Stratified random sampling for power estimation

In this paper, we present new statistical sampling techniques for performing power estimation at the circuit level. These techniques first transform the power estimation problem to a survey sampling problem, then apply stratified random sampling to improve the efficiency of sampling. The stratification a's based on a low-cost predictor, such as zero delay pourer estimates. We also propose a two-stage stratified sampling technique to handle very long initial sequences. Experimental results show that the efficiency of stratified random sampling and true-stage stratified sampling techniques are 3-1OX higher than that of simple random sampling and the Markov-based Monte Carlo simulation techniques.