Rolling partial rescheduling with efficiency and stability based on local search algorithm

Abstract

This paper discusses the single-machine large-scale rescheduling problem with efficiency and stability as criteria, where more disruptions arise during the execution of schedule. A rolling strategy is driven by disruption events and the reactive partial rescheduling (PR) is adopted at each disruption. Two types of PR sub-problem are designed respectively for the procedural and the terminal PR-horizons. A local search algorithm is used to solve the PR sub-problems. Computational results show that the rolling PR can greatly improve the schedule stability with little sacrifice in schedule efficiency and consistently outperforms the rolling RSR. © Springer-Verlag Berlin Heidelberg 2006.