Inventory Management Optimization in Multi-Stage Supply Chains Under Uncertainty

We deal with the optimal inventory control problem for Multi-Stage Supply Chains (MSSC) with uncertain dynamics. The two sources of uncertainty we consider are about the perishability factor of stored products and on the customer prediction information. The control problem consists in defining a Replenishment Policy (RP) keeping the inventory level as close as possible to a desired value and mitigating the Bullwhip Effect (BE). The solution we propose is based on Distributed Robust Model Predictive Control (DRMPC) approach. This implies solving a set of RMPC problems. To drastically reduce the numerical complexity of this problem, the control signal (i.e. the RP) is sought in the space of B-spline functions, which are known to be universal approximators admitting a parsimonious parametric representation.