With the numerous IoT devices, the cloud-centric data processing fails to meet the requirement of all IoT applications. The limited computation and communication capacity of the cloud necessitate the Edge Computing, i.e., starting the IoT data processing at the edge and transforming the connected devices to intelligent devices. Machine learning, the key means for information inference, should extend to the cloud-to-things continuum too. This article reviews the role of machine learning in IoT from the cloud down to embedded devices. Different usages of machine learning for application data processing and management tasks are studied. The state-of-the-art usages of machine learning in IoT are categorized according to their application domain, input data type, exploited machine learning techniques, and where they belong in the cloud-to-things continuum. The challenges and research trends toward efficient machine learning on the IoT edge are discussed. Moreover, the publications on the ‘machine learning in IoT’ are retrieved and analyzed systematically using machine learning classification techniques. Then, the growing topics and application domains are identified.

With the widespread use of IoT applications and the increasing trend in the number of connected smart devices, the concept of routing has become very challenging. In this regard, the IPv6 Routing Protocol for Low-power and Lossy Networks (PRL) was standardized to be adopted in IoT networks. Nevertheless, while mobile IoT domains have gained significant popularity in recent years, since RPL was fundamentally designed for stationary IoT applications, it could not well adjust with the dynamic fluctuations in mobile applications. While there have been a number of studies on tuning RPL for mobile IoT applications, but still there is a high demand for more efforts to reach a standard version of this protocol for such applications. Accordingly, in this survey, we try to conduct a precise and comprehensive experimental study on the impact of various mobility models on the performance of a mobility-aware RPL to help this process. In this regard, a complete and scrutinized survey of the mobility models has been presented to be able to fairly justify and compare the outcome results. A significant set of evaluations has been conducted via precise IoT simulation tools to monitor and compare the performance of the network and its IoT devices in mobile RPL-based IoT applications under the presence of different mobility models from different perspectives including power consumption, reliability, latency, and control packet overhead. This will pave the way for researchers in both academia and industry to be able to compare the impact of various mobility models on the functionality of RPL, and consequently to design and implement application-specific and even a standard version of this protocol, which is capable of being employed in mobile IoT applications.

The massive number of Internet of Things (IoT) devices generates a hard-to-manage volume of data. Cloud/centric processing approaches for IoT data suffer from high and unpredictable network latency, which causes poor experience in real-time IoT applications such as healthcare. To address this issue, in edge computing, the data inference starts from the data source (i.e. the IoT devices). However, the constrained computational capabilities of the IoT device and the power-hungry data transmission demand a trade-off between onboard processing and computation offloading. Hence, the IoT information inference requires efficient and lightweight techniques that are tailored for this trade-off and respect the constrained resources on IoT devices such as wearables. This article presents a hierarchical classification approach that decomposes the problem into three classifiers in two hierarchy layers: In the first layer, a lightweight classifier executes directly on the IoT device and decides whether to offload the computation to the gateway or to perform it onboard. The second layer comprises a lightweight classifier on the IoT device (can only distinguish a subset of classes) and a complex classifier on the gateway (to distinguish the remaining classes). The experimental results (using a real-world dataset for human activity recognition and implemented on a wearable IoT device) show higher accuracy (92% on average) than a non-hierarchical classifier (87% on average). The execution time and power measurements on the IoT device show 3× energy/saving for the classification.

Internet of Things (IoT) has made small objects and things to be networked and interconnected, and even connected to the Internet in order to offer advanced control and monitoring services. Smart embedded devices along with intelligent decision-making ability will increase the efficiency of services in different domains including smart grid. Similar to other IoT domain, smart grid consist of a massive number of sensors and data sources which continuously collect high-resolution data. Managing the large volume of data has been identified as one of the major challenges in IoT. To address this issue, Edge Computing envisions to process the data at the edge of the IoT network close to the embedded devices where the data is collected. This chapter aims to investigate the edge computing solutions for the smart grid. An edge computing model for the smart grid information processing, with a focus on smart home, is presented in this chapter. The advantages of this model in terms of self-supporting and privacy are discussed. Moreover, we present a use-case for smart home automation where the operating mode of home appliances are determined dynamically to respect the limited power budget of home while maximizing the user’s satisfaction and utility.

The Internet-of-Things (IoT) envisions an infrastructure of ubiquitous networked smart devices offering advanced monitoring and control services. The current art in IoT architectures utilizes gateways to enable application-specific connectivity to IoT devices. In typical configurations, IoT gateways are shared among several IoT edge devices. Given the limited available bandwidth and processing capabilities of an IoT gateway, the service quality (SQ) of connected IoT edge devices must be adjusted over time not only to fulfill the needs of individual IoT device users but also to tolerate the SQ needs of the other IoT edge devices sharing the same gateway. However, having multiple gateways introduces an interdependent problem, the binding, i.e., which IoT device shall connect to which gateway. In this article, we jointly address the binding and allocation problems of IoT edge devices in a multigateway system under the constraints of available bandwidth, processing power, and battery lifetime. We propose a distributed trade-based mechanism in which after an initial setup, gateways negotiate and trade the IoT edge devices to increase the overall SQ. We evaluate the efficiency of the proposed approach with a case study and through extensive experimentation over different IoT system configurations regarding the number and type of the employed IoT edge devices. Experiments show that our solution improves the overall SQ by up to 56% compared to an unsupervised system. Our solution also achieves up to 24.6% improvement on overall SQ compared to the state-of-the-art SQ management scheme, while they both meet the battery lifetime constraints of the IoT devices.