Effectiveness of antithetic sampling and stratified sampling in Monte Carlo chronological production cost modeling (power systems)

Sampling error detracts from the usefulness of estimates of mean hourly marginal cost produced by Monte Carlo chronological production cost models. Variance reduction techniques commonly used in other Monte Carlo simulation applications can significantly improve the precision of estimates. Two such techniques, antithetic sampling and stratified sampling, are tested for a fictitious system. The number of iterations needed to reach a precision target falls significantly. The estimated savings in total computing time could exceed 50% for a full one-year forecast. Both techniques are easily implemented and should be used in Monte Carlo production costing efforts to estimate hourly marginal cost.<
>