Optimizing inventory policies in process networks under uncertainty

We address the inventory planning problem in process networks under uncertainty through stochastic programming models. The scope of inventory planning requires the formulation of multiperiod models to represent the time-varying conditions of industrial process, but the multistage stochastic programming formulations are often too large to solve. We propose a policy-based approximation of the multistage stochastic formulation that avoids anticipativity by enforcing the same decision rule for all scenarios. The proposed formulation includes the logic modeling inventory policies, and it is used to find the parameters that offer the best expected performance. We propose policies for inventory planning in process networks with arrangements of inventories in parallel and in series. We compare the inventory planning strategies obtained from the policybased formulation with the analogous two-stage approximation of the multistage stochastic program. Sequential implementation of both planning strategies in receding horizon simulations show the advantages of the policy-based model, despite the increase in computational complexity.