Using smart grids to build low carbon networks is one of the most challenging topics in ICT (Information and Communication Technologies) industry. One of the first worldwide initiatives is the GreenStar Network, completely powered by renewable energy sources such as solar, wind and hydroelectricity across Canada. Smart grid techniques are deployed to migrate data centers among network nodes according to energy source availabilities, thus CO2 emissions are reduced to minimal. Such flexibility requires a scalable resource management support, which is achieved by virtualization technique. It enables the sharing, aggregation, and dynamic configuration of a large variety of resources. A key challenge in developing such a virtualized management is an efficient resource description and discovery framework, due to a large number of elements and the diversity of architectures and protocols. In addition, dynamic characteristics and different resource description methods must be addressed. An ontology-based resource description framework is developed particularly for ICT energy management purpose, where the focus is on energy-related semantic of resources and their properties. A scalable resource discovery method in large and dynamic collections of ICT resources, based on semantics similarity inside a federated index using a Bayesian belief network, is proposed. This framework allows users to identify the cleanest resource deployments in order to achieve a given task, taking into account the energy source availabilities. Experimental results are shown to compare the proposed framework with a traditional one in terms of GHG emission reductions.
Resource discovery mechanism uses ontology to skip from text based discovery mechanism to semantic one. As shown in the figure bellow, resource description contains information on energy source. This method enables the most resource efficient selection in terms of GHG reduction.
The Description and Discovry framework is illustrated in the figure bellow. Resource providers specify ontology concepts and description for exposed resources. A local index registers all resources. The end user searches for appropriate resources by submitting a request containing key words. The semantic analyzer performs information processing based on resource descriptions in order to determine the type of resources. Based on type of energy an efficient resource with low GHG emissions can be selected.
As shown in the figure bellow, in the classic method the first resource returned by the discovery mechanism is used. But in the proposed method the selection of the resource is based on type of energy source. This method can reduce a significant quantities of CO2.
These research results are published in Proceedings of the First IEEE International Conference on Smart Grid Communications.
A. Daouadji, K.-K. Nguyen, M. Lemay, and M. Cheriet. Ontology-based Framework for Low Carbon Resource Discovery. In Proceedings of the First IEEE International Conference on Smart Grid Communications, Gaithersberg, Maryland, October 4-6, 2010.