ABSTRACT
The United States Air Force currently uses the best analytical model available for the aircraft spares provisioning problem. It is named the Dynamic Multi-Echelon Technique for Recoverable Item Control (Dyna-METRIC) developed by the RAND Corporation [1]. Dyna-METRIC is a flexible inventory modeling tool, but its underlying assumption is that a large number of entities are being modeled. The following is a brief discussion of the Dyna-METRIC model. The central theorem in the Dyna-METRIC model is Palm’s theorem [2], also known as the infinite channel queuing assumption [3], which states that if demand for an item is given by a Poisson process with mean m per unit time, and if the repair time for each failed unit is independently and identically distributed according to any distribution with mean repair time T, then the steady-state probability distribution for the number of units in repair has a Poisson distribution with mean mT.
