Abstract
In a series of papers, Kleinrock proposed a performance metric called power for stable queueing systems in equilibrium, which captures the tradeoff every queue makes between work done and time needed to. In particular, he proved that in the M / GI / 1 family of models, the maximal power is obtained when the mean number of customers in the system is exactly one (a keep the pipe empty property). Since then, this metric has been used in different works, in the analysis of communication systems. In this paper we add some results about power, showing in particular that the concept extends naturally to Jackson product form queueing networks, and that, again, the keep the pipe empty property holds. We also show that this property does not hold in general for single-node models of the GI / GI / 1 type, or when the storage capacity of the system is finite. The power metric takes into account the cost in time to provide service, but not the cost associated with the server itself. For this purpose, we define a different metric, which we call effectiveness, whose aim is to also include this aspect of systems. Both metrics coincide on single server models, but differ on multi-server ones, and on networks. We provide arguments in support of this new metric and, in particular, we show that in the case of a Jackson network, the keep the pipe empty property again holds.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Of course, this doesn’t mean that the mean number of units waiting in the queue is 0: if \(a=2 - \sqrt{2}\), the mean length of the waiting queue is \(1 - a = \sqrt{2} - 1\).
References
Kleinrock, L.: Queueing Systems, vol. I. Wiley Interscience, New York (1975)
Giessler, A., Hanle, J., Konig, A., Pade, E.: Free buffer allocation - an investigation by simulation. Comp. Net. 1(3), 191–204 (1978)
Kleinrock, L.: Power and deterministic rules of thumb for probabilistic problems in computer communications. In: International Conference on Communications, pp. 43.1.1–43.1.10, Boston, June 1979
Kleinrock, L.: On flow control in computer networks. In: International Conference on Communications, vol. II, pp. 27.2.1–27.2.5, Toronto, July 1979
Gail, R., Kleinrock, L.: An invariant property of computer network power. In: International Conference on Communications, pp. 63.1.1–63.1.5, Denver, June 1981
Varshney, P.K., Dey, S.: Fairness in computer networks: A survey. J. Inst. Electron. Telecommun. Eng., May-June (1990)
Kleinrock, L., Huang, J.-H.: On parallel processing systems: amdahl’s law generalized and some results on optimal design. IEEE Tran. Soft. Eng. 18(5), 434–447 (1992)
Rosti, E., Smirni, E., Dowdy, L.W., Serazzi, G., Carlson, B.M.: Robust partitioning policies of multiprocessor systems. Perform. Eval. 19, 141–165 (1993)
Bournas, R.M.: Bounds for optimal flow control window size design with application to high-speed networks. J. Franklin Inst. 1, 77–89 (1995)
Kolias, C., Kleinrock, L.: Throughput analysis of multiple input-queueing in ATM switches. In: Mason, L., Casaca, A. (eds.) IFIP-IEEE Broadband Communications, pp. 382–393. Chapman and Hall, Boston (1996)
Hyytiä, E., Lassila, P., Penttinen, A., Roszik, J.: Traffic load in a dense wireless multihop network. In: Proceedings of the 2nd ACM International Workshop on Performance Evaluation of Wireless Ad Hoc, Sensor, and Ubiquitous Networks (PE-WASUN2005), pp. 9–17, Montreal (2005)
Inoie, A., Kameda, H., Touati, C.: A paradox in optimal flow control of M/M/n queues. Comput. Op. Res. 33, 356–368 (2006)
Safaei, F., Khonsari, A., Fathy, M., Ould-Khaoua, M.: Communication delay analysis of fault-tolerant pipelined circuit switching in torus. J. Comput. Syst. Sci. 73(8), 1131–1144 (2007)
Medidi, S., Ding, J., Garudapuram, G., Wang, J., Medidi, M.: An analytical model and performance evaluation of transport protocols for wireless ad hoc networks. In: Proceedings 41st Annual Simulation Symposium (ANSS-41), Ottawa, 14–16 April 2008
Rubino, G.: On Kleinrock’s power metric for queueing systems. In: Proceedings of the 5th International Workshop on Performance Modelling and Evaluation of Computer and Telecommunication Networks (PMECT 2011), Maui (2011)
Chung, P.-T., Van Slyke, R.: Equilibrium analysis for power based flow control algorithm. Appl. Math. Sci. 6(9), 443–454 (2012)
Yemini, Y.: A balance of power principle for decentralized resource sharing. Comput. Netw. 66, 46–51 (2014)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Rubino, G. (2015). Power and Effectiveness in Queueing Systems. In: Campos, J., Haverkort, B. (eds) Quantitative Evaluation of Systems. QEST 2015. Lecture Notes in Computer Science(), vol 9259. Springer, Cham. https://doi.org/10.1007/978-3-319-22264-6_18
Download citation
DOI: https://doi.org/10.1007/978-3-319-22264-6_18
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-22263-9
Online ISBN: 978-3-319-22264-6
eBook Packages: Computer ScienceComputer Science (R0)