CLONALG {metaheuristicOpt}

Optimization using Clonal Selection Algorithm

Description

This is the internal function that implements Clonal Selection Algorithm. It is used to solve continuous optimization tasks. Users do not need to call it directly, but just use metaOpt.

Usage

CLONALG(FUN, optimType = "MIN", numVar, numPopulation = 40,
  maxIter = 500, rangeVar, selectionSize = as.integer(numPopulation/4),
  multipicationFactor = 0.5, hypermutationRate = 0.1)

Arguments

FUN

an objective function or cost function,

optimType

a string value that represent the type of optimization. There are two option for this arguments: "MIN" and "MAX". The default value is "MIN", which the function will do minimization. Otherwise, you can use "MAX" for maximization problem. The default value is "MIN".

numVar

a positive integer to determine the number variables.

numPopulation

a positive integer to determine the number populations. The default value is 40.

maxIter

a positive integer to determine the maximum number of iterations. The default value is 500.

rangeVar

a matrix (2 \times n) containing the range of variables, where n is the number of variables, and first and second rows are the lower bound (minimum) and upper bound (maximum) values, respectively. If all variable have equal upper bound, you can define rangeVar as matrix (2 \times 1).

selectionSize

a positive integer between 0 and numVar to determine selection size (see details). The default value is as.integer(numPopulation/4).

multipicationFactor

a positive numeric between 0 and 1 to determine number of clones. The default value is 0.5.

hypermutationRate

a positive numeric between 0 and 1 to determine probabilty of variable in clone candidate solutions to be mutated, close to 1 probability is high and vice versa. The default value is 0.1.

Details

This algorithm was proposed by (Castro & Zuben, 2002). The Clonal Selection Algorithm (CLONALG) mimics maturation proses of imumune system. CLONALG consist 5 step initialize, selection, clonal, hypermutation and maturation.

In order to find the optimal solution, the algorithm follow the following steps.

• initialize population randomly.

• select top selectionSize candidate solutions from population with best fitness.

• clone each selected candidate solutions.

• hypermutation each variable in cloned candidate solutions.

• maturation combine each hypermutated candidate solution with population. Select top n candidate solution from population as new population.

• If a termination criterion (a maximum number of iterations or a sufficiently good fitness) is met, exit the loop.

Value

Vector [v1, v2, ..., vn] where n is number variable and vn is value of n-th variable.

References

Castro, L. & Zuben, F. J. V. (2002). Learning and optimization using the clonal selection principle. IEEE Transactions on Evolutionary Computation, Special Issue on Artificial. Immune Systems, 6(3), 239–251. https://doi.org/10.1109/TEVC.2002.1011539

See Also

metaOpt

Examples

##################################
## Optimizing the quartic with noise function

# define Quartic with noise function as objective function
quartic <- function(x){
    dim <- length(x)
    result <- sum(c(1:dim)*(x^4))+runif(1)
    return(result)
}

## Define parameter
numVar <- 5
rangeVar <- matrix(c(-1.28, 1.28), nrow=2)

## calculate the optimum solution clonal selection algorithm
resultCLONALG <- CLONALG(quartic, optimType="MIN", numVar, numPopulation=20,
                 maxIter=100, rangeVar)

## calculate the optimum value using quartic with noise function
optimum.value <- quartic(resultCLONALG)