5G Edge Computing Experiments with Intelligent Resource Allocation for Multi-Application Video Analytics

The fifth-generation mobile network is characterized as the edge of wireless connectivity for all intelligent automation. Technically, the services' requirements for Quality of Service (QoS) have become more strict on latency and throughput. As a result, the concept of Mobile Edge Computing (MEC) has become promising. By placing servers close to the user-equipment (UE), the paradigm enables much lower data transmission time compared to the cloud-based scenario. With this advantage, MEC reaches the requirements of low-latency. Moreover, recognition and detection technology can be thus implemented in several live video analytics scenarios. However, due to the limited physical size on the edge server, resource allocation becomes a crucial issue. In this paper, we proposed a Resource Management method with Multiple Applications in Edge architecture (RMMAE) to intelligently reallocate computing tasks in the heterogeneous network. We design an algorithm to allocate computing resources to applications such as facial detection, object detection and pose estimation in our Edge testbed, and we prove impressive improvement and performance on our testbed with multiple applications.