MMEliot: A Model for Internet of Things Exploring Cloud Computing Elasticity

Abstract

The adoption of Internet of Things (IoT) technologies has been growing in the last few years in a significant way. For this reason, there is a increasing necessity of systems capable of processing high amount of data with a certain performance level. A promissing solution to address this problem is the use of Cloud Computing technologies. In this context, this paper proposes MMEliot, a cloud computing elasticity model. MMEliot model combines CPU load data and response time from IoT requests to overpass the problem related to lack of reactivity.  Our experiments show that MMEliot is able to anticipate allocation and release of resources from the cloud, generating better performance and less number of lost requests.