Exploring the bullwhip effect using simulation and Taguchi experimental design

Abstract

This paper quantifies the impact of different causes of the bullwhip effect in a model of a multi-echelon supply chain with batching and information sharing. System dynamics simulation, using iThink ® software, has been initially used to explore the impact of various batch sizes on the bullwhip effect. It has been observed that the relationship between batch size and demand amplification is non-monotonic. Large batch sizes, which when combined in integer multiples can produce order rates that are close to the actual demand, produce little demand amplification. Next, a combination of simulation and Taguchi design of experiments is applied to quantitatively measure the impact of different causes of the bullwhip effect and the interaction that occurs between these causes. This is a contribution to the continuing research into controlling the bullwhip effect, giving supply chain operations managers a practical approach to understanding the impact of different causes of the bullwhip effect.