IEEE Internet of Things Journal · 2020 · 190 citations · 39 references
ComputingCloud ComputingComputer ScienceEdge ComputingInternet Of ThingsMachine LearningDeep LearningEdge ArchitectureEdge-cloud ArchitectureEdge-cloud IntegrationFog ComputingIndustrial Internet Of ThingsEdge Computing NetworksEdge NodesIndustrial Control SystemsIndustrial Edge ComputingIndustrial Internet Of Things IntegrationIndustrial Internet Of Things MonitoringNetwork Congestion ManagementNetwork Congestion Modeling
Industrial Internet of Things connects ubiquitous sensing and actuating devices, and deep learning is often deployed in the cloud for big‑data modeling, but transmitting data to cloud servers causes network congestion and degrades IIoT performance. This work proposes an edge‑based deep learning framework that migrates the training and inference process from cloud servers to edge nodes, thereby reducing data transmission demands and alleviating network congestion. To accommodate the limited computational resources of edge nodes, the authors optimize the convolutional neural network architecture and evaluate the approach on a Google Cloud‑based testbed using a real‑world IIoT dataset. Experiments show that the edge‑based model cuts network traffic while preserving classification accuracy compared with several baseline schemes.
As a typical application of the Internet of Things (IoT), the Industrial Internet of Things (IIoT) connects all the related IoT sensing and actuating devices ubiquitously so that the monitoring and control of numerous industrial systems can be realized. Deep learning, as one viable way to carry out big data-driven modeling and analysis, could be integrated in IIoT systems to aid the automation and intelligence of IIoT systems. As deep learning requires large computation power, it is commonly deployed in cloud servers. Thus, the data collected by IoT devices must be transmitted to the cloud for training process, contributing to network congestion and affecting the IoT network performance as well as the supported applications. To address this issue, in this paper we leverage fog/edge computing paradigm and propose an edge computing-based deep learning model, which utilizes edge computing to migrate the deep learning process from cloud servers to edge nodes, reducing data transmission demands in the IIoT network and mitigating network congestion. Since edge nodes have limited computation ability compared to servers, we design a mechanism to optimize the deep learning model so that its requirements for computational power can be reduced. To evaluate our proposed solution, we design a testbed implemented in the Google cloud and deploy the proposed Convolutional Neural Network (CNN) model, utilizing a real-world IIoT dataset to evaluate our approach. Our experimental results confirm the effectiveness of our approach, which can not only reduce the network traffic overhead for IIoT, but also maintain the classification accuracy in comparison with several baseline schemes.
39
Edge Computing: Vision and Challenges
Weisong Shi, Jie Cao, Quan Zhang et al. · IEEE Internet of Things Journal · 2016 · 7.9K citations
Adversarial Discriminative Domain Adaptation
Eric Tzeng, Judy Hoffman, Kate Saenko et al. · 2017 · 5K citations
Software-Defined Networking: A Comprehensive Survey
Diego Kreutz, Fernando M. V. Ramos, Paulo Esteves Veríssimo et al. · Proceedings of the IEEE · 2014 · 4.9K citations · Full text
Efficient Processing of Deep Neural Networks: A Tutorial and Survey
Vivienne Sze, Yu‐Hsin Chen, Tien-Ju Yang et al. · Proceedings of the IEEE · 2017 · 4K citations
The Limitations of Deep Learning in Adversarial Settings
Nicolas Papernot, Patrick McDaniel, Somesh Jha et al. · 2016 · 3.9K citations