Zhen Liu
ABSTRACT
We present a methodology for maximizing profits in a general class of e-commerce environments. The cost model is based on revenues that are generated when Quality-of-Service (QoS) guarantees are satisfied and on penalties that are incurred otherwise. The corresponding QoS criteria are derived from multiclass Service-Level-Agreements (SLAs) between service providers and their clients, which include the tail distributions of the per-class delays in addition to more standard QoS metrics such as throughput and mean delays. Our approach consists of formulating the optimization problem as a network flow model with a separable set of concave objective functions based on queueing-theoretic formulas, where the SLA classes are taken into account in both the constraints and the objective function. This problem is then solved via a fixed-point iteration. Numerous experiments illustrate the benefits of our approach.
- 1.R. Ahuja, T. Magnanti, and J. Orlin. Network Flows. Prentice Hall, Englewood Cliffs, New Jersey, 1993.Google Scholar
- 2.S. Borst, O. Boxma, and P. R. Jelenkovic. Asymptotic behavior of generalized processor sharing with long-tailed traffic sources. In Proceedings of the INFOCOM, Tel-Aviv, Israel, 2000.Google ScholarCross Ref
- 3.A. Federgruen and H. Groenevelt. The greedy procedure for resource allocation problems: Necessary and sufficient conditions for optimality. Operations Research, 34:909-918, 1986. Google ScholarDigital Library
- 4.B. Fox. Discrete optimization via marginal analysis. Management Science, 13:210-216, November 1966.Google ScholarDigital Library
- 5.G. Frederickson and D. Johnson. The complexity of selection and ranking in x + y and matrices with sorted columns. Journal of Computer and System Sciences, 24:197-208, 1982.Google ScholarCross Ref
- 6.Z. Galil and N. Megiddo. A fast selection algorithm and the problem of optimum distribution of effort. J. ACM, 26:58-64, 1979. Google ScholarDigital Library
- 7.T. Ibaraki and N. Katoh. Resource Allocation Problems: Algorithmic Approaches. The MIT Press, Cambridge, Massachusetts, 1988. Google ScholarDigital Library
- 8.F. P. Kelly. Reversibility and Stochastic Networks. John Wiley & Sons, New York, 1979.Google Scholar
- 9.L. Kleinrock. Queueing Systems Volume I: Theory. John Wiley and Sons, 1975. Google ScholarDigital Library
- 10.Z. Liu, N. Niclausse, and C. Jalpa-Villanueva. Web traffic modeling and performance comparison between HTTP 1.0 and HTTP 1.1. In E. Gelenbe, editor, Systems Performance Evaluation: Methodologies and Applications, pages 177-189. CRC Press, 2000. Google ScholarDigital Library
- 11.Z. Liu, M. S. Squillante, and J. L. Wolf. On maximizing service-level-agreement profits. Technical report, IBM Research Division, 2001.Google Scholar
- 12.D. A. Menasce, V. A. F. Almeida, R. Fonseca, and M. A. Mendes. A methodology for workload characterization of e-commerce sites. In Proceedings of the 1999 ACM Conference on Electronic Commerce, Denver, CO, 1999. Google ScholarDigital Library
- 13.D. A. Menasce, V. A. F. Almeida, R. Fonseca, and M. A. Mendes. Business-oriented resource management policies for e-commerce servers. Performance Evaluation, 42:223-239, 2000. Google ScholarDigital Library
- 14.A. K. Parekh and R. G. Gallager. A generalized processor sharing approach to flow control in integrated services networks - the single node case. IEEE/ACM Transactions on Networking, 1:344-357, 1993. Google ScholarDigital Library
- 15.A. K. Parekh and R. G. Gallager. A generalized processor sharing approach to flow control in integrated services networks - the multiple node case. IEEE/ACM Transactions on Networking, 2:137-150, 1994. Google ScholarDigital Library
- 16.P. Pirolli and J. E. Pitkow. Distributions of surfers paths through the world wide web: Empirical characterization. World Wide Web, 2:29-45, 1999. Google ScholarDigital Library
- 17.H. Takagi. Queueing Analysis: A Foundation of Performance Evaluation. Volume 1: Vacation and Priority Systems, Part 1. North Holland, Amsterdam, 1991.Google Scholar
- 18.A. Tantawi, D. Towsley, and J. Wolf. Optimal allocation of multiple class resources in computer systems. In ACM Sigmetrics Conference, May 1988. Google ScholarDigital Library
- 19.Z.-L. Zhang, Z. Liu, J. Kurose, and D. Towsley. Call admission control schemes under the generalized processor sharing scheduling discipline. Telecommunication Systems, 7:125-152, 1997.Google ScholarDigital Library
- 20.Z.-L. Zhang, Z. Liu, and D. Towsley. Closed-form deterministic performance bounds for the generalized processor sharing scheduling discipline. Journal of Combinatorial Optimaization,1, 1998.Google Scholar
- 21.Z. L. Zhang, D. Towsley, and J. Kurose. Statistical analysis of the generalized processor sharing scheduling discipline. IEEE Journal on Selected Areas in Communications, 13(6):1071-1080, 1995. Google ScholarDigital Library
- 22.A. Zwart and O. Boxma. Sojourn time asymptotics in the M/G/1 processor sharing queue. Queueing Systems, 35:141-166, 2000. Google ScholarDigital Library
Index Terms
- On maximizing service-level-agreement profits
Recommendations
On maximizing service-level-agreement profits
We present an initial study of a methodology for maximizing profits in a general class of e-commerce environments under a cost model in which revenues are generated when QoS guarantees are satisfied and penalties are incurred otherwise. The QoS ...
GIG/DISN quality of service and service level agreement management for integrated global wireless tactical services provider network
MILCOM'06: Proceedings of the 2006 IEEE conference on Military communicationsAs the Defense Information Systems Network (DISN) transitions to a native-IP network supporting converged unclassified and secret data, voice, and video on the Global Information Grid (GIG) backbone, an extensive Quality of Service (QoS) architecture ...
Class-Based Service Connectivity Using Multi-level Bandwidth Adaptation in Multimedia Wireless Networks
Due to the fact that quality of service requirements are not very strict for all traffic types, more calls of higher priority can be accommodated by reducing some bandwidth allocation for the bandwidth adaptive calls. The bandwidth adaptation to accept ...
Comments