Towards Mobility Support in Edge Clouds

Mobile-access edge clouds provide distributed compute capacities for low-latency applications. G technology will pave the way for such mobile deployment scenarios. In this paper, we propose an edge cloud infrastructure that supports low-latency video analysis connected with bandwidth reduction for a moving group of persons. As example, we consider a mobile body camera scenario that monitors the situation in a certain area and transmits it to an operations center. Our discussion focuses on three aspects: mobility support, low-latency video processing, and bandwidth reduction. For this, we propose a mobile edge cloud infrastructure with a central cloud. In order to optimize video processing we optimize the edge cloud device assignment of the cameras depending on their movement by reassigning it to another cloud device. This requires live migration of ongoing video analysis between edge devices. Finally we discuss the use of a mobile central cloud.