Stochastic MINLP Optimisation using Simplicial Approximation

Mathematical programming has long been recognized as a promising direction to the efficient solution of design, synthesis and operation problems that can gain industry the competitive advantage required to survive in today’s difficult economic environment. Most of the engineering design problems can be modeled as MINLP problems with stochastic parameters. In this paper a novel decomposition algorithm is presented to solve convex stochastic MINLP problems. The proposed approach is an extension of the simplicial-approximation approach proposed by Goyal and Ierapetritou, (Goyal and Ierapetritou, 2004a, 2004b), for solving deterministic MINLP problems and is based on the idea of closely approximating the feasible region defined by the set of constraints by an approximation of its convex hull. A case study is also presented illustrating the applicability and efficiency of the proposed approach.