Change search
ReferencesLink to record
Permanent link

Direct link
Prediction-Based Enforcement of Performance Contracts
KTH, School of Information and Communication Technology (ICT), Computer and Systems Sciences, DSV. KTH, School of Computer Science and Communication (CSC), Centres, Centre for High Performance Computing, PDC.
Hewlett-Packard Laboratories, Information Dynamics Laboratory, Palo Alto.
2007 (English)In: Grid Economics and Business Models / [ed] Altmann, J; Veit, DJ, 2007, Vol. 4685, 71-82 p.Conference paper (Refereed)
Abstract [en]

Grid computing platforms require automated and distributed resource allocation with controllable quality-of-service (QoS). Market-based allocation provides these features using the complementary abstractions of proportional shares and reservations. This paper analyzes a hybrid resource allocation system using both proportional shares and reservations. We also examine the use of price prediction to provide statistical QoS guarantees and to set admission control prices.

Place, publisher, year, edition, pages
2007. Vol. 4685, 71-82 p.
, Lecture Notes In Computer Science, ISSN 0302-9743 ; 4685
Keyword [en]
admission control, proportional share, computational market
National Category
Computer and Information Science
URN: urn:nbn:se:kth:diva-8395DOI: 10.1007/978-3-540-74430-6_6ISI: 000249580900006ScopusID: 2-s2.0-38049079767ISBN: 978-3-540-74428-3OAI: diva2:13704
4th International Workshop on Grid Economics and Business Models (GECON 2007) Location: Rennes, France, Date: AUG 28, 2007
Available from: 2008-05-09 Created: 2008-05-09 Last updated: 2011-09-27Bibliographically approved
In thesis
1. Statistical Methods for Computational Markets: Proportional Share Market Prediction and Admission Control
Open this publication in new window or tab >>Statistical Methods for Computational Markets: Proportional Share Market Prediction and Admission Control
2008 (English)Doctoral thesis, comprehensive summary (Other scientific)
Abstract [en]

We design, implement and evaluate statistical methods for managing uncertainty when consuming and provisioning resources in a federated computational market. To enable efficient allocation of resources in this environment, providers need to know consumers' risk preferences, and the expected future demand. The guarantee levels to offer thus depend on techniques to forecast future usage and to accurately capture and model uncertainties. Our main contribution in this thesis is threefold; first, we evaluate a set of techniques to forecast demand in computational markets; second, we design a scalable method which captures a succinct summary of usage statistics and allows consumers to express risk preferences; and finally we propose a method for providers to set resource prices and determine guarantee levels to offer. The methods employed are based on fundamental concepts in probability theory, and are thus easy to implement, as well as to analyze and evaluate. The key component of our solution is a predictor that dynamically constructs approximations of the price probability density and quantile functions for arbitrary resources in a computational market. Because highly fluctuating and skewed demand is common in these markets, it is difficult to accurately and automatically construct representations of arbitrary demand distributions. We discovered that a technique based on the Chebyshev inequality and empirical prediction bounds, which estimates worst case bounds on deviations from the mean given a variance, provided the most reliable forecasts for a set of representative high performance and shared cluster workload traces. We further show how these forecasts can help the consumers determine how much to spend given a risk preference and how providers can offer admission control services with different guarantee levels given a recent history of resource prices.

Place, publisher, year, edition, pages
Stockholm: KTH, 2008. xii, 75 p.
Report series / DSV, ISSN 1101-8526 ; 08-006
Distributed Systems, Grid Computing, Performance Analysis, Workload Modeling, Middleware, Quality of Service, Prediction, Admission Control
National Category
Information Science
urn:nbn:se:kth:diva-4738 (URN)978-91-7178-924-2 (ISBN)
Public defence
2008-05-26, Hall C, KTH-Forum, Isafjordsgatan 39, Stockholm, 13:00
QC 20100909Available from: 2008-05-09 Created: 2008-05-09 Last updated: 2010-09-09Bibliographically approved

Open Access in DiVA

No full text

Other links

Publisher's full textScopus

Search in DiVA

By author/editor
Sandholm, Thomas
By organisation
Computer and Systems Sciences, DSVCentre for High Performance Computing, PDC
Computer and Information Science

Search outside of DiVA

GoogleGoogle Scholar
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Altmetric score

Total: 43 hits
ReferencesLink to record
Permanent link

Direct link