Abstract
Die wachsende Bedeutung von Echtzeit-Anwendungen von Produktionensystemen erfordert die Entwicklung von Methoden zur Verringemng der Antwortzeiten. Aufgrund der beschränkten Rechenleistungen von Monoprozessorenist es notwendig, die inhärente Parallelität von Produktionen-systemen mittels Multiprozessorsysteme auszunützen. Um dies effizient durchführen zu können, benötigtman geeignete Algorithmen, die eine möglichst gleichmäßige Auslastung derProzessoren gewährleisten, ohne dabei den entsprechenden Organisations- und Kommunikations-Overhead dramatisch zu eihöhen. Es wird ein für Produktionensysteme allgemein verwendbarer Scheduling-Algorithmus vorgestellt, der auf einer dynamischer Verteilung von Daten beruht.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Literatur
Barachini F., Theuretzbacher N.: “The Challange of Real-time Process Control for Production Systems”, Proceedings of AAAI-88, Vol 2, pp. 705–709, St.Paul, Minnesota, 1988.
Barachini F.:”PAMELA: A Rule-Based AI Language for Process-Control Applications”, Proceedings on the first International Conference on Industrial amp; Engineering Applications of Artificial Intelligence amp; Expert Systems, Vol 2, pp 860–867, Tennessee, 1988.
Barachini F., “How Production Systems can Survive in Real-Time Process Control”, Eight International Conference on Expert Systems and their Applications, AVIGNON 88, Vol II, 1988.
Butler P.L., Allen J.P., Bouldin D.W.: “Parallel Architecture for OPS5”, The 15th Annual In temational Symposium on Computer Architecture, Honolulu, Proceedings pp 452–457, 1988.
Forgy CL.: “On the Efficient Implementation of Production Systems”, Ph.D. Thesis, Carnegie- Mellon University, 1979.
Forgy C.L.: “RETE: A Fast Algorithm for the Many Pattern/Many Object Pattern Matching Problem”, Artificial Intelligence, Vol. 19, pp. 17–37, 1982.
Gupta A.: “Parallelism in Production Systems”; CMU-CS-86-122, Ph.D. Thesis, Carnegie-Mellon University, March 1986
Gupta A. et al.: “Results of Parallel Implementation of OPS5 on the Encore Multiprocessor”; CMU-CS-87-146, August 1987
Gupta A., TambeM.: “Suitability of Message Passing Computers for Implementing Production Systems”, Proceedings of AAAI-88, Vol 2, pp. 687–692, St.Paul, Minnesota, 1988.
Kelly M.A., Seviora R.E.: “A Multiprocessor Architecture for Production System Matching”; Proceedings of the AAAI-87, Vol.1,pp. 36–41, 1987 1987
Miranker, D.P.: “The performance Analysis of TREAT: A DADO Production System Algorithm”, International Conference on Fifth Generation Computing, Tokyo 1984, revised article 1986
Miranker D.P.: “TREAT: A New and Efficient Match Algorithm for AI Production Systems”; Ph.D.Thesis, Colubia Unversity 1987
Oshisanwo A.O., Dasiewicz P.P.: “A Parallel Model and Architecture for Production] Systems”; Proceedings of the 1987 International Conference on Parallel Processing, pp. 147–153 May 1985
Schreiner F., Zimmermann G.: “PESA1 - A Parallel Architecture for Production Systems”; Proceedings of the 1987 International Conference on Parallel Processing, pp. 166–169
Stolfo S.J.: “Five Parallel Algorithms for Production System Execution on the DADO Machine”; National Conference on Artificial Intelligence, AAAI-1984
Tien S-B.R., Raghavendra C.S.: “A Parallel Algorithm for Execution of Production Systems on HMESH Architecture”; Fall Joint Computer Conference, 1987, pp. 349–356
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1989 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Mistelberger, H., Bahr, E., Barachini, F. (1989). Eine Neue Methode zur Parallelisierung von Produktionensystemen. In: Retti, J., Leidlmair, K. (eds) 5. Österreichische Artificial-Intelligence-Tagung. Informatik-Fachberichte, vol 208. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-74688-8_21
Download citation
DOI: https://doi.org/10.1007/978-3-642-74688-8_21
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-51039-0
Online ISBN: 978-3-642-74688-8
eBook Packages: Springer Book Archive