Deep learning is a promising approach for extracting accurate information from raw sensor data from IoT devices deployed in complex environments Because of its multilayer structure, deep learning is also appropriate for the edge computing environment Therefore, in this article, we first introduce deep learning for IoTs into the edge computing environment Since existing edge nodes have limited processing capability, we also design a novel offloading strategy to optimize the performance of IoT deep learning applications with edge computing In the performance evaluation, we test the performance of executing multiple deep learning tasks in an edge computing environment with our strategy The evaluation results show that our method outperforms other optimization solutions on deep learning for IoT

/pdf/learning-iot-in-edge-deep-learning-for-the-internet-of-18jz5dyghh.pdf

Learning IoT in Edge: Deep Learning for the Internet of Things with Edge Computing

The impact of the Internet of Things (IoT) on the advancement of the healthcare industry is immense. The ushering of the Medicine 4.0 has resulted in an increased effort to develop platforms, both at the hardware level as well as the underlying software level. This vision has led to the development of Healthcare IoT (H-IoT) systems. The basic enabling technologies include the communication systems between the sensing nodes and the processors; and the processing algorithms for generating an output from the data collected by the sensors. However, at present, these enabling technologies are also supported by several new technologies. The use of Artificial Intelligence (AI) has transformed the H-IoT systems at almost every level. The fog/edge paradigm is bringing the computing power close to the deployed network and hence mitigating many challenges in the process. While the big data allows handling an enormous amount of data. Additionally, the Software Defined Networks (SDNs) bring flexibility to the system while the blockchains are finding the most novel use cases in H-IoT systems. The Internet of Nano Things (IoNT) and Tactile Internet (TI) are driving the innovation in the H-IoT applications. This paper delves into the ways these technologies are transforming the H-IoT systems and also identifies the future course for improving the Quality of Service (QoS) using these new technologies.

The Future of Healthcare Internet of Things: A Survey of Emerging Technologies

The upcoming fifth generation (5G) of wireless networks is expected to lay a foundation of intelligent networks with the provision of some isolated artificial intelligence (AI) operations. However, fully intelligent network orchestration and management for providing innovative services will only be realized in Beyond 5G (B5G) networks. To this end, we envisage that the sixth generation (6G) of wireless networks will be driven by on-demand self-reconfiguration to ensure a many-fold increase in the network performance and service types. The increasingly stringent performance requirements of emerging networks may finally trigger the deployment of some interesting new technologies, such as large intelligent surfaces, electromagnetic–orbital angular momentum, visible light communications, and cell-free communications, to name a few. Our vision for 6G is a massively connected complex network capable of rapidly responding to the users’ service calls through real-time learning of the network state as described by the network edge (e.g., base-station locations and cache contents), air interface (e.g., radio spectrum and propagation channel), and the user-side (e.g., battery-life and locations). The multi-state, multi-dimensional nature of the network state, requiring the real-time knowledge, can be viewed as a quantum uncertainty problem. In this regard, the emerging paradigms of machine learning (ML), quantum computing (QC), and quantum ML (QML) and their synergies with communication networks can be considered as core 6G enablers. Considering these potentials, starting with the 5G target services and enabling technologies, we provide a comprehensive review of the related state of the art in the domains of ML (including deep learning), QC, and QML and identify their potential benefits, issues, and use cases for their applications in the B5G networks. Subsequently, we propose a novel QC-assisted and QML-based framework for 6G communication networks while articulating its challenges and potential enabling technologies at the network infrastructure, network edge, air interface, and user end. Finally, some promising future research directions for the quantum- and QML-assisted B5G networks are identified and discussed.

/pdf/quantum-machine-learning-for-6g-communication-networks-state-1zr3shv6z6.pdf

Quantum Machine Learning for 6G Communication Networks: State-of-the-Art and Vision for the Future

By moving service provisioning from the cloud to the edge, edge computing becomes a promising solution in the era of IoT to meet the delay requirements of IoT applications, enhance the scalability and energy efficiency of lightweight IoT devices, provide contextual information processing, and mitigate the traffic burdens of the backbone network. However, as an emerging field of study, edge computing is still in its infancy and faces many challenges in its implementation and standardization. In this article, we study an implementation of edge computing, which exploits transparent computing to build scalable IoT platforms. Specifically, we first propose a transparent computing based IoT architecture, and clearly identify its advantages and associated challenges. Then, we present a case study to clearly show how to build scalable lightweight wearables with the proposed architecture. Some future directions are finally pointed out to foster continued research efforts.

Serving at the Edge: A Scalable IoT Architecture Based on Transparent Computing

The ever-increasing number of resource-constrained machine-type communication (MTC) devices is leading to the critical challenge of fulfilling diverse communication requirements in dynamic and ultra-dense wireless environments. Among different application scenarios that the upcoming 5G and beyond cellular networks are expected to support, such as enhanced mobile broadband (eMBB), massive machine type communications (mMTCs), and ultra-reliable and low latency communications (URLLCs), the mMTC brings the unique technical challenge of supporting a huge number of MTC devices in cellular networks, which is the main focus of this paper. The related challenges include quality of service (QoS) provisioning, handling highly dynamic and sporadic MTC traffic, huge signalling overhead, and radio access network (RAN) congestion. In this regard, this paper aims to identify and analyze the involved technical issues, to review recent advances, to highlight potential solutions and to propose new research directions. First, starting with an overview of mMTC features and QoS provisioning issues, we present the key enablers for mMTC in cellular networks. Along with the highlights on the inefficiency of the legacy random access (RA) procedure in the mMTC scenario, we then present the key features and channel access mechanisms in the emerging cellular IoT standards, namely, LTE-M and narrowband IoT (NB-IoT). Subsequently, we present a framework for the performance analysis of transmission scheduling with the QoS support along with the issues involved in short data packet transmission. Next, we provide a detailed overview of the existing and emerging solutions toward addressing RAN congestion problem, and then identify potential advantages, challenges, and use cases for the applications of emerging machine learning (ML) techniques in ultra-dense cellular networks. Out of several ML techniques, we focus on the application of low-complexity $Q$ -learning approach in the mMTC scenario along with the recent advances toward enhancing its learning performance and convergence. Finally, we discuss some open research challenges and promising future research directions.

/pdf/toward-massive-machine-type-communications-in-ultra-dense-4vhhsazx8i.pdf

Toward Massive Machine Type Communications in Ultra-Dense Cellular IoT Networks: Current Issues and Machine Learning-Assisted Solutions

With the widespread adoption of the Internet of Things (IoT), the number of connected devices is growing at an exponential rate, which is contributing to ever-increasing, massive data volumes. Real-time analytics on the massive IoT data, referred to as the “real-time IoT analytics” in this paper, is becoming the mainstream with an aim to provide an immediate or non-immediate actionable insights and business intelligence. However, the analytics network of the existing IoT systems does not adequately consider the requirements of the real-time IoT analytics. In fact, most researchers overlooked an appropriate design of the IoT analytics network while focusing much on the sensing and delivery networks of the IoT system. Since much of the IoT analytics network has often been taken as granted, the survey, in this paper, we aim to review the state-of-the-art of the analytics network methodologies, which are suitable for real-time IoT analytics. In this vein, we first describe the basics of the real-time IoT analytics, use cases, and software platforms, and then explain the shortcomings of the network methodologies to support them. To address those shortcomings, we then discuss the relevant network methodologies which may support the real-time IoT analytics. Also, we present a number of prospective research problems and future research directions focusing on the network methodologies for the real-time IoT analytics.

A Survey on Network Methodologies for Real-Time Analytics of Massive IoT Data and Open Research Issues

The latest evolution of cellular technologies, i.e., 5G including long term evolution-advanced (LTE-A) Pro and 5G new radio promises enhancement to mobile technologies for the Internet of Things (IoT). Despite 5G’s vision to cater to IoT, yet some of the aspects are still optimized for human-to-human (H2H) communication. More specifically, the existing group paging mechanism in LTE-A Pro has not yet clearly defined approaches to group, mobile IoT devices (MIDs) having diverse characteristics, such as discontinuous reception (DRX) and data transmission frequency (DTF) with various mobility patterns. Inappropriate grouping of MIDs may lead to increased energy consumption and degraded quality of service, especially in terms of packet arrival delay (PAD) and packet loss rate (PLR). Therefore, in this paper, we devise novel models to estimate PAD, PLR, and energy consumption for MIDs, specifically for the group paging mechanism. Based on the proposed models, we formulate an optimization problem with the objective to minimize energy consumption of MIDs, while providing required PAD and PLR. The nonlinear convex optimization problem addressed herein is solved using the Lagrangian approach, and the Karush–Kuhn–Tucker conditions have been applied to derive optimal characteristics for MIDs to join the group, namely, DRX and DTF. The extensive numerical results presented verify the effectiveness of the proposed method, and the mathematical models demonstrate the superiority of our proposed approach over random grouping approach concerning significant energy consumption of MIDs.

Energy-Efficient Group Paging Mechanism for QoS Constrained Mobile IoT Devices Over LTE-A Pro Networks Under 5G

Despite unprecedented advancements, wireless local area network (WLAN) technologies for the Internet of Things (IoT), such as IEEE 802.11ah (i.e., WiFi-HaLow), are prone to serious security threats, owing to their constrained computational and memory resources, which limit the use of heavyweight intrusion protection and security protocols. To address this problem, security administrators (sec-admins) must perform regular and comprehensive vulnerability assessments of IoT devices. An Internet-wide port scan (IWPS) is the initial step. However, the medium access control mechanism of IEEE 802.11ah, designed specifically for heterogeneous IoT traffic and low-power operations, can degrade network performance in the case of traditional port-scan traffic. Moreover, Internet-security (IPSec) protocol support is mandatory for IPv6-enabled IoT devices to ensure data confidentiality, integrity, and availability. Although the objective of a port scan is to improve IoT security, the resultant network performance can adversely affect IPSec services. Therefore, in this study, we optimize the IWPS to maximize the IoT security over IEEE 802.11ah WLAN. To this end, we propose novel mathematical models to evaluate IoT security based on port-scan network performance and IPsec services, which derives an optimal scan rate for sec-admins. The effectiveness of the proposed framework is verified by comprehensive numerical analysis, which shows that our approach minimizes the risk to IoT devices while probing them at an optimal scan rate.

A Network-Aware Internet-Wide Scan for Security Maximization of IPv6-Enabled WLAN IoT Devices

The Internet of Things (IoT) has created acute network security concerns owing to their weak protocols and limited system resources. Vulnerable IoT devices increase the risk of compromising other devices connected to the network. Hence, vulnerability and risk assessments are necessary for IoT devices. Correspondingly, the Internet-wide port scan (IWPS) technique has garnered significant attention for its ability to discover and probe Internet-wide connected IoT devices. However, IWPS performance depends on the end wireless local area network (WLAN) state (e.g., congestion and signal-to-interference-plus-noise ratio). Scans oblivious to such dynamic WLAN factors can cause probe packet loss while increasing port-scan delays, which reduces the discovery rate, which misses the point of network security. Therefore, in this study, we propose a novel holistic approach to identifying WLAN environmental states based on round-trip time and probe-packet responses. To demonstrate the effectiveness of the proposed approach, we perform extensive experiments on real WLAN environments with various devices. The accuracy of the estimated states was validated at greater than 90% by analyzing the captured probe data at each WLAN.

A Smart Internet-Wide Port Scan Approach for Improving IoT Security Under Dynamic WLAN Environments

The evolution of cellular networks under Long Term Evolution (LTE) has paved the path for LTE-Advanced (LTE-A) Pro that proposes forward LTE enhancements for Machine Type Communications (MTC) and meets the stringent requirements for realization of the Internet-of-Things (IoT). This paper identifies possible improvements in LTE-A Pro's existing group paging scheme, which is more expedient for human-tohuman communications and inadequate for IoT applications. We propose a novel energy efficient group paging scheme by considering diverse IoT characteristics including Quality of Service considerations. Simulation results reveal that our proposed approach can significantly reduce energy consumption of IoT devices over existing group paging schemes.

Shikhar Verma

Papers

A Survey on Network Methodologies for Real-Time Analytics of Massive IoT Data and Open Research Issues

Energy-Efficient Group Paging Mechanism for QoS Constrained Mobile IoT Devices Over LTE-A Pro Networks Under 5G

A Network-Aware Internet-Wide Scan for Security Maximization of IPv6-Enabled WLAN IoT Devices

A Smart Internet-Wide Port Scan Approach for Improving IoT Security Under Dynamic WLAN Environments

Novel Group Paging Scheme for Improving Energy Efficiency of IoT Devices over LTE-A Pro Networks with QoS Considerations