article

Free access

On optimization of polling policy represented by neural network

Author:

Yutaka MatsumotoAuthors Info & Claims

ACM SIGCOMM Computer Communication Review, Volume 24, Issue 4

Pages 181 - 190

https://doi.org/10.1145/190809.190331

Published: 01 October 1994 Publication History

Abstract

This paper deals with the problem of scheduling a server in a polling system with multiple queues and complete information. We represent the polling policy by a neural network; namely, given the number of waiting customers in each queue, the server determines next queue he should visit according to the output of the neural network. By using the simulated annealing method, we improve the neural polling policy in such a way that the mean delay of customers is minimized. Numerical results show that the present approach is especially valid for asymmetric polling systems whose analytical optimization is considered intractable.

References

[1]

E. Aarts and J. Korst, Simulated annealing and Boltzmann machines, John Wiley & Sons, 1989.

Digital Library

[2]

N. Baba, "A new approach for finding the global minimum of error function of neural networks," Neural Networks, vol.2, pp.367- 373, 1989.

Digital Library

[3]

O.J. Boxma, H. Levy and J.A. Weststrate, "Optimization of polling systems," Proc. of PERFORMANCE'90, Elsevier Science Publishers B.V., 349-361, 1990.

Digital Library

[4]

S. Browne and U. Yechiali, "Dynamic priority rules for cyclic-type queues," Adv. Appl. Prob., 21,432-450, 1989.

[5]

G. L. Choudhury and H. Takagi, "Comments on "Exact results for nonsymmetric token ring systems," IEEE Trans. on Commun., vol. COM-38, no.8, pp.1125-1127, August 1990.

[6]

O. Fabian and H. Levy, "Polling system optimization through dynamic routing policies," Proc. of IEEE INFOCOM'93, 2b.3.1-2b.3.7, 1993.

[7]

M. J. Ferguson and Y. J. Aminetzah, "Exact results for nonsymmetric token ring systems," IEEE Trans. on Commun., vol. COM-33, no.3, pp.223-231, March 1985.

[8]

M. Hofri and K. W. Ross, "On the optimal control of two queues with server set-up times and its analysis," SIAM J. on Computing, 16, pp.399-419~ 1987.

Digital Library

[9]

K. Ishida, Y. Matsumoto and N. Okino, "The effect of correlated inputs on discrete Kohonen networks," Artificial Neural Networks, 2, I. Aleksander et. al. (eds.), pp.353-357, North- Holland, September 1992.

[10]

K. Ishida, Y. Matsumoto and N. Okino, "First passage time analysis of topologically correct feature maps in discrete Kohonen networks," Proc. of Int. Joint Conf. on Neural Networks, IJCNN'93, pp.2460-2463, October 1993.

[11]

L. Kleinrock, Queueing Systems, vol.1, John Wiley &: Sons, 1975.

Digital Library

[12]

T. Kohonen, G. Barna and R. Chrisley, "Statistical pattern recognition with neural networks: Benchmarking studies," Proc. of iEEE Int. Conf. on Neural Networks, ICNN'88, pp.I-61-I-68, 1988.

[13]

T. Kohonen, "The self-organizing map," Proceedings of the IEEE, vol.78, no.9, pp.1464- 1480, September 1990.

[14]

Z. Liu, P. Nain and D. Towsley, "On optimal polling policies," Queueing Systems and Their Applications, vol.11, pp.59-82, 1992.

Digital Library

[15]

S. Markon, H. Kita and Y. Nishikawa, "Reinforcement learning for stochastic system control by using a feature extraction with BP neural networks," Tech. Rep. of iEICE, NC91- 126, 209-214, 1991.

[16]

N. Miyoshi, Y. Takahashi and T. Hasegawa, "Discount optimal server assignment policy for symmetric polling systems," preprint, 1992.

[17]

D. E. Rumelhart, G. E. Hinton and R. Williams, "Learning internal representations by error propagation," Parallel Distributed Processing: Explorations in the Microstructure of Cognition, vol.1, Cambridge, MA: MIT Press.

Digital Library

[18]

H. Takagi, Analysis of polling systems, MIT Press, 1986.

Digital Library

[19]

J. Walrand, An introduction to Queueing Networks, Prentice Hall, NJ, 1988.

Cited By

Efrosinin DVishnevsky VStepanova N(2023)Optimal Scheduling in General Multi-Queue System by Combining Simulation and Neural Network TechniquesSensors10.3390/s2312547923:12(5479)Online publication date: 10-Jun-2023
https://doi.org/10.3390/s23125479
Chen M(2015)Neuro-fuzzy approach for online message schedulingEngineering Applications of Artificial Intelligence10.1016/j.engappai.2014.10.00238(59-69)Online publication date: Feb-2015
https://doi.org/10.1016/j.engappai.2014.10.002
Sato HMatsumoto YOkino NPearson DSteele NAlbrecht R(1995)Policy Optimization by Neural Network and Its Application to Queueing Allocation ProblemArtificial Neural Nets and Genetic Algorithms10.1007/978-3-7091-7535-4_90(344-347)Online publication date: 1995
https://doi.org/10.1007/978-3-7091-7535-4_90
Show More Cited By

Index Terms

Recommendations

On optimization of polling policy represented by neural network
SIGCOMM '94: Proceedings of the conference on Communications architectures, protocols and applications

This paper deals with the problem of scheduling a server in a polling system with multiple queues and complete information. We represent the polling policy by a neural network; namely, given the number of waiting customers in each queue, the server ...
Sojourn time distribution in polling systems with processor-sharing policy

We consider a polling system with a single server and multiple queues where customers arrive at the queues according to independent Poisson processes. The server visits and serves the queues in a cyclic order. The service discipline at all queues is ...
Heavy-traffic asymptotics of a priority polling system with threshold service policy

In this paper, by the singular-perturbation technique, we investigate the heavy-traffic behavior of a priority polling system with three queues under threshold policy. It turns out that the scaled queue-length of the critically loaded queue is ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image ACM SIGCOMM Computer Communication Review

ACM SIGCOMM Computer Communication Review Volume 24, Issue 4

Oct. 1994

318 pages

ISSN:0146-4833

DOI:10.1145/190809

Editor:
David Oran
Digital Equipment Corp., Littleton, MA

Issue’s Table of Contents

SIGCOMM '94: Proceedings of the conference on Communications architectures, protocols and applications
October 1994
328 pages
ISBN:0897916824
DOI:10.1145/190314
Chairman:
Jon Crowcroft
Univ. College London, UK

Copyright © 1994 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 01 October 1994

Published in SIGCOMM-CCR Volume 24, Issue 4

Check for updates

Qualifiers

Article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

6
Total Citations
View Citations
519
Total Downloads

Downloads (Last 12 months)72
Downloads (Last 6 weeks)26

Reflects downloads up to 22 Feb 2025

Other Metrics

View Author Metrics

Citations

Cited By

Efrosinin DVishnevsky VStepanova N(2023)Optimal Scheduling in General Multi-Queue System by Combining Simulation and Neural Network TechniquesSensors10.3390/s2312547923:12(5479)Online publication date: 10-Jun-2023
https://doi.org/10.3390/s23125479
Chen M(2015)Neuro-fuzzy approach for online message schedulingEngineering Applications of Artificial Intelligence10.1016/j.engappai.2014.10.00238(59-69)Online publication date: Feb-2015
https://doi.org/10.1016/j.engappai.2014.10.002
Sato HMatsumoto YOkino NPearson DSteele NAlbrecht R(1995)Policy Optimization by Neural Network and Its Application to Queueing Allocation ProblemArtificial Neural Nets and Genetic Algorithms10.1007/978-3-7091-7535-4_90(344-347)Online publication date: 1995
https://doi.org/10.1007/978-3-7091-7535-4_90
Papadimitriou GVakali APomportsis A(2004)A learning-automata-based controller for client/server systemsNeurocomputing10.1016/j.neucom.2003.12.00161:C(381-394)Online publication date: 1-Oct-2004
https://dl.acm.org/doi/10.1016/j.neucom.2003.12.001
Papadimitriou GVakali APomportsis A(2000)Designing a learning-automata-based controller for client/server systems: a methodologyProceedings 12th IEEE Internationals Conference on Tools with Artificial Intelligence. ICTAI 200010.1109/TAI.2000.889903(422-425)Online publication date: 2000
https://doi.org/10.1109/TAI.2000.889903
Sato HMatsumoto YOkino NSmith GSteele NAlbrecht R(1998)The Effect of Recurrent Networks on Policy Improvement in Polling SystemsArtificial Neural Nets and Genetic Algorithms10.1007/978-3-7091-6492-1_96(436-439)Online publication date: 1998
https://doi.org/10.1007/978-3-7091-6492-1_96

View Options

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

Figures

Tables

Media

View Issue’s Table of Contents