DataSys: Data-Intensive Distributed Systems LaboratoryData-Intensive Distributed Systems Laboratory

Illinois Institute of Technology
Department of Computer Science

Towards Co-operative Economic Meta-Scheduling in Grid and Cloud Systems Kyle Chard

Dr. Kyle Chard

Senior Research Project Professional

Computation Institute

University of Chicago & Argonne National Laboratory

Stuart Building 204
Tuesday, September 13th, 2011
12:45PM - 1:45PM

Abstract: The computational landscape is littered with 'islands' of disjoint resource providers that lack communication and coordination between one another. As a first step towards a global computing infrastructure we propose using a generic economic meta-scheduling architecture to facilitate federated resource allocation and therefore allow users to provision resources from a wide range of heterogeneous service providers. The use of economic resource allocation in distributed systems has long been proposed as an efficient means of resource allocation. However, until recently adoption has been slow due to, amongst other things, high overhead and poor performance. In this talk we extend upon the economic models currently used in Cloud computing, specifically focusing on secure privacy preserving auctions that facilitate the use of a 'co-op' meta-scheduling architecture. In addition, we present a unique case study showing the use of this meta-scheduling architecture in creating a 'Social Cloud' - a dynamic Cloud computing infrastructure composed of virtualized resources contributed by members of a social network.  

Bio: Dr. Kyle Chard is a Senior Research Project Professional at the Computation Institute, University of Chicago and Argonne National Laboratory. He received his PhD in Computer Science from Victoria University of Wellington in 2011, having previously received his BSc (Hons) in Computer Science and BSc in Mathematics and Electronics. His research interests include distributed meta-scheduling, Grid and Cloud computing, economic resource allocation, social computing, and medical natural language processing.