Distribution network dynamics with correlated demands

Abstract

We compare centralised and decentralised distribution network designs for a two-level supply chain. The demand pattern faced by the retailers is modelled as a first order Vector Auto-Regressive process, which is used to represent the progression of and relationship in sets of time series. All participants, i.e. retailers and distribution centres, operate an Order-Up-To policy with the MMSE forecasting. Inventory and capacity costs are considered. The result shows that the demand correlation has a significant impact on decision about consolidation of the distribution system.