C# Class SwarmOps.Optimizers.DESuite

Differential Evolution (DE) optimizer originally due to Storner and Price (1). This suite offers combinations of DE variants and various perturbation schemes for its behavioural parameters. Note that this has complicated the implementation somewhat.

References: (1) R. Storn and K. Price. Differential evolution - a simple and efficient heuristic for global optimization over continuous spaces. Journal of Global Optimization, 11:341-359, 1997.

Inheritance: Optimizer

显示文件 Open project: DanWBR/dwsim3

Protected Properties

Property	Type	Description
_crossover	DECrossover.Variant
_dither	DitherVariant

Public Methods

Method	Description
DESuite ( DECrossover crossover, DitherVariant dither ) : System.Diagnostics	Construct the object.
DESuite ( Problem problem, DECrossover crossover, DitherVariant dither ) : System.Diagnostics	Construct the object.
GetCR ( double parameters ) : double	Get parameter, CR, aka. crossover probability.
GetF ( double parameters ) : double	Get parameter, F, aka. differential weight.
GetFMid ( double parameters ) : double	Get parameter, FMid, aka. differential weight dithering midpoint.
GetFRange ( double parameters ) : double	Get parameter, FRange, aka. differential weight dithering range.
GetNumAgents ( double parameters ) : int	Get parameter, Number of agents, aka. population size.
Optimize ( double parameters ) : Result	Perform one optimization run and return the best found solution.

Protected Methods

Method	Description
SetVariant ( DECrossover crossover, DitherVariant dither ) : void	Set DE operator variants to be used, and determine the number of behavioural parameters associated with that variant.

Method Details

DESuite() public method

Construct the object.

public DESuite ( DECrossover crossover, DitherVariant dither ) : System.Diagnostics
crossover	DECrossover	Crossover variant to be used.
dither	DitherVariant	Dither variant to be used.
return	System.Diagnostics

DESuite() public method

Construct the object.

public DESuite ( Problem problem, DECrossover crossover, DitherVariant dither ) : System.Diagnostics
problem	Problem	Problem to optimize.
crossover	DECrossover	Crossover variant to be used.
dither	DitherVariant	Dither variant to be used.
return	System.Diagnostics

GetCR() public method

Get parameter, CR, aka. crossover probability.

public GetCR ( double parameters ) : double
parameters	double	Optimizer parameters.
return	double

GetF() public method

Get parameter, F, aka. differential weight.

public GetF ( double parameters ) : double
parameters	double	Optimizer parameters.
return	double

GetFMid() public method

Get parameter, FMid, aka. differential weight dithering midpoint.

public GetFMid ( double parameters ) : double
parameters	double	Optimizer parameters.
return	double

GetFRange() public method

Get parameter, FRange, aka. differential weight dithering range.

public GetFRange ( double parameters ) : double
parameters	double	Optimizer parameters.
return	double

GetNumAgents() public method

Get parameter, Number of agents, aka. population size.

public GetNumAgents ( double parameters ) : int
parameters	double	Optimizer parameters.
return	int

Optimize() public method

Perform one optimization run and return the best found solution.

public Optimize ( double parameters ) : Result
parameters	double	Control parameters for the optimizer.
return	Result

SetVariant() protected method

Set DE operator variants to be used, and determine the number of behavioural parameters associated with that variant.

protected SetVariant ( DECrossover crossover, DitherVariant dither ) : void
crossover	DECrossover	Crossover variant to be used.
dither	DitherVariant	Dither variant to be used.
return	void

Property Details

_crossover protected_oe property

protected DECrossover.Variant _crossover
return	DECrossover.Variant

_dither protected_oe property

protected DitherVariant _dither
return	DitherVariant