Data-driven construction of Convex Region Surrogate models
As we strive to solve more complex and integrated optimization problems, there is an increasing demand for process models that are sufficiently accurate as well as computationally efficient. In this work, we develop an algorithm for the data-driven construction of a type of surrogate models that can be formulated as mixed-integer linear programs yet still provide good approximations of nonlinearities and nonconvexities. In such a surrogate model, which we refer to as Convex Region Surrogate, the feasible region is given by the union of convex regions in the form of polytopes and for each region, the objective function can be approximated by a linear function. In this paper, we present the proposed two-phase algorithm and demonstrate its effectiveness with a real-world case study.