Tutorials

TUTORIAL #1

MONDAY, 5 OCTOBER 2020

Time: 1:30 PM – 5:00 PM Western Indonesia Time (GMT +7)

Room 3

Artificial Intelligence based Future Wireless Networks

Haijun Zhang

University of Science and Technology Beijing, China

Yansha Deng

King’s College London (KCL), U.K

Arumugam Nallanathan

Queen Mary University of London, UK

Abstract:

This tutorial will identify and discuss technical challenges and recent results related to the Artificial Intelligence (AI) based future wireless networks. The tutorial is mainly divided into four parts. In the first part, we will introduce future wireless networks and AI, discuss about the future wireless networks architecture, and provide some main technical challenges in AI based future wireless networks. In the second part, we will focus on the issue of AI based resource management in future wireless networks and provide different recent research findings that help us to develop engineering insights. In the third part, we will address the signal processing and PHY layer design of AI based future wireless networks and address some key research problems. In the last part, we will summarize by providing a future outlook of AI based future wireless networks.

Brief Description

Nowadays, the mobile network no longer just connects people but is evolving into billions of devices, such as sensors, controllers, machines, autonomous vehicles, drones, people and things with each other and then achieves information and Intelligence. From a planning and optimization perspective on the mobile network, this means that we also need a lot more flexibility to address these future needs.

Next-generation (B5G/6G) mobile networks are characterized by three key features: heterogeneity, in terms of technology and services, dynamics, in terms of rapidly varying environments and uncertainty, and size, in terms of number of users, nodes, and services. The need for smart, secure, and autonomic network design has become a central research issue in a variety of applications and scenarios. Intelligence (AI) and future wireless networks have attracted intense interest from both academia and industry to potentially improve spatial reuse and coverage, thus allowing cellular systems to achieve higher data rates, while retaining the seamless connectivity and mobility of cellular networks. However, considering the severe inter-tier interference and limited cooperative gains resulting from the constrained and non-ideal transmissions between adjacent base stations, a new paradigm for improving both spectral efficiency and energy efficiency through suppressing inter-tier interference and enhancing the cooperative processing capabilities is needed in the practical evolution of AI based future mobile networks.

This tutorial will identify and discuss technical challenges and recent results related to the AI based future mobile networks. The tutorial will introduce future mobile networks and AI, discuss about the future mobile networks architecture, AI based resource management, PHY layer design with AI and providing a future outlook of AI based future wireless networks.

Outline:

Part I: Overview of Future Wireless Networks and AI

  • RAN Evolutions: Brief introduction of 6G, and its potential evolution.
  • Introduction of AI based Future Wireless Networks: Features, definitions, challenges, and state of the art.
  • System architecture: Fronthaul, Fog/cloud computing, heterogeneous networks, performance metrics

Part II: AI based Resource Management in Future Wireless Networks

  • Artificial Intelligence based resource allocation in ultra-dense networks
  • Deep neural network based power control for NOMA networks
  • Cross layer optimization in AI based future wireless networks
  • User association and power allocation using deep learning

Part III: AI based Interference Management in Future Wireless Networks

  • Learning based interference mitigation
  • AI based interference mitigation and handover management
  • Coexistence of Wi-Fi and UDN with LTE-U
  • Incomplete CSI based resource optimization in SWIPT

Part IV: AI enabled dynamic optimization in IoT and UAV • Deep reinforcement learning in NB-IoT

  • Unmanned Aerial Vehicles Meet Multi-Agent Reinforcement Learning

Part V: Outlook of AI based Future Wireless Networks

  • Evolution of AI based Future Wireless Networks: Future research challenges

TUTORIAL #2

MONDAY, 5 OCTOBER 2020

Time: 4:00 PM – 7:30 PM Western Indonesia Time (GMT +7)

Main Room

Role of Flying Platforms for Global Connectivity

Muhammad Zeeshan Shakir

University of the West of Scotland, UK

Mohamed-Slim Alouini

King Abdullah University of Science and Technology, Thuwal, Saudi Arabia

Abstract:

Driven by an emerging use of flying platforms such as unmanned aerial vehicles (UAVs), drones and unmanned balloons in future network applications and the challenges that the 6G networks exhibit, the focus of this tutorial is to demonstrate the evolution of the flying platforms as a novel architectural enabler for radio access network (RAN) and their integration with the future cellular access and backhaul/fronthaul networks.These platforms are networked, flying and a potential way to offer high data rate, high reliability and ultra-low latent access and backhaul/fronthaul to future wireless networks. Such large scale deployable platforms and frameworks will guarantee the global information and communication requirements in future smart and resilient cities and solve the ubiquitous connectivity problems in many challenging network environments, e.g., coverage or capacity enhancements for remote or sparsely populated areas,social gathering, temporary health infrastructure (such as the ones being build during Covid-19 Pandemic in the UK) and disaster affected scenarios, etc. This tutorial will provide balanced coverage on recent trends, challenges and future research and development on the integration of flying platforms with the future wireless networks. Specifically, this tutorial will provide answers for the following:

  • How flying platforms can be used for autonomous coverage hole discovery as an alternate to the minimization drive test using machine learning to offer a reliable and scalable solution to enhance the coverage and capacity of the access networks (flying platform placement and user associations)?
  • How flying platforms can be used to fronthaul the small cell deployment to the core network (e.g. at temporary sites) and offer a flexible wireless solution (playing platform deployment architecture, potential high data rate technologies, e.g., free space optics (FSO) and playing platform-small cell association)?
  • What are the economic, regulatory and industrial perspectives of deploying flying platforms for cellular access and backhaul networks (total cost of operation, automation and some latest regulations)?

Outline:

1) Moving toward beyond 6G networks

  • Motivation of Ultra-dense small cell networks in the light of history: From Nikola Tesla’s vision till today and beyond 5G including 6G use cases and projections
  • A road map to beyond 6G networks covering technologies and tools for improving spectral efficiency, spectrum efficiency and network densification
  • Beyond 5G Perspectives and road map for resilience and reliable wireless communications for global connectivity – United Nation’s Sustainable Development Goals (SDG) covering use of 5G tech for Pandemic

2) Flying Platforms for 6G: Overview

  • Introduction to flying platforms covering emerging roles, fundamentals and limitations for 6G communications
  • Classification of flying platforms based on constraints such as battery, payload, endurance, and cost etc.
  • Introduction to Airborne Self organizing networks (SON) architecture – layered flying platforms architecture
  • Overview of the 6G use cases including provision of fronthaul/backhaul, relaying and access networks in airborne networks using Tethered/Untethered flying platforms

3) Coverage hole discovery – Industrial Use case

  • Industrial practises covering ongoing trials by BT-UWS project to discover coverage hole autonomously using machine learning; comparison with other approaches by Ericsson trials and Qualcomm trials; Live demo of not-spot detection using drone based machine learning on real data (Scotland)
  • ITU regulations related to drone commercial user and deployments as base station and limitations; covering recent discussions with UK Civil aviation agency and National Air Traffic Control Services (NATS)
  • General challenges including safety and security; costing; test-beds developments; and weather conditions

4) Vertical fronthaul/backhaul (30 min)

  • Overview of ultra dense small cell network deployment, challenges and requirements such as provision of wireless fronthaul, interference management, capacity and coverage
  • Comprehensive coverage and comparison of wireless backhaul/fronthaul technologies for small cells covering traditional non-line-of-sight (NLoS) solution, fiber, mm-wave, FSO and hybrid RF/mmWave/FSO
  • Vertical fronthaul design using flying platforms; FSO and performance evaluation including link margin analysis, achievable data rate and deployment scenarios and total cost of ownership (TCO) comparison
  • Flying platform-Small cell association problem covering central and distributed approaches for optimization of small cell association and performance evaluation

5) Hybrid RF/FSO for Airborne Networks (45 min)

  • New spectrum hunting for airborne architecture; FSO communication as a possible candidate
  • Overview of hybrid RF/FSO solutions for backhaul/fronthaul and access airborne networks covering limitations and requirements of backhaul/fronthaul/access airborne networks
  • Hybrid RF/FSO link design using Graph Theory and performance of hybrid link designs in terms of data rate, BER and deployment cost
  • FSO challenges for airborne network such as weather, cost, error modelling and regulations

6) Flying platforms for Access Networks

  • Motivation to deploy drone-BS and improve network densification covering requirements and challenges in access networks such as backhaul for drone-BS
  • Drone-BS deployment models covering Air to Ground channel modelling (user association), and system model including resource allocation
  • Backhaul/fronthaul aware 3D drone-BS placement problem formulation and performance evaluation of optimisation algorithms in terms of data rate, coverage probability and capacity
  • Integration of D2D in to airborne network including mode selection and performance evaluation

7) Conclusions

 

February 17, 2020

July 6, 2020

Regular Submission Deadline


February 17, 2020

July 6, 2020

Tutorial Proposal Deadline


February 17, 2020

July 6, 2020

Special Sessions Submission Deadline


March 16, 2020

August 3, 2020

Acceptance Notification


March 30, 2020

August 31, 2020

Camera-Ready Deadline


March 30, 2020

August 31, 2020

Registration Deadline


October 5-7, 2020

Conference Date


Organized by:

Technically Co-Sponsored by:

Supported by:

Patronized by:

Institut Teknologi Bandung, Indonesia

Institut Teknologi Del, Indonesia

King’s College London, United Kingdom