An increasing number of unhardened commercial-off-the-shelf embedded devices are deployed under harsh operating conditions and in highly-dependable systems. Due to the mechanisms of hardware degradation that affect these devices, ageing detection and monitoring are crucial to prevent critical failures. In this paper, we empirically study the propagation delay of 298 naturally-aged FPGA devices that are deployed in the European XFEL particle accelerator. Based on in-field measurements, we find that operational devices show significantly slower switching frequencies than unused chips, and that increased gamma and neutron radiation doses correlate with increased hardware degradation. Furthermore, we demonstrate the feasibility of developing machine learning models that estimate the switching frequencies of the devices based on historical and environmental data.

Ageing detection and failure prediction are essential in many Internet of Things (IoT) deployments, which operate huge quantities of embedded devices unattended in the field for years. In this paper, we present a large-scale empirical analysis of natural SRAM wear-out using 154 boards from a generalpurpose testbed. Starting from SRAM initialization bias, which each node can easily collect at startup, we apply various metrics for feature extraction and experiment with common machine learning methods to predict the age of operation for this node. Our findings indicate that even though ageing impacts are subtle, our indicators can well estimate usage times with an R2score of 0.77 and a mean error of 24% using regressors, and with an Fl score above 0.6 for classifiers applying a six-months resolution.

Constrained devices on the Internet of Things (IoT) continuously produce and consume data. LwM2M manages millions of these devices in a server-centric architecture, which challenges edge net-works with expensive uplinks and time-sensitive use cases. In this paper, we contribute two LwM2M extensions to enable client-to-client (C2C) communication: (i) an authorization mechanism for clients, and (ii) an extended management interface to allow secure C2C access to resources. We analyse the security properties of the proposed extensions and show that they are compliant with LwM2M security requirements. Our performance evaluation on off-the-shelf IoT hardware reveals that C2C communication out-performs server-centric deployments. First, LwM2M deployments with edge C2C communication yield a ≈ 90% faster notification delivery and ≈ 8 times higher throughput compared to common server-centric scenarios, while keeping a small memory overhead of ≈ 8%. Second, in server-centric communication, the delivery rate degrades when resource update intervals drop below 100 ms.