Cost efficient edge intelligence framework using docker containers

The emergence of edge computing has its basis in the integration of the Internet of Things (IoT) with the Cloud computing. In order to make it possible, management technologies of data centers have to be combined with significantly more limited devices. The Docker technology, which provides a very lightweight and effective virtualization solution, can be utilized to manage, deploy and distribute edge/cloud applications onto clusters (that, in our case, will be composed by lightweight and small board devices-such as Raspberry Pi). We apply this on the human activity identification scenario. These types of edge devices can be very useful especially in cases when the combination of low costs and robustness is desirable due to various reasons and conditions. In our work, we propose and analyze a framework based on the distributed edge/cloud paradigm. It is able to provide an advantageous combination of various benefits and lower costs of data processing performed at the edge instead of central servers. Support Vector Machine (SVM) has been utilized for recognizing human activity via the proposed framework. The results of the use case are presented in detail in this paper along with the simulated experiment.