Title :
Energy Efficient VM Placement Supported by Data Analytic Service
Author :
Dapeng Dong ; Herbert, J.
Author_Institution :
Dept. of Comput. Sci., Univ. Coll. Cork, Cork, Ireland
Abstract :
The popularity and commercial use of cloud computing has prompted an increased concern among cloud service providers for energy efficiency while still maintaining quality of service. One of the key techniques used for the efficient use of cloud server resources is virtual machine placement. This work introduces a precise VM placement algorithm that ensures energy efficiency and also prevents Service Level Agreement (SLA) violation. The mathematical model of the algorithm is supported by a sophisticated data analytic system implemented as a service. The precision of the algorithm is achieved by allowing each individual VM to build its own data model on demand over an appropriate time horizon. Thus the data model can reflect accurately the characteristics of resource usage of the VM. The algorithm can communicate synchronously or asynchronously with the data analytic service which is deployed as a cloud-based solution. In the experiments, several advanced data modelling and use forecasting techniques were evaluated. Results from simulation-based experiments show that the VM placement algorithm (supported by the data analytic service) can effectively reduce power consumption, the number of VM migrations, and prevent SLA violation, it also compares very favourably with other placement algorithms.
Keywords :
cloud computing; data analysis; data models; energy conservation; power aware computing; quality of service; service-oriented architecture; virtual machines; SLA; advanced data modelling; cloud computing; cloud server resources; cloud service providers; cloud-based solution; data analytic service; energy efficiency; energy efficient VM placement; mathematical model; power consumption; precise VM placement algorithm; quality of service; resource usage characteristics; service level agreement; simulation-based experiments; sophisticated data analytic system; virtual machine placement; Data analysis; Data models; Heuristic algorithms; Power demand; Prediction algorithms; Predictive models; Servers; VM placement; cloud computing; data analytic services; energy efficiency;
Conference_Titel :
Cluster, Cloud and Grid Computing (CCGrid), 2013 13th IEEE/ACM International Symposium on
Conference_Location :
Delft
Print_ISBN :
978-1-4673-6465-2
DOI :
10.1109/CCGrid.2013.94