SDN-LB: A novel server workload balancing algorithm for IoT video analytics

Abstract

The wide deployment of Internet of Things (IoT) cameras combined with powerful deep learning models for object detection and recognition will usher in a new generation of IoT video analytics applications. However, IoT video analytics require intensive computing resources, which often are not present in IoT devices and are provided by edge and/or cloud servers. This paper proposes a hierarchical edge/cloud-based solution for processing IoT video streaming flows. We devised a queuing model that considers the characteristics of the IoT video flows (i.e., frame rate and frame resolution), the network backbone (i.e., communication latency of the routing path from IoT devices to cloud/edge servers), and the characteristics of the servers (i.e., processing resources capabilities) to estimate the expected end-to-end latency experienced by the frames when processed at the edge and cloud servers. We then propose a software-defined networking (SDN)-based architecture to balance the workload (i.e., video frames to be processed) at the edge and cloud servers aimed at reducing the average latency when processing video frames. We design the SDN-LB algorithm to periodically collect data from programmable switches, determine the expected latency in each server, and re-assign IoT video streaming flows to edge and cloud servers aimed at reducing the end-to-end latency for the processing of video streaming. Extensive numerical evaluation results show that the proposed balancing solution can effectively balance the IoT video streaming flows across the edge and cloud servers, and reduce the average latency incurred in the processing of IoT video frames.