The number of connected Internet of Things (IoT) devices grows at an increasing rate, revealing shortcomings of current IoT networks for cyber-physical infrastructure systems to cope with ensuing device management and security issues. Data-based methods rooted in deep learning (DL) are recently considered to cope with such problems, albeit challenged by deployment of deep learning models at resource-constrained IoT devices. Motivated by the upcoming surge of 5G IoT connectivity in industrial environments, in this paper, we propose to integrate a DL-based anomaly detection (AD) as a service into the 3GPP mobile cellular IoT architecture. The proposed architecture embeds deep autoencoder based anomaly detection modules both at the IoT devices (ADM-EDGE) and in the mobile core network (ADM-FOG), thereby balancing between the system responsiveness and accuracy. We design, integrate, demonstrate and evaluate a testbed that implements the above service in a real-world deployment integrated within the 3GPP Narrow-Band IoT (NB-IoT) mobile operator network.

中文翻译：

---

蜂窝物联网深度学习异常检测及其在智能物流中的应用

连接的物联网（IoT）设备的数量正以越来越快的速度增长，这揭示了当前物联网网络在网络物理基础设施系统中的缺点，以应对随之而来的设备管理和安全问题。尽管在资源受限的物联网设备上部署了深度学习模型，但基于深度学习（DL）的基于数据的方法最近被认为可以解决此类问题。出于工业环境中即将出现的5G IoT连接激增的动机，我们建议将基于DL的异常检测（AD）作为服务集成到3GPP移动蜂窝IoT体系结构中。拟议的架构在IoT设备（ADM-EDGE）和移动核心网（ADM-FOG）中都嵌入了基于深度自动编码器的异常检测模块，从而在系统响应性和准确性之间取得平衡。我们设计，集成，演示和评估在3GPP窄带物联网（NB-IoT）移动运营商网络中集成的实际部署中实现上述服务的测试平台。