IEEE Transactions on Software Engineering
Characterization of E-Commerce Traffic
WECWIS '02 Proceedings of the Fourth IEEE International Workshop on Advanced Issues of E-Commerce and Web-Based Information Systems (WECWIS'02)
Performance by Design: Computer Capacity Planning By Example
Performance by Design: Computer Capacity Planning By Example
A capacity management service for resource pools
Proceedings of the 5th international workshop on Software and performance
Dynamic Provisioning of Multi-tier Internet Applications
ICAC '05 Proceedings of the Second International Conference on Automatic Computing
Live migration of virtual machines
NSDI'05 Proceedings of the 2nd conference on Symposium on Networked Systems Design & Implementation - Volume 2
1000 Islands: Integrated Capacity and Workload Management for the Next Generation Data Center
ICAC '08 Proceedings of the 2008 International Conference on Autonomic Computing
Generating Adaptation Policies for Multi-tier Applications in Consolidated Server Environments
ICAC '08 Proceedings of the 2008 International Conference on Autonomic Computing
How to parameterize models with bursty workloads
ACM SIGMETRICS Performance Evaluation Review
ICAC '09 Proceedings of the 6th international conference on Autonomic computing
An optimized capacity planning approach for virtual infrastructure exhibiting stochastic workload
Proceedings of the 2010 ACM Symposium on Applied Computing
IEEE Transactions on Software Engineering
Hi-index | 0.00 |
As enterprises increasingly adopt the cloud paradigm, there is a need for tools that can help cloud service providers (SPs) decide on service level agreements with customers. Existing approaches have not considered several important challenges such as workload burstiness, workload uncertainty, and scalability that need to be addressed to realize such tools. This paper describes a trace-based framework developed to consider these issues. We present simulation experiments that show that our framework is scalable and provides more accurate planning insights to SPs than those that ignore complex workload behaviour such as burstiness. Furthermore, the results also illustrate how SPs can exploit our framework to assess the risks of workload uncertainty.