A Novel Edge-Cloud Interworking Framework in the Video Analytics of the Internet of Things

Abstract

This letter proposes a novel edge-cloud interworking framework in the video analytics of the Internet of Things (IoT) that consists of cost-effective job load balancing and scheduling schemes for computation-intensive video analytics applications. The proposed framework aims to minimize the cost of cloud resource usage while guaranteeing deadlines when conducting concurrent operations. A formulation of a two-stage mixed-integer problem and its heuristic greedy algorithms is presented, which captures all intertwined goals. From the numerical analysis, we reveal that the proposed framework outperforms the existing schemes in terms of monetary cost and service latency with a practical complexity bound.