Exponential Splitting Based Artificial Regeneration in Supercomputer Queueing Model
Pages 385 - 396
Abstract
In this paper we suggest the method for performance estimation of a realistic size supercomputer model. To do so, we apply exponential splitting to the generalized semi-Markov process model of a supercomputer and obtain the so-called artificial regeneration points which allows to apply regenerative confidence estimation. Numerical results illustrate the method.
References
[1]
Afanaseva L, Bashtova E, and Grishunina S Stability analysis of a multi-server model with simultaneous service and a regenerative input flow Methodol. Comput. Appl. Probab. 2019 22 1439-1455
[2]
Andronov, A.: Artificial regeneration points for stochastic simulation of complex systems. In: Simulation Technology: Science and Art. 10th European Simulation Symposium ESS 1998, pp. 34–40. SCS, Delft, The Netherlands (1998)
[3]
Asmussen S Applied Probability and Queues 2003 New York Springer
[4]
Asmussen, S., Glynn, P.W.: Stochastic Simulation: Algorithms and Analysis. No. 57 in Stochastic Modelling and Applied Probability, Springer, New York (2007). oCLC: ocn123113652
[5]
Astafiev SN and Rumyantsev AS Vishnevskiy VM, Samouylov KE, and Kozyrev DV Distributed computing of R applications using RBOINC package with applications to parallel discrete event simulation Distributed Computer and Communication Networks 2022 Cham Springer 396-407
[6]
Crane, M.A., Iglehart, D.L.: Simulating stable stochastic systems, I: General multiserver queues. J. ACM (JACM) 21(1), 103–113 (1974). http://dl.acm.org/citation.cfm?id=321805
[7]
Feitelson DG Workload Modeling for Computer Systems Performance Evaluation 2015 Cambridge Cambridge University Press
[8]
Glynn PW A GSMP formalism for discrete event systems Proc. IEEE 1989 77 1 14-23
[9]
Grosof, I., Harchol-Balter, M., Scheller-Wolf, A.: Stability for Two-class Multiserver-job Systems. arXiv:2010.00631 [cs] (2020). http://arxiv.org/abs/2010.00631
[10]
Harchol-Balter M The multiserver job queueing model Queueing Syst. 2022 100 201-203
[11]
Henderson SG and Glynn PW Regenerative steady-state simulation of discrete-event systems ACM Trans. Model. Comput. Simul. 2001 11 4 313-345
[12]
Karatsuba, E.A.: On the asymptotic representation of the Euler gamma function by Ramanujan. J. Comput. Appl. Math. 135(2), 225–240 (2001)., https://linkinghub.elsevier.com/retrieve/pii/S0377042700005860
[13]
Leahu, H., Mandjes, M., Oprescu, A.M.: A numerical approach to stability of multiclass queueing networks. IEEE Trans. Autom. Control 62(10), 5478–5484 (2017)., http://arxiv.org/abs/1606.07294, arXiv: 1606.07294
[14]
Morozov, E., Rumyantsev, A., Peshkova, I.: Monotonicity and stochastic bounds for simultaneous service multiserver systems. In: 2016 8th International Congress on Ultra Modern Telecommunications and Control Systems and Workshops (ICUMT), pp. 294–297. IEEE (2016)., http://ieeexplore.ieee.org/abstract/document/7765374/
[15]
Rumyantsev, A., Basmadjian, R., Golovin, A., Astafiev, S.: A three-level modelling approach for asynchronous speed scaling in high-performance data centres. In: Proceedings of the Twelfth ACM International Conference on Future Energy Systems, pp. 417–423. e-Energy 2021, Association for Computing Machinery, New York, NY, USA (2021).
[16]
Rumyantsev A and Peshkova I Dudin A, Nazarov A, and Moiseev A Artificial regeneration based regenerative estimation of multiserver system with multiple vacations policy Information Technologies and Mathematical Modelling. Queueing Theory and Applications 2019 Cham Springer 38-50
[17]
Thorrison H Coupling, Stationarity, and Regeneration 2000 New York Springer
Index Terms
- Exponential Splitting Based Artificial Regeneration in Supercomputer Queueing Model
Index terms have been assigned to the content through auto-classification.
Recommendations
A discrete-time queueing model with abandonments
QTNA '10: Proceedings of the 5th International Conference on Queueing Theory and Network ApplicationsThis paper presents a multi-server queueing model with abandonments in discrete time. In every time slot a generally distributed number (batch) of customers arrives. The different numbers of arrivals in consecutive slots are mutually independent. Each ...
Distributed Simulation of Supercomputer Model with Heavy Tails
SupercomputingAbstractIn this paper we apply the distributed regenerative estimation of the steady-state performance to the supercomputer queueing model with heavy-tailed distributions. Discrete-event simulation by generalized semi-Markov processes is the key tool for ...
Exponential queuing system with negative customers and bunker for ousted customers
AbstractConsideration was given to the queuing system with Poisson flows of incoming positive and negative customers. For the positive customers, there is an infinite-capacity buffer. The arriving negative customer knocks out a positive customer queued in ...
Comments
Information & Contributors
Information
Published In
Sep 2022
446 pages
ISBN:978-3-031-23206-0
DOI:10.1007/978-3-031-23207-7
© The Author(s), under exclusive license to Springer Nature Switzerland AG 2022.
Publisher
Springer-Verlag
Berlin, Heidelberg
Publication History
Published: 01 January 2023
Author Tags
Qualifiers
- Article
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 0Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 08 Feb 2025