Towards a practical framework for code offloading in the Internet of Things

Abstract

Mobile code offloading is a popular technique for enhancing the apparent capabilities of resource constrained devices. It is of particular interest for developers trying to push ever more complex algorithms into embedded devices that belong to the Internet of Things (IoT). Although there is much research into this area in the realm of smartphones and tablets, the same cannot be said for IoT devices, for which very few code offloading frameworks exist. This paper presents MobiCOP-IoT, an extension of the MobiCOP mobile code offloading solution for the smartphone and tablet ecosystem, that supports embedded devices and Google’s newest IoT initiative, Android Things. MobiCOP-IoT allows developers to deploy surrogates on both distant clouds and proximate nodes located on the edge. As such, MobiCOP-IoT enabled applications can take advantage of the benefits of mobile edge computing to further enhance their capabilities. We tested MobiCOP-IoT in a variety of scenarios and we found improvements of up to 9 times in terms of performance and energy for centralized cloud deployments, and up to 16 times in the case of edge scenarios. Moreover, we show the platform is capable of automatic horizontal scaling, which allows it to adapt to varying network traffic conditions; and multitenancy, wherein a single server instance is capable of attending multiple clients’ requests with minimal loss in performance.