Compressed Stochastic Macromodeling of Electrical Systems via Rational Polynomial Chaos and Principal Component Analysis

This paper introduces a compression strategy to speed-up the calculation of frequency-domain stochastic models based on rational polynomial chaos expansions. Principal component analysis is used to remove redundancy in the data, thus leading to a considerable reduction in the number of model coefficients to estimate. Compared to the state-of-the-art techniques, the proposed solution turns out to be a good tradeoff between accuracy and processing efficiency. As a validation, the method is applied to the uncertainty quantification of the scattering responses of a nine-port distributed network.