Abstract

AbstractEdge Computing (EC) has gained a lot of attention from both industry and academia as it is an essential paradigm that addresses the Quality of Service (QoS) of Internet of Things (IoT) applications. The QoS metrics are defined in a Service Level Agreement (SLA) that must be fulfilled by Service Provider (SP). Indeed, the management of QoS in EC is not a trivial process due to the dynamicity nature of both EC and IoT devices as well as the IoT applications’ requirements. This rises the need to develop a Self-adaptive System (SAS) that is aware of IoT- and EC-nature and provides a continuous management over the operation environment with consideration to the optimization objectives. Self-adaptation is seen as a promising method to manage such objectives in an efficient manner. In this paper, a QoS framework embedded in a SAS is proposed with respect to the EC environment in terms of workload fluctuation and limited resources. Its design also evaluated using a comprehensive simulation-based investigation that considers the most suitable scheduling algorithm, resource threshold, and resource monitoring interval. The simulation results show that the considered parameters can significantly improve the targeted objectives, which can be up to ~35% and more than 50% in acceptance rate and processing time, respectively. Such improvement is related to understanding the relationship among these parameters and the adopted workload.KeywordsEdge computingInternet of ThingsQuality of ServiceSelf-adaptive systemElasticityProactiveReactiveHybridAutonomic computing

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call