The Internet of Things (IoT) connects massive smart devices to collect big data and carry out the monitoring and control of numerous things in cyber-physical systems (CPS). By leveraging machine learning (ML) and deep learning (DL) techniques to analyze the collected data, physical systems can be monitored and controlled effectively. Along with the development of IoT and data analysis technologies, a number of CPS (smart grid, smart transportation, smart manufacturing, smart cities, etc.) adopt IoT and data analysis technologies to improve their performance and operations. Nonetheless, directly manipulating or updating the real system has inherent risks. Thus, creating a digital clone of a real physical system, denoted as a Digital Twin (DT), is a viable strategy. Generally speaking, a DT is a data-driven software and hardware emulation platform, which is a cyber replica of physical systems. Meanwhile, a DT describes a specific physical system and tends to achieve the functions and use cases of physical systems. Since DT is a complex digital system, finding a way to effectively represent a variety of things in timely and efficient manner poses numerous challenges to the networking, computing, and data analytics for IoT. Furthermore, the design of a DT for IoT systems must consider numerous exceptional requirements (e.g., latency, reliability, safety, scalability, security, and privacy). To address such challenges, the thoughtful design of DTs offers opportunities for novel and interdisciplinary research efforts. To address the aforementioned problems and issues, in this paper, we first review the architectures of DTs, data representation, and communication protocols. We then review existing efforts on applying DT into IoT data-driven smart systems, including the smart grid, smart transportation, smart manufacturing, and smart cities. Further, we summarize the existing challenges from CPS, data science, optimization, and security and privacy perspectives. Finally, we outline possible future research directions from the perspectives of performance, new DT-driven services, model and learning, and security and privacy.

Irrigation refers to supplying water to soil through pipes, pumps, and spraying systems to ensure even distribution across the field. In traditional farming or gardening, the setup and usage of an agricultural irrigation system solely rely on the personal experience of farmers. The Food and Agriculture Organization of the United Nations (UN) has projected that by 2030, developing countries will expand their irrigated areas by 34%, while water consumption will only be up 14%. This discrepancy highlights the importance of accurately monitoring water flow and volume rather than people’s rough estimations. The smart irrigation systems, a key subsystem of smart agriculture known as the cyber–physical system (CPS) in the agriculture domain, automate the administration of water flow, volume, and timing via using cutting-edge technologies, especially the Internet of Things (IoT) technology, to solve the challenges. This study explores a comprehensive three-dimensional problem space to thoroughly analyze the IoT’s applications in irrigation systems. Our framework encompasses several critical domains in smart irrigation systems. These domains include soil science, sensor technology, communication protocols, data analysis techniques, and the practical implementations of automated irrigation systems, such as remote monitoring, autonomous operation, and intelligent decision-making processes. Finally, we discuss a few challenges and outline future research directions in this promising field.

Machine learning, as a viable way of conducting data analytics, has been successfully applied to a number of areas. Nonetheless, the lack of sufficient data is one critical issue for applying machine learning in Industrial Internet of Things (IIoT) systems. Insufficient data raises could negatively affect the accuracy of machine learning models. To tackle this issue, we design a framework to systematically investigate the impacts of insufficient data on model training. This framework employs the Generative Adversarial Network (GAN) and continuous learning to generate and engage new data in model training, enabling us to study the security risks of introducing new data in the model training process and develop countermeasures to mitigate these risks. To validate the efficacy of our framework, we consider a representative IIoT scenario, in which a variety of industrial components need to be recognized by Convolutional Neural Networks (CNNs), and design and implement three evaluation scenarios that are based on a real-world IIoT dataset. Our experimental results confirm that insufficient data can have a significant impact on the model accuracy, but that new data generated by GAN and continuous learning can greatly improve the model accuracy. Our experimental results also show that the data poisoning threat posed by the GAN can significantly reduce the model accuracy. However, our proposed defensive mechanism is capable of securing the model learning process. We conclude the paper by discussing some emerging issues that need to be addressed in future work.

The Internet of Things (IoT) has created a novel ecosystem for sensing and actuation throughout our world, enabling intelligently controlled autonomous systems to conserve energy, water crops, manage factories, and provide situation awareness on an unprecedented scale. As IoT progresses, the interest in IoT search engines, that is, search engines to find IoT devices and retrieve IoT data, has grown. While basic examples of IoT search engines exist, considerable challenges prevent the full realization of an efficient and intelligent IoT search engine that provides universal data service, scalable data communication and retrieval, and efficient querying of massively distributed heterogeneous devices and data. In this article, we first propose a generic framework for the IoT search engine, and then present a naming service for the IoT system, an essential component for an effective IoT search engine. We also outline some research challenges and possible solutions for building efficiency and intelligence in the IoT search engine. Further, we present a case study and seek to address a particular aspect of the query process for IoT search, namely efficient and timely query processing. Given the now obvious advances in machine learning, the potential for deep learning-based prediction to improve resource use, and thus query retrieval, is clear. In detail, we utilize Long-Short-Term Memory (LSTM) neural network architecture to predict aggregated query volumes to be preemptively applied and stored for immediate response. Combining several realistic IoT datasets, we explore the efficacy of simultaneously predicting multiple targets for predictive query retrieval.

Cyber-Physical Systems (CPS) are new systems designed to support and synthesize sensing, communication, and computing components that interact with physical objects so that the system can sense, monitor, control, and respond to changes occurring in their operating environments. With developing Internet of Things (IoT), edge/cloud computing, and Artificial Intelligence (AI), another new paradigm - Digital Twin (DT), as an enabler for realizing the Metaverse of CPS has emerged recently. The DT provides a virtual replica of the physical world, allowing for real-time monitoring, control, and analysis of safety-critical systems like the CPS. Even though many CPS-related problems can be addressed using DT concepts, it is critical to define DT’s integration clearly to leverage its features to the best possible extent. This paper introduces a new layer called the data layer in the CPS layer architecture to support different DT functionalities. Like the layer and abstract design paradigm of modern operation systems and computer networks, the data layer serves as an abstraction layer, providing immense flexibility and interchangeability of various data sources, supporting applications, and adapting to other components and environments. This also accelerates the growth of smart-world systems and their integration in different application domains (smart grid, smart transportation, smart manufacturing, smart cities, smart healthcare, etc.). To this end, this paper presents a new data layer structure to support CPS applications and the integration of multiple CPS. We propose a hierarchical architecture to synthesize DT techniques as an independent layer in our architecture, deeply integrated into existing CPS. We discuss key issues: leveraging the data layer to support applications in various CPS, incorporating the data layer and physical layer, and building a data layer using distributed computing, naming services, etc. Finally, the paper outlines future research directions based on the presented new data layer architecture for CPS.

The Internet of Things (IoT) constitutes a vast network comprising various components such as physical devices, vehicles, buildings, and other items equipped with sensors, actuators, and software. These components are interconnected, facilitating the collection and exchange of copious data across networked communications. IoT empowers extensive monitoring and control over a myriad of objects, enabling them to gather and disseminate data that bolster applications, thereby enhancing the system’s capacity for informed decision making, environmental surveillance, and autonomous inter-object interaction, all without the need for direct human involvement. These systems have achieved seamless connectivity requirements using the next-generation wireless network infrastructures (5G, 6G, etc.), while their diverse reliability and quality of service (QoS) requirements across various domains require more efficient solutions. Open RAN (O-RAN), i.e., open radio open access network (RAN), promotes flexibility and intelligence in the next-generation RAN. This article reviews the applications of O-RAN in supporting the next-generation smart world IoT systems by conducting a thorough survey. We propose a generic problem space, which consists of (i) IoT Systems: transportation, industry, healthcare, and energy; (ii) targets: reliable communication, real-time analytics, fault tolerance, interoperability, and integration; and (iii) artificial intelligence and machine learning (AI/ML): reinforcement learning (RL), deep neural networks (DNNs), etc. Furthermore, we outline future research directions concerning robust and scalable solutions, interoperability and standardization, privacy, and security. We present a taxonomy to unveil the security threats to emerge from the O-RAN-assisted IoT systems and the feasible directions to move this research forward.