A combined OWA–DEA method for dispatching rule selection

Abstract

Dispatching rule selection is an important issue in dynamic scheduling of production systems. When there are multiple performance criteria, identification of the most efficient dispatching rule is not an easy task. This paper considers an ordered weighted averaging (OWA) methodology combined with a data envelopment analysis (DEA) model for identifying the best dispatching rule in a flowshop environment. Standard DEA cannot be used directly, due to ambiguity in the inputs and outputs that may be specified in the flowshop scheduling problem. To overcome this drawback, an OWA method is used to first assess the dispatching rules, measured in terms of multiple factors, for different decision making optimism levels. This is followed by using a DEA model to aggregate the OWA assessments, in order to identify the dispatching rule(s) with the best overall performance. A computational analysis is performed by using randomly generated test problems, and different scenarios involving different factor priorities. The results demonstrate that the proposed OWA–DEA approach successfully identifies which dispatching rules are efficient, and which are not.