The robustness of multi-echelon service models under autocorrelated demands

A common assumption underlying the development of multi-echelon service models is that successive demands are independent. This paper studies the robustness of two models, developed for a two-echelon serial inventory network, when the demand process is autocorrelated. Both stockpoints operate a periodic review order-up-to-S echelon inventory policy. Using an analytic approach, the paper extends the original models so that they apply exactly for any autocorrelated period demand process and explore the behaviour of the extended models under different scenarios. In order to study the effects of different autocorrelation characteristics, an MA(1) and an AR(1) process are analysed in detail. The results demonstrate that, depending on the overall system parameters setting, models which ignore the effects of autocorrelation may provide very unsatisfactory estimates of the system performance. Hence, extreme cuation is required when deciding the use of multi-echelon service models in practice.