crossover: Crossover Method

In YsoSirius/windfarmGA: Genetic Algorithm for Wind Farm Layout Optimization

Crossover Method

Description

The crossover method creates new offspring with the selected individuals by permutating their genetic codes.

Usage

crossover(se6, u, uplimit, crossPart = c("EQU", "RAN"), verbose, seed)

Arguments

se6	The selected individuals. The output of selection
u	The crossover point rate
uplimit	The upper limit of allowed permutations
crossPart	The crossover method. Either "EQU" or "RAN"
verbose	If TRUE, will print out further information
seed	Set a seed for comparability. Default is NULL

Value

Returns a binary coded matrix of all permutations and all grid cells, where 0 indicates no turbine and 1 indicates a turbine in the grid cell.

See Also

Other Genetic Algorithm Functions: fitness(), genetic_algorithm(), init_population(), mutation(), selection(), trimton()

Examples

## Create two random parents with an index and random binary values
Parents <- data.frame(
  ID = 1:20,
  bin = sample(c(0, 1), 20, replace = TRUE, prob = c(70, 30)),
  bin.1 = sample(c(0, 1), 20, replace = TRUE, prob = c(30, 70))
)

## Create random Fitness values for both individuals
FitParents <- data.frame(ID = 1, Fitness = 1000, Fitness.1 = 20)

## Assign both values to a list
CrossSampl <- list(Parents, FitParents)
## Cross their data at equal locations with 2 crossover parts
crossover(CrossSampl, u = 1.1, uplimit = 300, crossPart = "EQU")

## with 3 crossover parts and equal locations
crossover(CrossSampl, u = 2.5, uplimit = 300, crossPart = "EQU")

## or with random locations and 5 crossover parts
crossover(CrossSampl, u = 4.9, uplimit = 300, crossPart = "RAN")

YsoSirius/windfarmGA documentation built on March 13, 2024, 8:37 a.m.