A computational economy for grid computing and its implementation in the Nimrod-G resource broker
Future Generation Computer Systems - Grid computing: Towards a new computing infrastructure
Blueprint for the Intercloud - Protocols and Formats for Cloud Computing Interoperability
ICIW '09 Proceedings of the 2009 Fourth International Conference on Internet and Web Applications and Services
The Complement of Hypergraph Capacitated Min-k-Cut Problem
PAAP '10 Proceedings of the 2010 3rd International Symposium on Parallel Architectures, Algorithms and Programming
Cloud brokering mechanisms for optimized placement of virtual machines across multiple providers
Future Generation Computer Systems
A coordinator for scaling elastic applications across multiple clouds
Future Generation Computer Systems
| Hi-index | 0.00 |
With the rapid adoption of cloud computing, we are witnessing an explosion in the number of Cloud Providers. At the same time, the expectations of meeting SLAs is also growing amongst cloud customers. The competition has resulted in a lower prices and a better quality of service from most providers. Currently service providers offer a wide range of services (sizes of machine, availability, attached storage etc.) with complex pricing schemes (spot pricing, reservation pricing etc.). At the same time, customers have the need for distributed deployments of their applications driven by their own SLA commitments to customers around the world. The two factors taken together now necessitates the customer having to make a complex choice of deploying different applications and data blocks amongst a set of cloud providers. Optimizing cost, while meeting SLAs under this scenario is not easy - in this paper we look at deployment planning in the context of multi-site multi-cloud deployments and present a greedy heuristic to achieve the same. Our goal is to optimize cost while meeting SLA requirements. We show that our approach can lead to a 59% reduction in the total infrastructure cost incurred by the customer.