CS&E Seminar: Verena Kantere - 17 June 2010 - 12.00 @ Aula Magna
Speaker: Verena Kantere École Polytechnique Fédérale de Lausanne
Title: Online data services in the cloud
Abstract: The term ‘cloud computing’ is nowadays synonymous to computing services offered by large-scale infrastructures. The key to the success of cloud computing is to provide seamless and efficient management of large dynamic disseminated data collections, such as scientific data, in order to maximize their availability while minimizing capital expenditure. This talk leverages lessons learned from financial management to solve the problem of efficient cost management on clouds offering online data services. We propose a novel economy model for a cloud where users pay on-the-go for the data services they receive and user payments are used for service provision, service maintenance and profit. The economy employs a cost model that takes into account all the available resources in a cloud, such as disk space and I/O operations, CPU time and network bandwidth. In order to ensure the economic viability of the cloud, the cost of offering new services has to be amortized to prospective users that will use them. We propose a novel cost amortization model that predicts the extent of amortization in time and number of users. The economy is completed with a dynamic pricing scheme that achieves optimal cloud profit while ensuring user satisfaction with service prices.
The talk concludes with future research directions on the provision of online data services that are tailored to the user specifics and support data-intensive applications.
Verena Kantere received a Diploma in Electrical and Computer Engineering and a Ph.D. in Computer Science from the National Technical University of Athens, as well as a M.Sc. in Computer Science from the University of Toronto. Her research interests include peer-to-peer (P2P) overlays with structured and unstructured data, as well as multidimensional data sharing. During her graduate studies her research focused on P2P databases, dealing with the problems of data heterogeneity and coordination. Furthermore, she is interested and has shown research in the field of Semantic Web, concerning the problem of semantic similarity, annotation, clustering, and integration.
Since March 2008, she has been a postdoctoral researcher at the École Polytechnique Fédérale de Lausanne, in Switzerland, working on the problem of data service provisioning in the cloud, with a special interest in the needs of scientific applications.