountBits = ((Binary)parent1.Variable[variable]).NumberOfBits;
while (acountBits < (crossoverPoint + 1))
{
variable++;
acountBits += ((Binary)parent1.Variable[variable]).NumberOfBits;
}
//4. Compute the bit into the selected encodings.variable
int diff = acountBits - crossoverPoint;
int intoVariableCrossoverPoint = ((Binary)parent1.Variable[variable]).NumberOfBits - diff;
//5. Make the crossover into the gene;
Binary offSpring1, offSpring2;
offSpring1 = (Binary)parent1.Variable[variable].DeepCopy();
offSpring2 = (Binary)parent2.Variable[variable].DeepCopy();
for (int i = intoVariableCrossoverPoint; i < offSpring1.NumberOfBits; i++)
{
bool swap = offSpring1.Bits[i];
offSpring1.Bits[i] = offSpring2.Bits[i];
offSpring2.Bits[i] = swap;
}
offSpring[0].Variable[variable] = offSpring1;
offSpring[1].Variable[variable] = offSpring2;
//6. Apply the crossover to the other variables
for (int i = 0; i < variable; i++)
{
offSpring[0].Variable[i] = parent2.Variable[i].DeepCopy();
offSpring[1].Variable[i] = parent1.Variable[i].DeepCopy();
}
//7. Decode the results
for (int i = 0; i < offSpring[0].Variable.Length; i++)
{
((Binary)offSpring[0].Variable[i]).Decode();
((Binary)offSpring[1].Variable[i]).Decode();
}
} // Binary or BinaryReal
else
{ // Integer representation
int crossoverPoint = JMetalRandom.Next(0, parent1.NumberOfVariables() - 1);
int valueX1;
int valueX2;
for (int i = crossoverPoint; i < parent1.NumberOfVariables(); i++)
{
valueX1 = ((Int)parent1.Variable[i]).Value;
valueX2 = ((Int)parent2.Variable[i]).Value;
((Int)offSpring[0].Variable[i]).Value = valueX2;
((Int)offSpring[1].Variable[i]).Value = valueX1;
}
}
}
}
catch (Exception ex)
{
Logger.Log.Error("Error in: " + this.GetType().FullName + ".DoCrossover()", ex);
Console.WriteLine("Error in " + this.GetType().FullName + ".DoCrossover()");
throw new Exception("Exception in " + this.GetType().FullName + ".DoCrossover()");
}
return(offSpring);
}