Issue No. 06 - June (2008 vol. 57)
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/TC.2008.37
Giuliano Casale , College of William and Mary
Richard Muntz , UCLA
Giuseppe Serazzi , Politecnico di Milano
We propose the Geometric Bounds (GB), a new family of fast and accurate non-iterative bounds on closed queueing network performance metrics that can be used in the on-line optimization of distributed applications. Compared to state-of-the-art techniques such as the Balanced Job Bounds (BJB), the GB achieve higher accuracy at similar computational costs, limiting the worst-case bounding error typically within 5%-13% when for the BJB it is usually in the range 15%-35%. Optimization problems that are solved with the GB bounds return solutions that are much closer to the global optimum than with existing bounds. We also show that the GB technique generalizes as an accurate approximation to closed fork-join networks commonly used in disk, parallel and database models, thus extending the applicability of the method beyond the optimization of basic product-form networks.
Performance of Systems, Queuing theory, Performance, Operating Systems, Software/Software Engineering, Modeling techniques, Performance of Systems, Computer Systems Organization
G. Casale, G. Serazzi and R. Muntz, "Geometric Bounds: A Noniterative Analysis Technique for Closed Queueing Networks," in IEEE Transactions on Computers, vol. 57, no. , pp. 780-794, 2008.