Management of demand uncertainty within MRP2 using possibility theory

In our increasingly competitive context, companies must closely adapt what they produce to what will be sold. In that purpose, it is mandatory to make early decisions on the base of an uncertain production planning. We suggest a way to explicitly model the uncertainty and imprecision of the demand using possibility theory, all along the MRPII steps (Material Requirement Planning, Load Planning, Scheduling). This "Fuzzy-MRP" method aims at providing a richer information to decision makers, based on a quantification of the various situations that may arise according to the possible variations of the customer's demand. Decisions requiring a long preparation (sub-contracting, order of components, increase of capacity, etc.) can so be considered earlier, on the base of quantified data, leading to a better use of the suppliers and to a better dimensioning of the inventories.