pub enum NoiseMethod {
Saa,
Lhs,
QmcSobol,
QmcHalton,
Selective,
HistoricalResiduals,
}Expand description
Opening tree noise generation algorithm for a stage.
Controls which algorithm is used to generate noise vectors for
the opening tree at this stage. This is orthogonal to
SamplingScheme, which selects the forward-pass noise source
(in-sample, external, historical). NoiseMethod governs how
the noise vectors are produced (SAA, LHS, QMC-Sobol, QMC-Halton,
Selective, or HistoricalResiduals).
See Input Scenarios §1.8 for the full method catalog and use cases.
Variants§
Saa
Sample Average Approximation. Pure Monte Carlo random sampling.
Lhs
Latin Hypercube Sampling. Stratified sampling ensuring uniform coverage.
QmcSobol
Quasi-Monte Carlo with Sobol sequences. Low-discrepancy.
QmcHalton
Quasi-Monte Carlo with Halton sequences. Low-discrepancy.
Selective
Selective/Representative Sampling. Clustering on historical data.
HistoricalResiduals
Historical residuals from the HistoricalScenarioLibrary.
Copies pre-computed eta (residual) vectors from actual historical
observations. Skips the parametric Cholesky correlation step since
empirical cross-entity correlation is embedded in the residuals.
Year pool configuration is sourced from the system-level
HistoricalYears config (same as the Historical forward sampling
scheme).
Trait Implementations§
Source§impl Clone for NoiseMethod
impl Clone for NoiseMethod
Source§fn clone(&self) -> NoiseMethod
fn clone(&self) -> NoiseMethod
1.0.0 · Source§fn clone_from(&mut self, source: &Self)
fn clone_from(&mut self, source: &Self)
source. Read more