Chance Constrained Program with Quadratic Randomness: A Unified Approach Based on Gaussian Mixture Distribution

Abstract: This paper investigates the stochastic program with the chance constraint on a quadratic form of random variables following multivariate Gaussian mixture distribution (GMD). Under some mild conditions, it is proved that the asymptotic distribution of this kind of quadratic randomness is a univariate GMD. This finding helps to translate the chance constrained program into a more tractable one, based on which an effective branch-and-bound algorithm that takes advantage of the special structure of the problem is introduced to search the global optimal solution. Furthermore, it is shown that the error resulting from approximating the quadratic randomness with its associated asymptotic distribution can be reduced by restricting the condition numbers of covariance matrices of the multivariate GMD's components. In addition, some numerical simulations are also carried out to verify the effectiveness of this flexible and unified approach.