Users’ time preference based stochastic resource allocation in cloud spot market: cloud provider’s perspective

No Thumbnail Available
Files
3493.pdf(210.65 KB)
Published Version
Date
2017
Authors
Mukherjee, Anik
Sundarraj, R. P.
Dutta, Kaushik
Journal Title
Journal ISSN
Volume Title
Publisher
Karlsruher Institut für Technologie (KIT)
Published Version
Research Projects
Organizational Units
Journal Issue
Abstract
Cloud Computing spot markets have enabled the users to make use of the spare computing capacities of the cloud providers at a relatively cheaper price which in turn has given the providers such as Amazon and Google an opportunity to earn extra money by auctioning-off the underutilized resources. However, resource availability is a problem in the spot market owing to spot-price fluctuations. Ignoring the customer’s preference is one of the potential reasons behind this. In this paper, we propose a time preference (value of service at different points of time) based stochastic integer linear programming model to allocate the cloud resources among the cloud users with a view to maximizing the revenue of cloud providers from the spot-market.
Description
Keywords
Cloud computing , Resource allocation , Spot market , Time preference , Stochastic programming.
Citation
Mukherjee, A., Sundarraj, R. P. and Dutta, K. 2017. 'Users’ time preference based stochastic resource allocation in cloud spot market: Cloud provider’s perspective'. In: Maedche, A., vom Brocke, J., Hevner, A. (eds.) Designing the Digital Transformation: DESRIST 2017 Research in Progress Proceedings of the 12th International Conference on Design Science Research in Information Systems and Technology. Karlsruhe, Germany. 30 May - 1 Jun. Karslruhe: Karlsruher Institut für Technologie (KIT), pp. 92-100