PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Policy-based autonomous bidding for overload management in eCommerce websites
Toni Moreno, Nicolas Poggi, Josep Lluis Berral, Ricard Gavaldà and Jordi Torres
In: Group Decision and Negotiation Meeting 2007, May 14th-17th, 2007, Mount Tremblant, Québec, Canada.

Abstract

In eCommerce applications with heterogeneous traffic, which typically run on execution environments where resources are shared with other applications, being able to dynamically adapt to the application workload in real time is crucial for proper self-management and business efficiency. The AUGURES platform has recently introduced a novel approach to deal with server overload situations, based on the prioritization of sessions according to the expected revenue that the session is likely to generate. However, by denying access to exceeding low priority users, the website may be loosing potential customers, while there might be other resources available in the market of the execution environment, be it a server, a server farm, or a grid. This paper presents an extension of the AUGURES architecture with a simple policy-based autonomous bidding agent that generates automated bids for the extra resources needed to execute the transactions that have been refused by the server due to overload.

PDF - PASCAL Members only - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Conference or Workshop Item (Paper)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Computational, Information-Theoretic Learning with Statistics
User Modelling for Computer Human Interaction
ID Code:3331
Deposited By:Ricard Gavaldà
Deposited On:07 February 2008