Cloud computing is, says Salvatore Distefano of the Polytechnic of Milan and the University of Messina, Italy, and colleagues “a service-centric, distributed computing paradigm in which all capabilities and resources (usually geographically distributed) are provided to users as a service, to be accessed through the Internet without any specific knowledge of, expertise with, or control over the underlying technology infrastructure that supports them.” Moreover, it is an attractive emerging technology for wide area applications that usually require huge amount of computational, storage and sensing resources.
Cloud computing embraces everything from online file storage sites like Wuala, DropBox and Copy to amazon hosting services and web-based email and other applications and much more. In a recent issue of the International Journal of Computational Science and Engineering, the researchers explain how the volunteer paradigm, where companies, communities and users offer their contributions to a project or share their own services represents particular challenges to cloud computing.
The researchers and their collaborators have developed a framework – Cloud@Home – this infrastructure offers a “user-centric interface that acts as a unique, user friendly, point of access for users needs and requirements”. They have now proposed a technique for managing resources in volunteer clouds using a hierarchical reference to the Cloud@Home framework. They explain that by ordering the resources into a hierarchical cluster and implementing autonomic, distributed and self-adapting algorithms, the infrastructure can be managed – without a central manager – and so cope with the endless and inevitable shifts in resource availability so that users and resources can integrate functionality even when they are added asynchronously.
“The Cloud@Home resource management system detailed in our paper adopts and specifies autonomic and self-adapting algorithms that allow to built-up a Cloud@Home hierarchical-cluster infrastructure without any centralised management or control,” the team explains. The researchers add that in this approach, a node autonomously identifies its position in the cloud hierarchy by communicating with other nodes and also reacts to changes in the infrastructure as other nodes join and leave, using splitting and merging algorithms that exploit the elasticity of the systems hierarchy.
Fazio M., Puliafito A. & Distefano S. (2013). Managing volunteer resources in the cloud, International Journal of Computational Science and Engineering, 8 (3) 227. DOI: 10.1504/IJCSE.2013.055357