IEEE International Conference on Communications
20-24 May 2019 // Shanghai, China
Empowering Intelligent Communications

Tutorials

Download Description of 20 May Tutorials PDF >>
Download Description of 24 My Tutorials PDF >>

Monday, 20 May 2019, 9:00 – 12:30

TUT-01: UAV Applications over Cellular Networks: Sensing, Communication, and Computation
TUT-02: Fog Computing: An Enabling Paradigm for Intelligent Services
TUT-03: Communication Network Design: Model-Based, Data-Driven, or Both?
TUT-04: MIMO Transmission with Finite Input Signals CANCELLED
TUT-05: Accessing from the Sky: UAV Communications for 5G and Beyond
TUT-06: Quantum Internet: Wiring the Weirdness
TUT-07: Cognitive Backscatter Network: A New Paradigm of Energy- and Spectrum-Efficient IoT Communications
TUT-08: 5G Tactile Internet with Human-in-the-Loop

Monday, 20 May 2019, 14:00 – 17:30

TUT-09: Deep Learning for Communications: A Hands-On Experience
TUT-10: Cyber-Security Solutions for Internet of Things Based on Hardware Security Primitives
TUT-11: Cellular-Based V2X Communications
TUT-12: Channel Measurement and Modeling for Fifth-Generation (5G) System
TUT-13: Ultra-Low Latency and Machine-Learning Based Mobile Networking
TUT-14: Sparse Signal Processing in Intelligent Communications: from Theory to Practice
TUT-15: A Unifying Data-Oriented Approach to Wireless Transmission of Big and Small Data
TUT-16: Energy and Spectral Efficiency Tradeoffs in Future Communication Networks

Friday, 24 May 2019, 9:00 – 12:30

TUT-17: Optimization and Economics of Edge-based User-Provided Networks
TUT-18: Physical Layer Authentication and Location Verification: A Machine-Learning Perspective
TUT-19: One Step Closer Towards Intelligent Wireless Network: Spatiotemporal Models, Learning, and Control
TUT-20: Machine Learning and Stochastic Geometry: Statistical Frameworks Against Uncertainty in Wireless LANs
TUT-21: Machine Learning for AI-Driven Wireless Networks: Challenges and Opportunities
TUT-22: Molecular Communications: Theory, Practice and Challenges
TUT-23: Wireless Communications with Unmanned Aerial Vehicles
TUT-24: 5G for Vehicle-to-Everything (V2X) Communication
TUT-25: Integrated Aerial/Terrestrial 6G Networks for 2030s

Friday, 24 May 2019, 14:00 – 17:30

TUT-26: Rate-Splitting and Non-Orthogonal Multiple Access Techniques for 5G and Beyond
TUT-27: Safeguarding the 5G Era and Beyond with Physical Layer Wireless Security
TUT-28: Fog-Radio Access Networks: Principles, Key Techniques, and Applications
TUT-29: Unlocking New Dimensions in Radio-based Positioning "5G Localization"
TUT-30: Machine Learning for Wireless Networks: Basics, Applications, and Trends
TUT-31: Orthogonal Time Frequency Space (OTFS) Modulation
TUT-32: Orbital Angular Momentum for Wireless Communications: Theory, Challenges, and Future Trends
TUT-33: Wireless Channel Measurements and Models for 5G and Beyond


TUT-01: UAV Applications over Cellular Networks: Sensing, Communication, and Computation
Zhu Han, University of Houston, USA; Lingyang Song, Peking University, China

The emerging unmanned aerial vehicles (UAVs) have been playing an increasing role in the military, public, and civil applications. Very recently, 3GPP has approved the study item on enhanced support to seamlessly integrate UAVs into future cellular networks. Unlike terrestrial cellular networks, UAV communications have many distinctive features such as high dynamic network topologies and weakly connected communication links. In addition, they still suffer from some practical constraints such as battery power, no-fly zone, etc. As such, many standards, protocols, and design methodologies used in terrestrial wireless networks are not directly applicable to airborne communication networks. Therefore, it is essential to develop new communication, signal processing, and optimization techniques in support of the ultra-reliable and real-time sensing applications, but enabling high data-rate transmissions to assist the terrestrial communications in LTE. Typically, to integrate UAVs into cellular networks, one needs to consider two main scenarios of UAV applications: UAV Assisted Cellular Communications and Cellular assisted UAV Sensing. There are four main objectives. The first objective is to provide an introduction to the UAV paradigm, from 5G and beyond communication perspective. The second objective is to introduce the key methods, including optimization, game, and graph theory, for UAV applications, in a comprehensive way. The third objective is to discuss UAV assisted cellular communications. The fourth objective is to present the state-of-the-art for cellular network assisted UAV sensing. Many examples will be illustrated in details so as to provide wide scope for general audiences.

 

TUT-02: Fog Computing: An Enabling Paradigm for Intelligent Services
Xiliang Luo, ShanghaiTech University, China; Xu Chen, Sun Vat-sen University, China; Ai-Chun Pang, National Taiwan University, Taiwan; Ming-Tuo Zhou,  Shanghai lnstitute of Microsystem and lnformation Technology (SlMlT), Chinese Academy of Sciences, China

A key networking trend during the past decade is to push various capabilities, such as computation, control, and storage, to the cloud. Such an over-dependence on the cloud, however, indicates that availability and fault tolerance issues in the cloud would directly impact millions of end-users. Such a cloud-centric architecture is not suitable for those many delay-sensitive applications in SG and loT. To deal with these challenges, the cloud is now "descending" to the network edges and diffuses among the client devices in both mobile and wireline networks. Such a transition leads to the new paradigm of fog computing and networking.

This tutorial will provide an overview of fog computing and networking, both in terms of industry practices and academic researches, with emphases on various intelligent services enabled by fog computing. The key topics are: (1) Overview of Fog Computing and Networking; (2) Computation Offloading and Resource Pooling for Fog Networking; (3) Distributed Learning and Applications in Fog Networks; (4) Enabling Low-Latency Applications in Fog Access Network; and (5) Fog Computing Technologies for SG and loT Applications.

 

TUT-03: Communication Network Design: Model-Based, Data-Driven, or Both?
Marco Di Renzo, Paris-Saclay University / CNRS, France; Alessio Zappone, CentraleSupelec, France; Merouane Debbah, Huawei, France

Data-driven approaches are not new to wireless communications, but their implementation through deep learning techniques has never been considered in the past, even though deep learning is the most widely used machine learning approach in other fields than wireless communication. This is mainly due to the fact that, unlike other fields of science where theoretical modeling is particularly hard, thus motivating the use of data-driven approaches, wireless communications could always rely on strong mathematical models for system design. However, the situation is rapidly changing, and very recently the use of deep learning has started being envisioned for wireless communications too. The increasing complexity of wireless networks makes it harder and harder to come up with theoretical models that are at the same time accurate and tractable. The rising complexity of 5G and beyond 5G networks is exceeding the modeling and optimization possibilities of standard mathematical tools. Nevertheless, purely data-driven approaches require a huge amount of data to operate, which might be difficult and/or expensive to acquire in practical large-scale scenarios. In this context, the specific field of communication theory presents a major opportunity thanks to the availability of many more theoretical models compared to other fields of science. Indeed, despite being usually inaccurate and/or cumbersome, available communication models still provide important prior information that should be exploited. The aim of this tutorial is to put forth the idea that theoretical modeling and data-driven approaches are not contrasting paradigms, but should be used jointly to get the most out of them.

 

TUT-05: Accessing from the Sky: UAV Communications for 5G and Beyond
Rui Zhang, National University of Singapore, Singapore; Yong Zeng, The University of Sydney, Australia

The integration of UAVs into existing (4G) and future (5G and beyond) cellular networks calls for a paradigm shift on the design of both cellular and UAV systems. In particular, both paradigms of cellular-connected UAV communications and UAV-assisted terrestrial communications are significantly different from the conventional terrestrial-only communications, due to the high altitude and mobility of UAVs, the unique channel characteristics of UAV-ground links, the asymmetric quality of service (QoS) requirements for downlink C&C and uplink mission-related data transmission, the stringent constraints imposed by the size, weight, and power (SWAP) limitations of UAVs, as well as the additional design degrees of freedom with joint UAV movement control and communication resource allocation. Significant research efforts from both academia and industry have been devoted to exploring this exciting new field, with remarkable progress made, especially in the past couple of years. This tutorial thus aims to provide a comprehensive overview of the state-of-the-art results on UAV-cellular integration, with a particular emphasis on the latest research findings on interference management and trajectory optimization in cellular-connected UAV communications. Open challenges and promising directions for future research will also be highlighted.

 

TUT-06: Quantum Internet: Wiring the Weirdness
Angela Sara Cacciapuoti, University of Naples Federico II, Italy; Marcello Caleffi, University of Naples Federico II, Italy

The tutorial provides an introduction to the Quantum Internet from a communication engineering perspective. First, the importance of the Quantum Internet will be highlighted, by reviewing the very last efforts, from both Industry and Academia. Then, the physical mechanisms underlying quantum communications, such as entanglement, no-cloning theorem, teleportation, as well as the quantum bra-ket notation will be gently introduced. Furthermore, the unique implications of these physical mechanisms on quantum communications will be presented and discussed. Moreover, quantum noise phenomena with no counterpart in the classical world, such as decoherence mechanisms, will be described along with their impacts on the transmission of the quantum information in the Quantum Internet. Finally, a review of the existing open problems and possible research directions for designing the Quantum Internet will conclude the tutorial.

 

TUT-07: Cognitive Backscatter Network: A New Paradigm of Energy- and Spectrum- Efficient IoT Communications
Ying-Chang Liang, University of Electronic Science and Technology of China, China; Dusit Niyato, Nanyang Technological University, Singapore

Ambient backscatter communication (AmBC) has recently emerged as a promising technology for energy- and spectrum-efficient Internet-of-Things (IoT) communication technology. On the one hand, AmBC enables IoT backscatter devices (BDs) to modulate their information symbols over ambient radio-frequency (RF) carriers (e.g., WiFi, TV, or cellular signals) without using costly and power-hungry RF transmitter. On the other hand, AmBC does not need dedicated radio spectrum which is scarce and expensive, due to the spectrum sharing between the backscatter transmission and the ambient transmission. Since the backscatter transmission depends on the ambient RF signals, there are many challenging problems in both fundamental theory and key techniques waiting to be solved, for example, how to find the communication limits, design a high-rate AmBC transceiver, and allocate resource optimally? In this tutorial, we will introduce the cognitive backscatter network (CBN) architecture based on AmBC, and provide efficient technical solutions for the above questions. In particular, this tutorial includes the basics of IoT communications, AmBC over OFDM carriers, MIMO-CBN, machine learning receiver for AmBC, spectrum sharing for AmBC, as well as future directions.

 

TUT-08: 5G Tactile Internet with Human-in-the-Loop
Frank H.P. Fitzek, Technische Universität Dresden, Germany; Gerhard Fettweis, Technische Universität Dresden, Germany

A big step lies ahead, when moving from today's 4G cellular networks to tomorrows 5G network. Today, the network is used for content delivery, e.g. voice, video, data. Tomorrow, the 5G network will provide a ubiquitous Tactile Internet infrastructure for controlling and steering real and virtual objects. For this we must create a control processing and a control communications infrastructure. For enabling the former, distributed mobile edge cloud computing will be created at a level, unheard of today. For enabling the latter, latency and resilience requirements must be met by designing networks along new paradigms. The resulting Tactile Internet will shape our future and our society, touching almost every part of life.

 

TUT-09: Deep Learning for Communications: A Hands-On Experience
Stephan ten Brink, University of Stuttgart, Germany; Jakob Hoydis, Nokia Bell Labs, France; Sebastian Cammerer, University of Stuttgart, Germany; Sebastian Dorner, University of Stuttgart, Germany

In the last decade, deep learning has led to many breakthroughs in various domains, such as computer vision, natural language processing, and speech recognition. Motivated by these successes, researchers all over the world have recently started to investigate applications of this tool to their respective domain of expertise, with communications being one of them. The goal of this tutorial is to provide an introduction to deep learning that will enable the attendees to identify potential applications in their own research field. We give an overview of the very rapidly growing body of literature, explain state-of-the-art neural network architectures and training methods, and go through several promising applications and concepts, such as neural decoding, deep MIMO detection and autoencoders. In the second part of this tutorial, we aim to lower the barrier-to-entry for ML-newcomers to enable the implementation of own applications. Therefore, a practical hands-on coding session introduces a state-of-the-art deep learning toolchain by implementing, training and evaluating an autoencoder system in Tensorflow. The attendees receive tutorial slides and Jupyter notebooks containing code examples, which allows them to quickly get up to speed with this new and exciting field. During the break, we demonstrate the world's first fully neural network-based communications system.

 

TUT-10: Cyber-Security Solutions for Internet of Things Based on Hardware Security Primitives
Biplab Sikdar, National University of Singapore, Singapore

The Internet of Things (IoT) represents a paradigm shift in the connectivity between people, information, and things, and is envisioned as the enabling technology for a wide range of application domains such as smart cities, power grids, health care, and control systems for critical installments and public infrastructure. This diversity, increased control and interaction of devices, and the fact that IoT systems use public networks to transfer large amounts of data make them a prime target for cyber attacks. IoT security and human safety are often tied to each other, and security breaches can lead to loss of service, damage to equipment, economic losses, and even loss of human lives. IoT devices are usually small, low cost and have limited resources, which makes them vulnerable to a wide range of physical, side-channel, and cloning attacks. This tutorial will start with an introduction and in-depth coverage of the security challenges associated with IoT systems and highlight the common methods to address these challenges. Next, the tutorial will address the shortcomings of current solutions, specially in the context of physical and side-channel attacks. The tutorial will then motivate the use of hardware based security primitives for solving these security issues, followed by an in-depth description of the current state-of-the-art in this area. Physically unclonable function (PUFs) and nano-enabled security primitives will be the two main focus technologies that will be covered in detail. Next, security protocols for authentication, confidentiality, and message integrity for IoT devices based on hardware security primitives will be introduced. Finally, the tutorial will conclude with a discussion on open research issues in this area.

 

TUT-11: Cellular-Based V2X Communications
Yi Qian, University of Nebraska–Lincoln, USA

A wide variety of work has been down in vehicle-to-everything (V2X) communications to enable various applications for road safety, traffic efficiency and passenger infotainment. Although IEEE 802.11p used to be considered as the main technology for V2X, new research trends nowadays are considering cellular technology as the future of V2X due to its rapid development and ubiquitous presence. This tutorial surveys the recent development and challenges on 4G LTE and 5G mobile wireless networks to support efficient V2X communications. In the first part, we highlight the technical motivations of 4G LTE for V2X communications. In the second part, we explore the LTE V2X architecture and operating scenarios being considered. In the third part, we discuss the challenges and the new trends in 4G and 5G for supporting V2X communications such as physical layer structure, synchronization, resource allocation, security, multimedia broadcast multicast services (MBMS), as well as possible solutions to these challenges. Finally, we discuss some open research issues for future 5G based V2X communications.

 

TUT-12: Channel Measurement and Modeling for Fifth-Generation (5G) System
Andreas Molisch, University of Southern California, USA; Jianhua Zhang, Beijing University of Posts and Telecommunications, China

For the design, performance assessment, and deployment planning of wireless systems, understanding of the propagation mechanisms and creation of suitable channel models is a conditio sine qua non. For 5G systems, measurement and modeling of the corresponding propagation channels is thus of the utmost interest. This is particularly relevant since the emerging massive or 3D MIMO bring a new domain, i.e., vertical plane while currently 4G standard channel model only including azimuth plane. Secondly, many of the dominant propagation effects of mm wave are significantly different from those at the traditional cm-wave frequencies. It is therefore clear that more efforts are needed to understand propagation characteristics especially in mm wave bands and to demonstrate their impact on system design and deployment. The proposed tutorial is intended both for experts in 5G channel modeling, and for communications engineers that want to apply channel models and gain an understanding of how channel characteristics impact system design.

 

TUT-13: Ultra-Low Latency and Machine-Learning Based Mobile Networking
Kwang-Cheng Chen, University of South Florida, USA; Shih-Chun Lin, North Carolina State University, USA

Autonomous (or unmanned) vehicles (AVs) emerge as one major technological paradigm shift of the industry and human society, while introducing more technological challenges in wireless networks. As the technology for single AV/robot becoming mature, the real challenge comes from reliable, safe, real-time operation of AVs/robots in massive scale. To achieve such multi-scale management and control, effective cloud computing, edge computing, and on-board computing, networking and computing in real-time to interact with environments and other agents such as vehicles and individuals. Ultra-low latency mobile networking is inevitably wanted to ensure successful control and services in this most challenging Internet of Things and robotics. Considering high reliability and safety, various innovative networking technologies would be needed. This tutorial will present key and emerging technological aspects of ultra-low latency mobile networking based on machine learning (ML) network architecture: uplink and downlink air-interface, ultra reliable and ultra-low latency communication (uRLLC) for 5G and beyond, network function virtualization (NFV) of network resources, ML enabled anticipatory mobility management, channel estimation and radio resource allocation based on ML, software defined networking architecture and realization, network security, and machine-learning based network architecture under new development by the ITU-T, toward future ultra-low latency and ML based mobile networking.

 

TUT-14: Sparse Signal Processing in Intelligent Communications: from Theory to Practice
Yue Gao, Queen Mary University of London, United Kingdom; Zhijin Qin, Queen Mary University of London, United Kingdom; Geoffrey Li, Georgia Tech, USA

Sparse representation can efficiently model signals in different applications to facilitate processing. In this tutorial, we will discuss the sparse representations in wireless communications, with focus on the most recent machine learning and compressive sensing enabled approaches. With the help of the sparsity property, compressive sensing is able to enhance the spectrum efficiency and energy efficiency for the fifth generation (5G) networks and Internet of Things (IoT) networks. This tutorial starts from a comprehensive overview of compressive sensing principles and different sparse domains potentially used in 5G and IoT networks. Then recent research progress on applying compressive sensing to address the major opportunities and challenges in 5G and IoT networks will be introduced, in which the wideband spectrum sensing is provided as an example. Particularly, both the latest theory contributions and the implementation platform will be discussed. Moreover, other potential applications and research challenges on sparse representation for 5G and IoT networks are discussed. This tutorial will provide readers a clear picture of how to exploit the sparsity properties to process wireless signals in different applications.

 

TUT-15: A Unifying Data-Oriented Approach to Wireless Transmission of Big and Small Data
Hong-Chuan Yang, University of Victoria, Canada; Mohamed-Slim Alouini, King Abdullah University of Science and Technology (KAUST), Saudi Arabia

Wireless communication systems will play an essential role in the data transmission for future big data and Internet of Things (IoT) applications. In the proposed tutorial, we present a unique data-oriented approach for the design and analysis of wireless transmission strategies, targeting an integrated common physical transmission infrastructure for both big and small data. After introducing the key idea and example designs, we present novel data-oriented performance metrics and apply them to the analysis of wireless transmission strategies in information theoretical and practical transmission settings. We also develop analytical frameworks to accurately characterize the data transmission time in both cognitive and non-cognitive environments. Compared to conventional analytical approach, the data-oriented approach offers important new insights and leads to interesting new research directions. Through this tutorial, the attendees will obtain a brand new perspective to wireless transmission technology design.

 

TUT-16: Energy and Spectral Efficiency Tradeoffs in Future Communication Networks
Guowang Miao, KTH Royal Institute of Technology, Sweden; Zhisheng Niu, Tsinghua University, China; Ender Ayanoglu, University of California, Irvine, USA

The future success of communication networks hinges on the ability to overcome the mismatch between requested quality of service and limited network resources. Spectrum is a natural resource that cannot be replenished and therefore must be used efficiently. This makes spectrum efficiency to be very important for communication systems. Communications engineers have developed many techniques to maximize spectral efficiency. Accompanying this great success is also the significant energy consumption that is generating growing environmental and economical concerns. The sustainable development calls for solutions to reduce network energy consumption and improve network energy efficiency. It is particularly important to consider energy efficiency as the key performance metric designing future communication networks. We will then concentrate on mobile data networks. With the upcoming Fifth Generation (5G) cellular standard and the expected tremendous increase in network traffic, these networks will become even more important than today. It is already known that today's cellular networks are not energy-efficient. After revealing the causes of energy inefficiency in today's networks, we will introduce a large number of techniques, applicable across several layers of the communications hierarchy, that have demonstrated substantial improvement in energy and spectral efficiency. We will discuss techniques to jointly optimize spectral and energy efficiency in such networks. Finally, we will discuss energy efficiency in future data centers. Data centers are where most of the future Internet services will originate from and where the biggest challenges to energy efficiency exist. Currently, data centers provide about 4% of the total energy consumption, with today's 5 billion devices connected to the Internet. Yet, Internet-of-Things is expected to bring about 50 billion devices connected to the Internet, with much more intelligence expected to take place in data centers, for example, via extensive simulations of the data provided by sensors. Resulting energy consumption figures are very high. Therefore, new approaches to data center energy efficiency are needed. We will discuss such existing approaches.

 

TUT-17: Optimization and Economics of Edge-based User-Provided Networks
George Iosifidis, Trinity College Dublin, Ireland; Lin Gao, Harbin Institute of Technology (Shenzhen), China; Jianwei Huang, The Chinese University of Hong Kong, Hong Kong; Leandros Tassiulas, Yale University, USA

The ever-increasing communication and computing needs of mobile services place the edge-based user-provided networks (UPNs) in a conspicuous position for next-generation Internet (of Things) architectures. These systems enable the orchestration of user-owned network, computation and caching resources at the very edge, right next to demand, and hence are scalable and resource-efficient. Today there are numerous proposals for UPN-inspired solutions coming from network operators, over-the-top service providers, or innovative start-ups; and their role is expected to be even more central in the Internet of Things. However, these architectures rely on the availability of resources shared by the end-users, who are inherently self-interested, often risk-averse, and even egotistic. This makes the design of UPNs a multifaceted techno-economic problem, and raises many currently-open challenges that are hindering their large-scale adoption. This tutorial will provide an overview of UPNs, both in terms of industry practice and academic research. Motivated by novel business models in network sharing solutions, we will focus on mobile UPNs where the energy consumption and data usage costs are critical, while storage and computation resources are limited. Hence, the values of these parameters have large impacts on users' decisions both for requesting and offering their resources to UPNs. We will first analyze the technical design challenges of UPNs, discussing possible solutions and presenting results from working prototypes and extensive field tests. Next, we will present different classes of incentive mechanisms aiming to jointly maximize user participation and service performance. We will analyze such mechanisms for different business models, namely self-organizing and operator-controlled wireless networks, and explain the arising trade-offs between performance, efficiency and fairness. The tutorial will discuss cutting-edge UPN design techniques based on cooperative game theory, bargaining theory, auctions, and distributed optimization algorithms; and will conclude by presenting bottleneck issues that must be further addressed in order to unleash the full potential of this promising solution.

 

TUT-18: Physical Layer Authentication and Location Verification: A Machine-Learning Perspective
Stefano Tomasin, University of Padova, Italy; Xianbin Wang, University of Western Ontario, Canada

The problem of user and device authentication has been typically approached by cryptographic techniques, while more recently features of the physical transmission channel have been considered as new authentication tags. Since the channel features are typically associated with the specific position of both the transmitter and the receiver, the physical layer user authentication can also be seen as a way to authenticate the position of the user at a single spot or in an area, in what is known as location verification process. However, the channel feature estimates used for authentication are affected by noise, interference and time-varying phenomena, whose statistics are required for an effective authentication. Since these statistics strongly depend on the environment, new approaches based on machine learning are needed. This is particularly relevant when fusing multiple heterogeneous features to make the authentication more robust. Similarly, learning becomes pivotal with location verification, where feature statistics must be known for an entire area rather than for a single position. Indeed, by a proper design, the machine learning solution directly learns the whole decision process behind authentication in the specific use context, exploiting at best the potentials of artificial intelligence (AI). The tutorial will give an overview of physical layer user authentication and location verification techniques, outlining potentials and shortcomings, and indicating practical solutions. An important part of the tutorial will focus on machine learning approaches for fusing multiple channel features in both user authentication and location verification, also establishing the connection with optimal authentication when statistics are perfectly known.

 

TUT-19: One Step Closer Towards Intelligent Wireless Network: Spatiotemporal Models, Learning, and Control
Howard Yang, SUTD, Singapore; Tony Q. S. Quek, Singapore University of Technology and Design, Singapore

The rapid growth of wireless applications brings new challenges for next generation system, where it is expected to manage a massive number of devices in real time within a highly dynamic environment. Motivated by the burgeoning progress of artificial intelligence and the breakthroughs it led in a variety of domains, the communication society is currently seeking solutions from machine learning for intelligent controls on the physical (PHY) and medium access control (MAC) layers of future network. While many learning based methods, e.g., reinforcement learning, are able to directly devise control policies from the collected data set without an explicit model, such approaches can on the one hand take a long time to converge, and on the other, perform unreliable trial-and-error exploration actions on real network, which degrades the network performance. To guarantee the real time effectiveness and avoid trying potentially wrong solutions, it becomes essential to incorporate an suitable model that captures the fundamental features of a wireless network, i.e., the physical transmission environment and the temporal dynamic of traffic, for the efficient training procedure of machine learning schemes. In this tutorial, we introduce an approach to develop appropriate spatiotemporal models and incorporate them in the design of intelligent wireless networks. Specifically, we first provide a complete survey to the basic spatiotemporal models for wireless networks, follow by a recently developed refined establishment. We then show how these models can be leveraged with machine learning techniques to design various intelligent applications in wireless networks. Finally, we conclude by shedding light on the future works.

 

TUT-20: Machine Learning and Stochastic Geometry: Statistical Frameworks Against Uncertainty in Wireless LANs
Koji Yamamoto, Kyoto University, Japan; Takayuki Nishio, Kyoto University, Japan

This tutorial aims to provide fundamentals of machine learning and stochastic geometry. For machine learning, deep supervised learning and reinforcement learning are introduced. One special feature of this tutorial is that it is specialized to microwave and mmWave wireless LANs (WLANs). The outline is as follows: (1) Issues in microwave and mmWave WLANs, (2) Stochastic geometry and analysis of microwave WLAN taking into account spatial reuse technique in IEEE 802.11ax, (3) Reinforcement learning towards spatial reuse technique in IEEE 802.11ax, (4) From basics to practice: Supervised learning in WLANs, and (5) Deep Learning in/for WLANs. In detail, we address how to apply the machine learning techniques to challenges in WLANs based on mmWave, received power prediction and handover. In addition, we demonstrate how to use deep learning frameworks with using Google Colab, Tensorflow with Keras, and the publicly available dataset.

 

TUT-21: Machine Learning for AI-Driven Wireless Networks: Challenges and Opportunities
Walid Saad, Virginia Tech, USA; Mehdi Bennis, University of Oulu, Finland

The goal of this tutorial is to provide a holistic introduction to machine learning for intelligent wireless network design. In particular, we first provide a comprehensive treatment of the fundamentals of machine learning and artificial neural networks. Then, we introduce a classification of the various types of neural networks that include feed-forward neural networks, recurrent neural networks, spiking neural networks, and deep neural networks. For each type, we provide an introduction on their basics and to specific use cases. Then, we overview a broad range of wireless applications that can make use of neural network designs. This range of applications includes spectrum management, multiple radio access technology cellular networks, wireless virtual reality, mobile edge computing and caching, drone-based communications, the Internet of Things, and vehicular networks. For each application, we first outline the main rationale for applying machine learning while pinpointing illustrative scenarios. Then, we overview the challenges and opportunities brought forward by the use of neural networks in the specific wireless application. We complement this overview with a detailed example drawn from the state-of-the-art. Finally, we conclude by shedding light on the potential future works within each specific area and within the overall area of machine learning for wireless networks.

 

TUT-22: Molecular Communications: Theory, Practice and Challenges
Lie-Liang Yang, University of Southampton, United Kingdom

Molecular communications (MC) has been recognized as an attractive solution for information exchange between nano-machines and in nano-scale networks operated in fluid and gas environments. By taking its potential advantages of bio-compatibility and low energy consumption, MC is expected to find a lot of applications in the areas, where the operation of conventional electromagnetic based communications is inefficient and/or impractical. Potential applications of MC may include health-care, intelligent drug delivery, environment monitoring, industry applications, Internet of Nano Things (IoNT), etc. Owing to these, MC has received an increasing attention in research and development in recent years. In this tutorial, we motivate to provide a comprehensive introduction to the state-of-the-art in MC. We will emphasize the similarity and difference between MC and the conventional electromagnetic based communications. The fundamentals of MC, channel modeling in MC and the transceiver techniques for MC, as well as some advanced MC techniques, including multiple-input multiple-output (MIMO) MC, multiple-access MC, and the error-control coding in MC, will be addressed. Furthermore, some challenges and opportunities of MC will be discussed.

 

TUT-23: Wireless Communications with Unmanned Aerial Vehicles
Evgenii Vinogradov, KU Leuven, Belgium; Sofie Pollin, KU Leuven, Belgium

The growing use of Unmanned Aerial Vehicles (UAVs) for various applications requires ubiquitous and reliable connectivity for safe control and data exchange between these devices and ground terminals. Depending on the application, UAV-mounted wireless equipment can either be an aerial user equipment (AUE) that co-exists with the terrestrial users, or it can be a part of wireless infrastructure providing a range of services to the ground users. For instance, AUE can be used for real-time search and rescue and Aerial Base Station (ABS) can enhance coverage, capacity, and energy efficiency of wireless networks. We will start with discussing the open challenges of communication with UAVs. To give answers to the posed questions, we will focus on the UAV communication basics, providing the channel modeling background and giving guidelines on how various channel models should be used. Next, theoretical, simulation- and measurement-based approaches to address the key challenges for AUE usage will be presented. Moreover, we will provide a comprehensive overview on how UAV-mounted equipment (e.g. ABS) can be used as apart of the communication network. Based on the theoretical analysis, we will show how various network parameters (for example coverage area of ABSs, power efficiency, or user localization error)can be optimized. Finally, we will discuss how to ensure the safe use of UAVs via various RF-based techniques for detecting the presence of UAVs in the airspace (including Machine Learning and Passive Coherent Location techniques).

 

TUT-24: 5G for Vehicle-to-Everything (V2X) Communication
Robert Heath, The University of Texas at Austin, USA; Nuria González-Prelcic, The University of Texas at Austin, USA

Vehicles are becoming more intelligent and automated. To achieve higher automation levels, vehicles are being equipped with more and more sensors. High data rate connectivity seems critical to allow vehicles and road infrastructure exchanging all these sensor data to enlarge their sensing range and make better safety related decisions. Connectivity also enables other applications such as infotainment or high levels of traffic coordination. Current solutions for vehicular communications though do not support the gigabit-per-second data rates. This presentation makes the case for 5G as the solution for the next generation of V2X. First, the motivation and challenges associated with vehicle-to-vehicle and vehicle-to-infrastructure applications are highlighted. Second, the key uses cases for V2X in 5G are summarized including raw sensor data sharing, platooning, collision avoidance, see-through, and mapping are reviewed. Finally, specific technical challenges in realizing 5G V2X are identified, with an emphasis on solutions that make use of millimeter wave spectrum.

 

TUT-25: Integrated Aerial/Terrestrial 6G Networks for 2030s
Halim Yanikomeroglu, Carleton University, Canada

The 5G standards are currently being developed with a scheduled completion date of late-2019; the 5G wireless networks are expected to be deployed globally throughout 2020s. As such, it is time to reinitiate a brainstorming endeavour followed by the technical groundwork towards the subsequent generation (6G) wireless networks of 2030s. One reasonable starting point in this new 6G discussion is to reflect on the possible shortcomings of the 5G networks to-be-deployed. 5G promises to provide connectivity for a broad range of use-cases in a variety of vertical industries; after all, this rich set of scenarios is indeed what distinguishes 5G from the previous four generations. Many of the envisioned 5G use-cases require challenging target values for one or more of the key QoS elements, such as high rate, high reliability, low latency, and high energy efficiency; we refer to the presence of such demanding links as the super-connectivity. However, the very fundamental principles of digital and wireless communications reveal that the provision of ubiquitous super-connectivity in the global scale - i.e., beyond indoors, dense downtown or campus-type areas - is infeasible with the legacy terrestrial network architecture as this would require prohibitively expensive gross over-provisioning. The problem will only exacerbate with even more demanding 6G use-cases such as UAVs requiring connectivity (ex: delivery drones), thus the 3D super-connectivity. In this talk, we will present a 5-layer vertical architecture composed of fully integrated terrestrial and non-terrestrial layers for 6G networks of 2030s.In the absence of a clear technology roadmap for the 2030s, the talk has, to a certain extent, an exploratory view point to stimulate further thinking and creativity. We are certainly at the dawn of a new era in wireless research and innovation; the next twenty years will be very interesting.

 

TUT-26: Rate-Splitting and Non-Orthogonal Multiple Access Techniques for 5G and Beyond
Bruno Clerckx, Imperial College London, United Kingdom

Numerous techniques have been developed in the last decade for MIMO wireless networks, including among others MU-MIMO, CoMP, Massive MIMO, NOMA, millimetre wave MIMO. All those techniques rely on two extreme interference management strategies, namely fully decode interference and treat interference as noise. Indeed, while NOMA based on superposition coding with successive interference cancellation relies on strong users to fully decode and cancel interference created by weaker users, MU-MIMO/Massive MIMO/CoMP/millimetre wave MIMO based on linear precoding rely on fully treating any residual multi-user interference as noise. In this tutorial, we depart from those two extremes and introduce the audience to a more general and more powerful transmission framework based on Rate-Splitting (RS) that consists in decoding part of the interference and in treating the remaining part of the interference as noise. This enables RS to softly bridge and therefore reconcile the two extreme strategies of fully decode interference and treat interference as noise. RS relies on the transmission of common messages decoded by multiple users, and private messages decoded by their corresponding users. As a result, RS pushes multiuser transmission away from conventional unicast-only transmission to non-orthogonal unicast multicast-like transmission and leads to a more general class/framework of strategies, e.g. NOMA and SDMA/MU-MIMO with linear precoding being special cases of RS. RS will be shown to provide significant benefits in terms of spectral efficiencies, reliability and CSI feedback overhead reduction over conventional strategies used/envisioned in LTE-A/5G. The gains of RS will be demonstrated in a wide range of scenarios: multi-user MIMO, massive MIMO, multi-cell MIMO/CoMP, overloaded systems, NOMA, multigroup multicasting, mmwave communications, communications in the presence of RF impairments. Open problems and challenges will also be discussed.

 

TUT-27: Safeguarding the 5G Era and Beyond with Physical Layer Wireless Security
Nan Yang, The Australian National University, Australia; Xiangyun Zhou, The Australian National University, Australia; Jemin Lee, Daegu Gyeongbuk Institute of Science and Technology (DGIST), Korea

Wireless everything-this is the goal that the digital society is marching towards. Looking 10-20 years ahead, the ubiquitous wireless world aims at building ultra-high-quality wireless networks that connect a massive number of human- and machine-type devices and enable fully interoperable information exchange among them. Security is one of the pivotal issues that need to be carefully addressed in the design and implementation of such wireless networks, since wireless transmissions are inherently vulnerable to security breaches. This tutorial focuses on physical layer security, which has been recognized as a promising paradigm to protect data confidentiality by exploiting the intrinsic randomness of the communications medium. In particular, this tutorial places an emphasis on leveraging disruptive wireless technologies to secure data transmission from the physical layer.

 

TUT-28: Fog-Radio Access Networks: Principles, Key Techniques, and Applications
Zhongyuan Zhao, Beijing University of Posts and Telecommunications, China; Haijun Zhang, University of Science and Technology Beijing, China; Mugen Peng, Beijing University of posts & Telecommunications, China

To satisfy the explosively increasing demands of diverse mobile services and massive access requirements of various Internet-of-thing (IoT) devices, a framework of fog-radio access networks (F-RANs) has emerged as a promising evolution path for the network architecture. In F-RANs, the principles and the key techniques should be studied to take full advantages of distributed caching and centralized processing, which can provide great flexibility to satisfy quality-of-service requirements of various application scenarios. In this tutorial, we will provide a comprehensive overview of F-RANs. The objective of this tutorial is to provide a solid guidelines of F-RAN to the audience, which can present the most recent research progress comprehensively, by clarifying the key problems, by introducing the research methodologies, as well as by explaining the main results. Moreover, we share our points of view with respect to the possible future research directions.

 

TUT-29: Unlocking New Dimensions in Radio-based Positioning "5G Localization"
Henk Wymeersch, Chalmers University of Technology, Sweden; Gonzalo Seco-Granados, Universitat Autonoma de Barcelona, Spain

5G will be characterized by increased data rates, higher density of devices, and a wide variety of use cases. The use mmWave technology is one of the novel elements in 5G systems, and it offers the potential to satisfy the rate requirements is mmWave thanks to the large available bandwidth and directional interference-free transmissions. As a side-effect, mmWave signals are useful for inter-device ranging as well as inter-device angle estimation. In turn, this leads to a potential new positioning technology: 5G localization. This tutorial will cover the basics of the new area 5G localization, covering models; performance bounds; algorithms for localization, tracking, and mapping; and applications. The tutorial presumes basic knowledge on wireless communication and statistical signal processing.

 

TUT-30: Machine Learning for Wireless Networks: Basics, Applications, and Trends
Ekram Hossain, University of Manitoba, Canada

This tutorial will provide a friendly introduction to the different machine learning (ML) techniques with their applications to design and optimization of wireless communications networks. After motivating the potential applications of machine learning for the evolving future cellular networks (e.g. 5G and beyond 5G [B5G] cellular networks), it will introduce the basics of machine learning (ML) tools and the related mathematical preliminaries. In particular, the basics of supervised, unsupervised, and reinforcement learning techniques as well as artificial neural networks will be discussed. The basics of deep learning and deep reinforcement learning will be also provided. Then, applications of ML techniques to different ``wireless" problems including resource allocation, mobility prediction, channel estimation, as well as coverage and capacity optimization will be discussed and the current state-of-the-art will be reviewed. This will be followed by three case studies on using (i) supervised and unsupervised learning for cooperative spectrum sensing, (ii) a deep supervised learning technique for resource allocation, and (iii) reinforcement learning techniques for mobile computation offloading in cellular networks. Finally, the current trends, open research challenges and future research directions on using ML techniques in wireless networks will be discussed.

 

TUT-31: Orthogonal Time Frequency Space (OTFS) Modulation
Emanuele Viterbo, Monash University, Australia; Yi Hong, Monash University, Australia; A. Chockalingam, Indian Institute of Science, India

Emerging mass transportation systems - such as self-driving cars, high-speed trains, drones, flying cars, and supersonic flight - will challenge the design of future wireless networks due to high-mobility environments: a large number of high-mobility users require high data rates and low latencies. The physical layer modulation technique is a key design component to meet the system requirements of high mobility. Currently, orthogonal frequency division multiplexing (OFDM) is the modulation scheme deployed in 4G long term evolution (LTE) mobile systems, where the wireless channel typically exhibits time-varying multipath fading. OFDM can only achieve a near-capacity performance over a doubly dispersive channel with a low Doppler effect, but suffers heavy degradations under high Doppler conditions, typically found in high-mobility environments. Orthogonal time frequency space (OTFS) modulation has been very recently proposed by Hadani et al. at WCNC'17, San Francisco. It was shown to provide significant advantages over OFDM in doubly dispersive channels. OTFS multiplexes each information symbol over a 2D orthogonal basis functions, specifically designed to combat the dynamics of the time-varying multipath channels. As a result, all information symbols experience a constant flat fading equivalent channel. OTFS is only in its infancy, leaving many opportunities for significant developments on both practical and theoretical fronts.

 

TUT-32: Orbital Angular Momentum for Wireless Communications: Theory, Challenges, and Future Trends
Wenchi Cheng, Xidian University, China

It is now very difficult to use the traditional plane-electromagnetic (PE) wave based wireless communications to satisfy the ever-lasting capacity demand growing. Fortunately, the electromagnetic (EM) wave possesses not only linear momentum, but also angular momentum, which includes the orbital angular momentum (OAM). The orbital angular momentum (OAM), which is a kind of wave front with helical phase and has not been well studied yet, is another important property of EM wave. The OAM-based vortex wave has different topological charges, which are independent and orthogonal to each other, bridging a new way to significantly increase the capacity of wireless communications. This proposal will be discussing the fundamental theory of using orbital angular momentum (OAM) for wireless communications. This proposal would start with the background introduction on what is OAM based wireless communication and how OAM is important in current and future wireless communications. Then, the fundamental theory of OAM will be elaborated on in details, including OAM versus MIMO, OAM signal generation/reception, and OAM beam converging. Moreover, we would also like to share our latest research progress regarding how to apply OAM into wireless communications, including mode modulations, OAM mode convergence, mode hopping, OAM based MIMO, orthogonal mode division multiplexing, concentric UCAs based low-order OAM transmission, degree of freedom in mode domain as well as orthogonality of OAM mode. Finally, the applications of OAM based wireless communication are also discussed.

 

TUT-33: Wireless Channel Measurements and Models for 5G and Beyond
Cheng-Xiang Wang, Southeast University, China; Zaichen Zhang, Southeast University, China; Haiming Wang, Southeast University, China

For the design, performance evaluation, and optimization of 5G and B5G wireless communication systems, experimental channel measurements and realistic channel models with good accuracy-complexity-generality trade-off are indispensable. The proposed tutorial is intended to offer a comprehensive and in-depth crash course to communication professionals and academics, aiming to address recent advances and future challenges for (B)5G channel measurements and models. The tutorial will start with illustrating the fundamentals of wireless channel characterization and evolution of wireless channel models from 2G to 5G. Channel measurements and models are then reviewed for some challenging 5G scenarios, including massive MIMO, millimetre wave, V2V, and HST communication channels. We will also review existing standard 5G channel models in terms of their capabilities and drawbacks. Two more general three-dimensional (3D) non-stationary 5G channel models are proposed, filling the gaps of standard 5G channel models. It is shown that the proposed 5G channel models have statistical properties agreeing well with corresponding channel measurements and are expected to serve as good basis for future standard (B)5G channel models. B5G requirements and potential technologies will be further discussed, including the newly proposed optical mobile communication (OMC) which incorporates traditional optical wireless communication (OWC) into the mobile communication architecture. Future research challenges and trends for (B)5G channel measurements and models will be discussed in the end of the tutorial.

Patrons

Exhibitors