Yunni Xia

Cloud computing is a recently developed new technology for complex systems with massive service sharing, which is different from the resource sharing of the grid computing systems. IaaS is a provision model in which an organization outsources the equipment used to support operations, including storage, hardware, servers and networking components. Instances are created on IaaS computational resources in the form of virtual machines (VM) and deployed in a cloud data center. Quality modeling and analysis of IaaS clouds are not easy tasks because of the complexity of the automated provisioning mechanism and dynamically changing cloud environment. A careful investigation into existing methods has found their limitations when applied to address the quality analysis challenge: 1) incomplete modeling of details such as machine provisioning, request handling, and machine failure/repair process, 2) reliance on measurement-based QoS data which require extensive experimentations and real-system tests, and 3) separate modeling of provisioning phases which simplifies the solution but loses accuracy. In this study, we propose a comprehensive quality determination framework for Infrastructure-as-a-Service clouds. It features with: 1) taking machine provisioning, request handling, machine occupation/releasing, and machine failure/repair process mechanism into an unified analytical model, 2) employing queuing networks as the fundamental means of quality analysis, 3) analytical solutions of three important quality metrics, 4) analytical modeling of different strategies of machine warm-up/cool-down and the ability to identify the optimal balance between system overhead and performance, and 5) a confidence interval analysis to validate model correctness based on simulative QoS data. The proposed framework can aid the design and optimization of industrial cloud computing systems and practitioners’ understanding of quality aspects of cloud-based applications.

Biography: Yunni Xia received the PhD degree from the computer science Department, Peking University, China, in 2008. He is currently an Associate Professor with the School of Computers, Chongqing University, China. He is an active member of the special interest group of Petri nets of China's computer federation. His research interests include performance evaluation, Petri nets, stochastic analysis, service-oriented architectures. He is a member of the IEEE.