Towards an event-aware approach for ubiquitous computing based on automatic service composition and selection
Loading...
Date
2012-08
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Springer-Verlag
Abstract
Service composition in ubiquitous and pervasive environments is becoming an active research domain which has received widespread attention in recent years. It aims to offer seamless access to a variety of high level and complex functionalities by combining existing services. Several frameworks have been designed to support service composition in ubiquitous and pervasive environments. Although some ubiquitous requirements and challenges are relatively well addressed by the proposed frameworks, others are still at a preliminary stage and should be well explored such as, automatic service composition with little human intervention, context and quality of service management, and service selection under uncertainty and changes. For this end, we propose in this paper a layered design approach for flexible and failure tolerant service composition using two main phases: off-line phase and on-line phase. In the off-line phase, a global graph that links all the available abstract services is generated automatically using rule-based technique. The defined rules aim at optimizing both the number of services and parameters that appear in the global graph. In the on-line phase, a subgraph is extracted spontaneously from the global graph according to the occurred and detected event in the environment at real time. Thereafter, the extracted subgraph is performed using service selection strategies. A prototype implementation including real services for event detection in smart home shows clearly the feasibility of the proposed approach in real environment. Also, the set of performed evaluation tests reveals the interest and the performance of the proposed algorithms.
Description
Keywords
Ubiquitous and pervasive computing, Service composition, Context and QoS-based service selection, Uncertainty management, Event handling