Category Archives: Uncategorized

Paper accepted in IEEE CLOUD

The paper “How to Supercharge the Amazon T2: Observations and Suggestions” by Jiawei Wen, Lihua Ren, Feng Yan, Daniel J. Dubois, Giuliano Casale, and Evgenia Smirni has been accepted for IEEE CLOUD 2017. The paper proposes a methodology to increase the performance benefits of T2 instances on Amazon EC2.

Best paper award at ACM/SPEC ICPE 2016

Our paper Maximum Likelihood Estimation of Closed Queueing Network Demands from Queue Length Data;, co-authored by W. Wang, G. Casale, A. Kattepur and M. Nambiar has received the best paper award at ICPE2016, the IEEE International Conference on Performance Engineering!

The paper proposes maximum likelihood (ML) estimators for service demands in closed queueing networks with load-independent and load-dependent stations. The obtained ML estimators are expressed in implicit form and require only to compute mean queue lengths and marginal queue length probabilities from an empirical dataset.

An open dataset for this paper is available on Zenodo.

Best paper award at IEEE ICCAC

Our paper Autonomic Provisioning and Application Mapping on Spot Cloud Resources;, co-authored by D. Dubois and G. Casale, has received the best paper award at ICCAC2015, the IEEE International Conference on Cloud and Autonomic Computing!

The paper proposes a deployment model for cloud applications based on the notion of random environment. The random environment is used to model the risk of loss of virtual machines due to spot price fluctuations. A heuristic is proposed to quickly find a good local optimum to the deployment model.

An open dataset for this paper is available on Zenodo.

Accepted paper at CNSM 2015

The paper “Experiments or Simulation? A Characterization of Evaluation Methods for In-Memory Databases” by Karsten Molka and Giuliano Casale has been accepted for full paper presentation at IFIP/IEEE CNSM 2015.

The paper compares the applicability of response surface methods and queueing network simulation in performance assessment of in-memory databases, based on an extensive experimental study on SAP HANA. Simulation is shown to be surprisingly accurate against several performance metrics such as response times, server utilization, energy consumption and memory usage.