Title :
Sample size reduction in stochastic production simulation
Author :
Lee, F.N. ; Breipohl, A. ; Huang, J. ; Feng, Q.
Author_Institution :
Sch. of Electr. Eng. & Comput. Sci., Oklahoma Univ., Norman, OK, USA
Abstract :
A method of Monte Carlo simulation that combines the use of a control variable with stratified sampling is presented. The method reduces the number of required runs from approximately 10000 to 10. This reduction also lessens computational time and should enable chronological simulation to play a much more significant role in many long-range planning applications. The theory and a sample study are presented. In the sample study, the proposed method using the 10 samples produces an estimator of the mean production cost that has a much smaller variance than an estimator based on a traditional Monte Carlo study which uses 8000 samples
Keywords :
Monte Carlo methods; digital simulation; estimation theory; power system analysis computing; power system planning; stochastic processes; Monte Carlo simulation; chronological simulation; computational time; control variable; long-range planning applications; mean production cost; sample size reduction; stochastic production simulation; stratified sampling; Computational modeling; Computer simulation; Costs; Monte Carlo methods; Power system modeling; Power system planning; Power system simulation; Production; Sampling methods; Stochastic processes;
Conference_Titel :
Circuits and Systems, 1990., IEEE International Symposium on
Conference_Location :
New Orleans, LA
DOI :
10.1109/ISCAS.1990.112011
