Approche Green Computing agile guidée par les ontologies d’accès automatique à des environnements intelligents

Abstract

Currently, everybody can access to existing services on the Cloud from a wide variety of mobile devices at any time and from anywhere (at home, working, on the car, etc.). The massive use of new heterogeneous mobile devices and technologies for discovering and deploying Cloud services has led a trade-off between costs and improved quality of services (e.g. fast response time, low price, improved security, the reduction of energy consumption and considerable emissions of Carbon, etc.). This trade-off has led most Cloud service providers to call for new intelligent, faster and energy-saving solutions. In a first part, the semantic modeling framework provides a semantic level that allows the automatic enrichment of client requests and the semantic filtering of quality services. It facilitates the semantic interoperability of heterogeneous Cloud services and manages the quality of services. This heterogeneity results from the representation of different languages and Cloud service providers. To meet the different quality of service requirements, the semantic model integrates the requirements and contextual preferences of customers. The semantic model (ontology) focuses on the energy optimization of data centers that store all Cloud services that support user activities and integrate new smart services according to its application domains (e-health, ecommunication, e-tourism, e-education, etc..) via a generic class of service class and its specific classes on the formalism of SPARQL semantic languages. This formalism is used for semantic filtering of domain services and classified by customer preferences and energy consumption. In a second part, the issue of optimizing the energy of services composite is handled. A new approach based on Semantic Web technologies and Ant Colony Optimization (ACO) algorithm which intends to reduce the energy consumption of a wide variety of Cloud services