Internet Access in Vehicular Networks

✍ Scribed by Wenchao Xu, Haibo Zhou, Xuemin (Sherman) Shen

• Publisher: Springer
• Year: 2021
• Tongue: English
• Leaves: 175
• Edition: 1st ed. 2021
• Category: Library

✦ Synopsis

This book introduces the Internet access for vehicles as well as novel communication and computing paradigms based on the Internet of vehicles. 

To enable efficient and reliable Internet connection for mobile vehicle users, this book first introduces analytical modelling methods for the practical vehicle-to-roadside (V2R) Internet access procedure, and employ the interworking of V2R and vehicle-to-vehicle (V2V) to improve the network performance for a variety of automotive applications. 

In addition, the wireless link performance between a vehicle and an Internet access station is investigated, and a machine learning based algorithm is proposed to improve the link throughout by selecting an efficient modulation and coding scheme.

This book also investigates the distributed machine learning algorithms over the Internet access of vehicles. A novel broadcasting scheme is designed to intelligently adjust the training users that are involved in the iteration rounds for an asynchronous federated learning scheme, which is shown to greatly improve the training efficiency. This book conducts the fully asynchronous machine learning evaluations among vehicle users that can utilize the opportunistic V2R communication to train machine learning models. 

Researchers and advanced-level students who focus on vehicular networks, industrial entities for internet of vehicles providers, government agencies target on transportation system and road management will find this book useful as reference. Network device manufacturers and network operators will also want to purchase this book. 

✦ Table of Contents

Preface
Contents
Acronyms
1 Introduction of Internet Access of Vehicular Networks
1.1 Internet of Vehicles Overview
1.1.1 DSRC
1.1.2 ISM Band WiFi with Opportunistic Access
1.1.3 TVWS with Cognitive Spectrum Access
1.1.4 Cellular IoV
1.1.5 Summary
1.2 Internet Access Procedure
1.2.1 Network Detection
1.2.2 Authentication
1.2.3 Network Parameters Assignment
1.2.4 Summary
1.3 Aim of the Book
References
2 Internet Access Modeling for Vehicular Connection
2.1 Background and Motivation
2.2 Delay Analysis of Vehicular Internet Access
2.2.1 System Model
2.2.2 Access Delay Analysis
2.2.3 Delay Analysis and Simulation
2.2.4 Experiment
2.2.5 Summary
2.3 Throughput Capacity Analysis of Drive-Thru Internet
2.3.1 System Model
2.3.2 3D Markov Chain Based Throughput Analysis
2.3.2.1 Dimension of Back Off Procedure
2.3.2.2 Dimension of Management Frame Delivery Sequence
2.3.2.3 Dimension of Zone Transition: Embedding 3D Markov Chain
2.3.3 Simulation Results
2.3.4 Summary
References
3 V2X Interworking via Vehicular Internet Access
3.1 Background and Motivation
3.2 Queueing Model for Opportunistic V2V Assistance
3.2.1 System Model
3.2.1.1 Network Model
3.2.2 Queueing Model
3.2.3 Queueing Analysis About V2V Communication
3.2.3.1 L.T. Method for Effective Service Time
3.2.3.2 SOR Type
3.2.3.3 PDF of Effective Service Time
3.2.3.4 M/G/1/K Queue Solution
3.2.4 Simulation and Discussion
3.2.5 Summary
3.3 Vehicular Offloading via V2X Interworking
3.3.1 System Model
3.3.1.1 Network Model
3.3.1.2 Vehicle Mobility Model
3.3.1.3 Internet Access Procedure
3.3.1.4 WiFi Offloading Queue Model
3.3.1.5 V2V Assistance Model
3.3.2 Offloading Performance Analysis
3.3.3 Access Delay Approximation
3.3.3.1 Effective Service Time Derivation
3.3.3.2 WiFi Queue Solution
3.3.4 V2V Assistance Analysis
3.3.4.1 Offloading Ratio Calculation
3.3.5 Simulation and Verification
3.3.6 Summary
References
4 Intelligent Link Management for Vehicular Internet Access
4.1 Background and Motivation
4.2 Reinforcement Learning Based Link Adaptation for Drive-Thru Internet
4.2.1 System Model and Problem Formulation
4.2.1.1 Network Model
4.2.1.2 RA Model
4.2.2 Problem Formulation
4.2.2.1 Inputs
4.2.2.2 RA Timeline
4.2.2.3 Performance Metric
4.2.3 RL Based RA Design
4.2.3.1 Network Context Map to RL
4.2.3.2 Learning Structure
4.2.3.3 Testing Procedure
4.2.4 Performance Evaluation and Discussion
4.2.5 Experiment Setup
4.2.5.1 Channel Parameters
4.2.5.2 Medium Access Trace
4.2.6 Performance Evaluation
4.2.6.1 Drive-Thru Internet Performance
4.2.6.2 Model Generalization
4.2.7 Feasibility Analysis
4.2.7.1 Product Compatibility
4.2.7.2 RL Implementation
4.2.8 Summary
4.3 Deep Learning Classifier Enabled Rate Adaptation for 802.11af TVWS Vehicular Internet Access
4.3.1 System Model
4.3.1.1 Vehicle Mobility Model
4.3.1.2 Channel Model
4.3.1.3 RA Model
4.3.2 Problem Formulation and DL Solution
4.3.2.1 Requisitions
4.3.2.2 Assumptions
4.3.2.3 Objective
4.3.3 Evaluation of the TSC for TVWS RA
4.3.4 Performance Evaluation
4.3.4.1 Classification Accuracy
4.3.4.2 Throughput
4.3.5 Summary
4.4 Autonomous Rate Control for More Categories of Vehicles
4.4.1 System Model
4.4.1.1 Network Model
4.4.1.2 Mobility Model
4.4.1.3 Rate Profile
4.4.2 Problem Formulation and DRL Based RC
4.4.2.1 Problem Objective
4.4.2.2 DQL Based RC Algorithm
4.4.3 Performance Evaluation
4.4.3.1 Experiment Setup
4.4.3.2 Performance
4.4.4 Summary
4.5 Intelligent Rate Control for Internet of Maritime Vehicles
4.5.1 Related Works
4.5.1.1 TVWS Access for MIoT
4.5.1.2 MCS Selection Schemes
4.5.1.3 NARXNN Forecaster
4.5.2 System Model
4.5.2.1 Network Model
4.5.2.2 MCS Profile
4.5.3 Proactive NARXNN Forecaster Based MCS Selection
4.5.4 Performance Evaluation
4.5.4.1 Channel SNR Prediction
4.5.4.2 Lag Order Impact
4.5.4.3 NN Size Selection
4.5.4.4 ACU Performance
4.5.4.5 Resistance to Trajectory Deviation
4.5.4.6 Impact of Trace Set Size X
4.5.5 Summary
References
5 Intelligent Networking enabled Vehicular Distributed Learning
5.1 Background and Motivation
5.2 Rateless Coding Enabled Broadcasting for Vehicular Federated Learning
5.2.1 System Model
5.2.2 BAP for Vehicular Cooperative Learning
5.2.3 Convergence Analysis
5.2.4 Performance Evaluation
5.2.5 Summary
5.3 Opportunistic Collaborated Learning Over Intelligent Internet of Vehicles
5.3.1 System Model
5.3.2 Opportunistic Collaborated Learning via V2R Interaction
5.3.3 Convergence Analysis
5.3.4 Summary
References
6 Conclusions and Future Workers
6.1 Conclusions
6.2 Future Directions