2009 | OriginalPaper | Buchkapitel
Selection of Heuristics for the Job-Shop Scheduling Problem Based on the Prediction of Gaps in Machines
verfasst von : Pedro Abreu, Carlos Soares, Jorge M. S. Valente
Erschienen in: Learning and Intelligent Optimization
Verlag: Springer Berlin Heidelberg
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
We present a general methodology to model the behavior of heuristics for the Job-Shop Scheduling (JSS) that address the problem by solving conflicts between different operations on the same machine. Our models estimate the gaps between consecutive operations on a machine given measures that characteristics the JSS instance and those operations. These models can be used for a better understanding of the behavior of the heuristics as well as to estimate the performance of the methods. We tested it using two well know heuristics: Shortest Processing Time and Longest Processing Time, that were tested on a large number of random JSS instances. Our results show that it is possible to predict the value of the gaps between consecutive operations from on the job, on random instances. However, the prediction the relative performance of the two heuristics based on those estimates is not successful. Concerning the main goal of this work, we show that the models provide interesting information about the behavior of the heuristics.