Technologies to support the Internet of Things are becoming more important as the need to better understand our environments and make them smart increases. As a result it is predicted that intelligent devices and networks, such as WSNs, will not be isolated, but connected and integrated, composing computer networks. So far, the IP-based Internet is the largest network in the world; therefore, there are great strides to connect WSNs with the Internet. To this end, the IETF has developed a suite of protocols and open standards for accessing applications and services for wireless resource constrained networks. However, many open challenges remain, mostly due to the complex deployment characteristics of such systems and the stringent requirements imposed by various services wishing to make use of such complex systems. Thus, it becomes critically important to study how the current approaches to standardization in this area can be improved, and at the same time better understand the opportunities for the research community to contribute to the IoT field. To this end, this article presents an overview of current standards and research activities in both industry and academia.

Reliable real-time sensing plays a vital role in ensuring the reliability and safety of industrial cyber-physical systems (CPSs) such as wireless sensor and actuator networks. For many reasons, such as harsh industrial environments, fault-prone sensors, or malicious attacks, sensor readings may be abnormal or faulty. This could lead to serious system performance degradation or even catastrophic failure. Current anomaly detection approaches are either centralized and complicated or restricted due to strict assumptions, which are not suitable for practical large-scale networked industrial sensing systems (NISSs), where sensing devices are connected via digital communications, such as wireless sensor networks or smart grid systems. In this paper, we introduce a fully distributed general anomaly detection (GAD) scheme, which uses graph theory and exploits spatiotemporal correlations of physical processes to carry out real-time anomaly detection for general large-scale NISSs. We formally prove the scalability of our GAD approach and evaluate the performance of GAD for two industrial applications: building structure monitoring and smart grids. Extensive trace-driven simulations validate our theoretical analysis and demonstrate that our approach can significantly outperform state-of-the-art approaches in terms of detection accuracy and efficiency.

Federated learning (FL) is a promising paradigm that enables collaboratively learning a shared model across massive clients while keeping the training data locally. However, for many existing FL systems, clients need to frequently exchange model parameters of large data size with the remote cloud server directly via wide-area networks (WAN), leading to significant communication overhead and long transmission time. To mitigate the communication bottleneck, we resort to the hierarchical federated learning paradigm of HiFL, which reaps the benefits of mobile edge computing and combines synchronous client-edge model aggregation and asynchronous edge-cloud model aggregation together to greatly reduce the traffic volumes of WAN transmissions. Specifically, we first analyze the convergence bound of HiFL theoretically and identify the key controllable factors for model performance improvement. We then advocate an enhanced design of HiFlash by innovatively integrating deep reinforcement learning based adaptive staleness control and heterogeneity-aware client-edge association strategy to boost the system efficiency and mitigate the staleness effect without compromising model accuracy. Extensive experiments corroborate the superior performance of HiFlash in model accuracy, communication reduction, and system efficiency.

Smart grids are essentially electric grids that use information and communication technology to provide reliable, efficient electricity transmission and distribution. Security and trust are of paramount importance. Among various emerging security issues, FDI attacks are one of the most substantial ones, which can significantly increase the cost of the energy distribution process. However, most current research focuses on countermeasures to FDIs for traditional power grids rather smart grid infrastructures. We propose an efficient and real-time scheme to detect FDI attacks in smart grids by exploiting spatial-temporal correlations between grid components. Through realistic simulations based on the US smart grid, we demonstrate that the proposed scheme provides an accurate and reliable solution.

It is predicted that billions of intelligent devices and networks, such as wireless sensor networks (WSNs), will not be isolated but connected and integrated with computer networks in future Internet of Things (IoT). In order to well maintain those sensor devices, it is often necessary to evolve devices to function correctly by allowing device management (DM) entities to remotely monitor and control devices without consuming significant resources. In this paper, we propose a lightweight RESTful Web service (WS) approach to enable device management of wireless sensor devices. Specifically, motivated by the recent development of IPv6-based open standards for accessing wireless resource-constrained networks, we consider to implement IPv6 over low-power wireless personal area network (6LoWPAN)/routing protocol for low power and lossy network (RPL)/constrained application protocol (CoAP) protocols on sensor devices and propose a CoAP-based DM solution to allow easy access and management of IPv6 sensor devices. By developing a prototype cloud system, we successfully demonstrate the proposed solution in efficient and effective management of wireless sensor devices.

Federated learning (FL) is an emerging privacy-preserving paradigm that enables multiple participants collaboratively to train a global model without uploading raw data. Considering heterogeneous computing and communication capabilities of different participants, asynchronous FL can avoid the stragglers effect in synchronous FL and adapts to scenarios with vast participants. Both staleness and non-IID data in asynchronous FL would reduce the model utility. However, there exists an inherent contradiction between the solutions to the two problems. That is, mitigating the staleness requires to select less but consistent gradients while coping with non-IID data demands more comprehensive gradients. To address the dilemma, this paper proposes a two-stage weighted $K$ asynchronous FL with adaptive learning rate (WKAFL). By selecting consistent gradients and adjusting learning rate adaptively, WKAFL utilizes stale gradients and mitigates the impact of non-IID data, which can achieve multifaceted enhancement in training speed, prediction accuracy and training stability. We also present the convergence analysis for WKAFL under the assumption of unbounded staleness to understand the impact of staleness and non-IID data. Experiments implemented on both benchmark and synthetic FL datasets show that WKAFL has better overall performance compared to existing algorithms.