Machine Learning for Mobile Communications

✍ Scribed by Sinh Cong Lam & Chiranji Lal Chowdhary & Tushar Hrishikesh Jaware & Subrata Chowdhury

• Publisher: CRC Press
• Year: 2024
• Tongue: English
• Leaves: 214
• Category: Library

✦ Synopsis

Machine Learning for Mobile Communications will take readers on a journey from basic to advanced knowledge about mobile communications and machine learning. For learners at the basic level, this book volume discusses a wide range of mobile communications topics from the system level, such as system design and optimization, to the user level, such as power control and resource allocation. The authors also review state-of-the-art machine learning, one of the biggest emerging trends in both academia and industry. For learners at the advanced level, this book discusses solutions for long-term problems with future mobile communications such as resource allocation, security, power control, and spectral efficiency. The book brings together some of the top mobile communications and machine learning experts throughout the world, who contributed their knowledge and experience regarding system design and optimization. This book:
Discusses the 5G new radio system design and architecture as specified in 3GPP documents. Highlights the challenges including security and privacy, energy, and spectrum efficiency from the perspective of 5G new radio systems. Identifies both theoretical and practical problems that can occur in mobile communication systems. Covers machine learning techniques such as autoencoder and Q-learning in a comprehensive manner. Explores how to apply machine learning techniques to mobile systems to solve modern problems.
This book is for senior undergraduate and graduate students and academic researchers in the fields of electrical engineering, electronics and communication engineering, and computer engineering.

✦ Table of Contents

Cover
Half Title
Series
Title
Copyright
Contents
Preface
About the Editors
List of Contributors
1 Introduction to 5G New Radio
1.1 Introduction
1.1.1 Background
1.1.2 Expectations for 5G
1.2 Moving Toward a 5G Network
1.2.1 5G Drivers
1.2.2 5G Technologies
1.2.3 MIMO Systems
1.2.4 Comparison of MIMO in 5G vs. 4G
1.2.5 MIMO and 5G
1.2.6 Massive MIMO and 5G
1.2.7 Software-Defined Networking
1.2.8 Multiaccess Edge Computing
1.2.9 Radio Access Networks in 5G
1.2.10 Frequency Bands in 5G
1.3 Frequency Band Advantages and Disadvantages
1.4 Conclusion
2 NR Physical Layer
2.1 Introduction
2.2 The 5G NR Structure
2.2.1 5G NR Numerology
2.2.2 Advantages of the 5G NR Structure
2.2.3 Disadvantages of the 5G NR Structure
2.3 5G NR Techniques
2.3.1 Beamforming
2.3.2 Massive MIMO
2.3.3 Channel Coding
2.4 MmWave Communication
2.4.1 Advantages
2.4.2 Disadvantages
2.5 Air Interface of 5G
2.6 Conclusion
3 NR Layer 2 and Layer 3
3.1 Introduction
3.1.1 Mobile Communication
3.1.2 Fifth-Generation Mobile Communication
3.1.3 Fifth-Generation Mobile Communication Using NR Waves
3.2 NR Band Spectrum
3.2.1 Layers of NR Waves
3.2.2 Structure of L2
3.2.3 Function of L2
3.2.4 Structure of L3
3.2.5 Function of L3
3.3 Security Problems in L2 and L3
3.4 Control Measures
3.4.1 Slicing
3.5 Conclusion
4 4G and 5G NR Core Network Architecture
4.1 Introduction
4.2 The Evolution of the Fourth- and Fifth-Generation Core Networks
4.2.1 Fourth-Generation Communication Systems
4.2.2 Fifth-Generation Communication Systems
4.3 The Architecture of the 4G LTE Core Network
4.4 The 5G LTE Core Network
4.4.1 Network Slicing
4.4.2 How Does Network Slicing Work in 5G?
4.4.3 Network Slicing Benefits
4.4.4 Network Slicing Use Cases
4.5 5G New Radio
4.5.1 A 5G NR Roadmap
4.5.2 5G NR Tasks with High Performance
4.5.3 Merits of 5G NR
4.6 5G Central Network Architecture
4.6.1 Server Authentication
4.6.2 Access and Mobility Management (AMM)
4.6.3 Session Management
4.6.4 User Plane Management
4.6.5 Network Exposure Management
4.6.6 Network Repository Management
4.6.7 Policy Control
4.6.8 Unified Data Management
4.7 Application Functions
4.7.1 The Data Network
4.7.2 5G Core Architecture
4.8 The Future of 5G
5 5G—Further Evolution
5.1 Introduction
5.2 5G Cellular System
5.2.1 Reduced Latency
5.2.2 Enhanced Capacity
5.2.3 Improved Bandwidth
5.2.4 Speed
5.3 Working Technologies
5.4 Global Scenario
5.5 5G Use Cases
5.6 Benefits of 5G
5.7 Limitations of 5G
5.8 5G in IoT
5.8.1 Massive Device Connectivity
5.8.2 Enhanced Coverage and Dependability
5.8.3 Enhanced Security and Privacy
5.8.4 Transformative IoT Applications
5.9 5G and Beyond
5.10 When Can We Expect the Advent of 6G?
5.11 What Is 6G?
5.11.1 Terahertz Frequencies
5.11.2 Holographic Beamforming
5.11.3 AI-Driven Networking
5.11.4 Integrated Satellite Networks
5.11.5 Quantum Communications
5.11.6 Sustainable and Green Networks
6 Security and Privacy
6.1 Physical Security Using Machine Learning
6.2 Attack Prevention/Detection Using ML
6.3 Eavesdropping Detection Using ML
6.3.1 Eavesdropping Methods
6.3.2 ML Approaches
6.4 Channel Contamination in Massive MIMO Using ML
7 Traffic Prediction and Congestion Control Using Regression Models in Machine Learning for Cellular Technology
7.1 Introduction
7.2 Data Transfer in Cellular 5G
7.3 Traffic in 5G
7.4 Congestion in 5G
7.5 Traffic Congestion in 5G
7.6 Regression Models in Machine Learning
7.7 Comparative Study Considerations
7.8 Conclusion
8 Resource Allocation Optimization
8.1 Introduction
8.2 Resource Allocation Using ML
8.2.1 Key Aspects of Resource Allocation in Mobile Communication
8.2.2 ML in Resource Allocation
8.3 Massive MIMO Beamforming Optimization Using ML
8.3.1 Massive MIMO Beamforming
8.3.2 ML Approaches to Optimizing Massive MIMO Beamforming
8.4 Joint Beamforming Using ML
8.4.1 Outline of Joint Beamforming in Mobile Communications
8.4.2 ML in Joint Beamforming
8.5 Adaptive Cell Association and Load Balancing Using ML
8.5.1 Adaptive Cell Association Using ML
8.5.2 Load Balancing Using ML
9 Reciprocated Bayesian-Rnn Classifier-Based Mode Switching and Mobility Management in Mobile Networks
9.1 Introduction
9.2 Problem Statement
9.3 Proposed Work
9.3.1 Mobile Network Initialization
9.3.2 Route Exploration
9.3.3 Mode Switching
9.3.4 Effectiveness Metrics for Assessing Mobile Users
9.3.5 Reciprocated Bayesian-RNN Classifier
9.3.6 Mobility Management
9.4 Performance Analysis
9.4.1 Location Management
9.4.2 Throughput
9.4.3 Routing Efficiency
9.4.4 Latency
9.4.5 Network Utilization
9.4.6 Power Requirement
9.4.7 Security
9.5 Conclusion
10 Mobility Management through Machine Learning
10.1 Introduction
10.1.1 Challenges of 5G
10.1.2 The Role of AI in 5G
10.1.3 Traffic Management in 5G Using AI
10.2 Background
10.2.1 5G in IoT Applications
10.2.2 5G in Industrial Applications
10.2.3 Network Management in 5G
10.3 Case Studies
10.3.1 5G and AI in Manufacturing
10.3.2 5G and AI in the Smart Grid
10.3.3 5G and AI in Mobile Applications
10.4 Security in 5G
10.4.1 Security Issues
10.4.2 The Role of AI in Securing 5G Networks
10.4.3 Defensive Mechanisms for Security Attacks in 5G
10.5 AI Applications for Mobility Management
10.5.1 Applications of 5G Bio-Inspired Computation
10.5.2 The Role of Explainable AI and Federated Learning in 5G Performance Enhancement
10.6 Conclusions
11 Applying Heuristic Methods to the Offloading Problem in Edge Computing
11.1 Introduction
11.2 Related Work
11.3 The Background
11.3.1 Cuckoo Search
11.3.2 Genetic Algorithms
11.3.3 Particle Swarm Optimization
11.3.4 Firefly Algorithm Optimization
11.3.5 Teaching–Learning-Based Optimization
11.4 The Proposed Offloading Scenarios and Numerical Results
11.4.1 Assumptions
11.4.2 Numerical Validation and Comparisons
11.5 Conclusion
11.6 Acknowledgment
12 AR/VR Data Prediction and a Slicing Model for 5G Edge Computing
12.1 Introduction
12.1.1 Literature Survey
12.1.2 Methodology
12.1.3 Implementation
12.2 Conclusion
Index