Title: SLA-driven dynamic capacity forecasting and resource allocation with risk analysis on clouds

Authors: G.M. Siddesh; K.G. Srinivasa

Addresses: Jawaharlal Nehru Technological University, Hyderabad Kukatpally, Hyderabad 500085, Andhra Pradesh, India; Department of Information Science and Engineering, MS Ramaiah Institute of Technology, Bangalore 560054, India ' Department of Computer Science and Engineering, MS Ramaiah Institute of Technology, Bangalore 560054, India

Abstract: With the advent of gaining popularity in cloud computing, there is an increase in demand of resources among the heterogeneous workload types on cloud. Resource management is a key challenging problem that is faced by the cloud service providers, by achieving business goals and agreed level of service with the subscribers. This paper focuses on dynamic resource allocation with risk analysis by meeting service level agreements. Further proposed framework handles heterogeneous workload types by dynamic capacity planning with risk assessment to maximise the profit and resource utilisation on clouds. In addition to advanced resource reservation, SLA-based scheduling/rescheduling with risks involved in resource allocation is considered in the proposed model. The experimental results demonstrate that proposed framework maximises the resource utilisation and profit gain of the cloud service provider when evaluated against widely used static configuration strategy.

Keywords: capacity forecasting; risk assessment; service level agreements; SLAs; scheduling; rescheduling; cloud computing; resource allocation; resource management.

DOI: 10.1504/IJCNDS.2013.056227

International Journal of Communication Networks and Distributed Systems, 2013 Vol.11 No.3, pp.327 - 346

Published online: 28 Feb 2014 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article