Deploying edge computing nodes for large-scale IoT: A diversity aware approach

Abstract

The recent advances in microelectronics and communications have led to the development of large-scale IoT networks, where tremendous sensory data is generated and needs to be processed. To support real-time processing for large-scale IoT, deploying edge servers with storage and computational capability is a promising approach. In this paper, we carefully analyze the impacting factors and key challenges for edge node deployment. We then propose a novel three-phase deployment approach which considers both traffic diversity and the wireless diversity of IoT. The proposed work aims at providing real-time processing service for the IoT network and reducing the required number of edge nodes. We conducted extensive simulation experiments, the results show that compared to the existing works that overlooked the two kinds of diversities, the proposed work greatly reduces the number of edge nodes and improves the throughput between IoT and edge nodes.