
Generative AI for Communications Systems
Description
Alles über E-Books | Antworten auf Fragen rund um E-Books, Kopierschutz und Dateiformate finden Sie in unserem Info- & Hilfebereich.
Comprehensive review of state-of-the-art research and development in Generative AI for future communications and networking
Generative AI for Communications Systems provides a systematic foundation of knowledge on Generative AI for communications and networking. This book discusses the great potential and challenges in applying Generative AI as promising solutions to future communications systems and enables and facilitates "Generative AI as a Service" by exploring novel communications, networking architectures, protocols, and research trends.
The book also includes information on:
- Crucial challenges to solve in Generative AI, such as training data availability, computational complexity, generalization for various scenarios, robustness of noisy and incomplete data, and real-time adaptation in communications and networking systems
- Cybersecurity concerns such as ethics and privacy in relation to Generative AI
- Applications of Generative AI across various layers, including the PHY layer, MAC layer, Network layer, and Application layer
- Communications and networking solutions to meet the computing and communications challenges and demands to train and deploy large-scale Generative AI models
Generative AI for Communications Systems is an excellent up-to-date resource on the subject for scholars and researchers in the fields of communications, artificial intelligence, machine learning, and network optimization as well as professionals working in the communications industry including engineers, network architects, and system designers.
More details
Other editions
Additional editions

Persons
Diep N. Nguyen is the Head of UTS 5G/6G Lab with the Faculty of Engineering and Information Technology at the University of Technology Sydney (UTS), Sydney, NSW, Australia.
Nam H. Chu is a Faculty Member with the Department of Telecommunications Engineering at the University of Transport and Communications, Hanoi, Vietnam. He is also with the University of Technology Sydney (UTS), Australia, and the Crown Institute of Higher Education, Australia.
Dinh Thai Hoang is a Faculty Member at the University of Technology Sydney (UTS), Australia.
Octavia A. Dobre is a Professor and Canada Research Chair Tier-1 at Memorial University, Canada.
Dusit Niyato is a President's Chair Professor in Computer Science and Engineering in the College of Computing and Data Science at Nanyang Technological University, Singapore.
Petar Popovski is currently a Professor with Aalborg University in Denmark where he heads the Section on Connectivity. He is also a Visiting Excellence Chair with the University of Bremen, Germany.
Content
List of Contributors xiii
Preface xxiii
Acronyms xxix
1 Future AI-empowered Communications Systems 1
Nguyen Van Huynh, Thien Huynh-The, and Quoc-Viet Pham
1.1 Fundamental Background of Future Communications Systems 1
1.1.1 Overview of Future Communications Systems 1
1.1.2 Key Challenges and Research Trends 7
1.2 AI-powered Communication Enablers 10
1.2.1 Deep Learning-based Approaches 10
1.2.2 Reinforcement Learning-based Approaches 17
1.2.3 Federated/Distributed Learning-based Approaches 24
1.2.4 Existing Challenges 28
1.2.5 Potential of Generative AI 28
1.3 Conclusion 30
References 30
2 Generative AI Background and Its Potentials for Future Communications Systems 39
Asmaa Abdallah, Abdulkadir Celik, and Ahmed M. Eltawil
2.1 Introduction 39
2.2 A Taxonomy of Generative Models 40
2.2.1 Explicit Density Models 41
2.2.2 Implicit Density Models 41
2.2.3 Ways GenAI Complements Discriminative AI 42
2.3 Prominent Generative Models 42
2.3.1 Generative Adversarial Networks 42
2.3.2 Variational Autoencoders 44
2.3.3 Flow-based Generative Models 47
2.3.4 Diffusion-based Generative Models 49
2.3.5 The Trilemma of GMs 51
2.3.6 Generative Autoregressive Models 52
2.3.7 Generative Transformers and LLMs 54
2.3.8 Strategies to Address LLM Limitations 59
2.4 GenAI Applications to Canonical Problems in Communications Systems 63
2.4.1 Physical Layer Design 63
2.4.2 Network Resource Management 64
2.4.3 Network Traffic Analytics 65
2.4.4 Cross-layer Network Security 65
2.4.5 Localization and Positioning 66
2.5 Future Communication Frontiers for GMs 66
2.5.1 Semantic Communications 66
2.5.2 Integrated Sensing and Communications 67
2.5.3 Digital Twins 68
2.5.4 AI-generated Content for 6G Networks 69
2.5.5 MEC and EAI 69
2.5.6 Adversarial Machine Learning and Trustworthy AI 70
2.6 Regulation and Policy 71
2.7 Summary 71
References 72
3 Key Study Cases of Generative AI Applications to Communications Systems 79
Mehdi Letafati, Samad Ali, and Matti Latva-aho
3.1 Overview on the Roles of Generative AI in Communication Systems 79
3.1.1 Use Cases of Generative Adversarial Networks in Communications 79
3.1.2 Use cases of VAEs in Communications 81
3.1.3 Use-cases of Diffusion Models in Communications 82
3.2 Case Study: Diffusion Models in Wireless Communications 83
3.2.1 Working Mechanism of Diffusion Models 83
3.2.2 Case Study: Diffusion Models Applications for Data Reconstruction Enhancement in Communication Systems 89
3.3 Future Implications and Potential Impacts on Communication Systems 98
3.4 Chapter Summary 99
References 99
4 Generative AI at PHY Layer: Native AI or Trainable Radios 105
Eren Balevi
4.1 Wireless Communications Empowered with Generative Models 105
4.1.1 Motivations of GenAI at the PHY 105
4.1.2 Applications of GenAI at the PHY 106
4.2 Channel Modeling 110
4.2.1 Generative Channel Modeling 111
4.2.2 Site-specific Generative Models 115
4.3 Generative Channel Estimation 116
4.3.1 Narrowband Channel Estimation with Reduced Pilots 120
4.3.2 Wideband Channel Estimation with Reduced Pilots 122
4.4 Channel Compression 123
4.5 Beamforming 125
4.6 Summary 129
References 129
5 Generative AI at the MAC Layer 133
Kemal Davaslioglu, Ender Ayanoglu, and Yalin E. Sagduyu
5.1 Introduction 133
5.2 Generative Models 137
5.2.1 Variational Autoencoders 139
5.2.2 Generative Adversarial Networks 140
5.2.3 Diffusion Models 141
5.3 Spectrum Awareness Applications 142
5.3.1 Data Augmentation and Synthetic Data Generation 143
5.3.2 Signal Classification Applications - UAV Classification 147
5.3.3 Anomaly Detection in RF Spectrum 148
5.4 RF Spectrum Security Applications 149
5.4.1 Emitter Identification 149
5.4.2 Wireless Spoofing 151
5.4.3 Enhanced Jamming Attacks 152
5.5 Scheduling Applications 153
5.5.1 Traffic Prediction and Pattern Generation 153
5.5.2 Adaptive Scheduling Algorithms 154
5.5.3 Interference Patterns 154
5.5.4 Fairness and QoS 154
5.5.5 Millimeter-wave Networks 155
5.6 Open Problems and Future Research Directions 155
5.6.1 Reconfigurable Intelligent Surface (RIS)-assisted Networks 156
5.6.2 Spectrum Sharing in the Presence of Interference 157
5.6.3 Integrated Sensing and Communications (ISAC) 159
5.6.4 Link Scheduling in Large Networks 160
5.6.5 Enhancing Wireless MAC-layer Security 160
5.7 Concluding Remarks 162
References 162
6 Generative AI at Network Layer 169
Athanasios Karapantelakis, Pegah Alizadeh, Abdulrahman Alabbasi, Kaushik Dey, and Alexandros Nikou
6.1 Introduction 169
6.2 Network Layer in Mobile Networks 172
6.2.1 Radio Access Network 172
6.2.2 Core Network 175
6.3 Generative AI in the Network Layer 177
6.3.1 Introduction 177
6.3.2 Advantages of GenAI Models 177
6.3.3 Short-term Applications (GenAI for Network Layer) 180
6.3.4 Long-term Applications (Network Layer for GenAI) 184
6.4 Challenges and Opportunities for GenAI in the Network Layer 185
6.4.1 Challenges 185
6.4.2 Research Opportunities 186
6.5 Summary 187
References 187
7 Generative AI at Application Layer: Mobile AI-generated Content 191
Paria Mohammadzadeh Hesar, Amirhossein Mohammadi, and Hina Tabassum
7.1 Introduction to AIGC 191
7.1.1 General Overview 191
7.1.2 AIGC in the Application Layer 192
7.1.3 AIGC Product Lifecycle 194
7.2 Collaborative Network Infrastructure for Enabling GenAI Services 196
7.2.1 Enabling AIGC - Challenges 196
7.2.2 Infrastructure Components and Capabilities 198
7.2.3 Collaborative Edge-cloud Infrastructure 201
7.3 Network Resource Efficient GenAI Methods 203
7.3.1 Model Optimization Techniques 203
7.3.2 Service Optimization Methods 206
7.4 Security and Privacy at Application Layer 208
7.4.1 Security Threat Models and Privacy Risks 209
7.4.2 Ethical Considerations in AIGC services 211
7.4.3 Enabling Secure AIGC-as-a-Service 212
7.5 Use Cases of Mobile AIGC 213
7.5.1 AI-generated Content in Social Media 213
7.5.2 Immersive Streaming (AR/VR) 215
7.5.3 Personalized AI Services 219
7.6 Conclusion and Research Directions 222
7.7 Summary 223
References 224
8 Applications of GenAI on Wireless and Cybersecurity 239
Brian Kim, Yalin E. Sagduyu, Tugba Erpek, Yi Shi, and Sennur Ulukus
8.1 Introduction to GenAI in Wireless and Cybersecurity 239
8.2 Adversarial Machine Learning in Wireless Communications 242
8.2.1 Different Types of Attacks Against GenAI-driven Wireless Applications 243
8.2.2 Defense Against Adversarial Attacks for GenAI-driven Wireless Applications 245
8.3 GenAI for Wireless Security and Cybersecurity 245
8.3.1 GenAI for Wireless Security 245
8.3.2 GenAI for Cybersecurity 248
8.3.3 GenAI-driven Attacks Against Wireless and Cybersecurity Applications 249
8.4 Ethical Issues Related to GenAI for Wireless Communications and Cybersecurity 251
8.5 Summary 252
References 253
9 Challenges and Opportunities for Generative AI in Wireless Communications and Networking 261
Songyang Zhang and Zhi Ding
9.1 Introduction 261
9.2 Challenges of Applying Generative AI in Wireless Communications 262
9.2.1 Efficiency and Robustness 263
9.2.2 Cost and Complexity 267
9.2.3 Standardization, Regulation, and Policy 269
9.3 Adopting Generative AI in NextG Communications: Case Studies 270
9.3.1 Integration of Generative AI and Physical Communications Models 270
9.3.2 Trustworthy Generative AI for Distributed Wireless Communications 277
9.4 Summary 281
References 281
10 Future Research Directions 285
Nam H. Chu, Diep N. Nguyen, Dinh Thai Hoang, Octavia A. Dobre, Dusit Niyato, and Petar Popovski
10.1 Introduction 285
10.2 Emerging Foundational Research Frontiers 286
10.2.1 Dedicated GenAI Models for Communication Systems 287
10.2.2 Fusion of GenAI and Emerging Technologies 288
10.3 Enhancing Generative AI Models for Wireless Communication Systems 290
10.3.1 Model Optimization and Generalization 290
10.3.2 Energy Efficiency 291
10.3.3 Generative AI for Spectrum Management 292
10.3.4 AI-driven Network Management and Orchestration 293
10.3.5 Security and Privacy Concerns 295
10.4 Practical Case Studies 296
10.4.1 AI-powered Network Optimization by T-Mobile 296
10.4.2 DeepSig's Generative AI for Wireless Communications 297
10.5 Conclusion 297
References 298
Index 305
List of Contributors
Asmaa Abdallah received the Ph.D. degree in electrical engineering from the American University of Beirut, Beirut, Lebanon, in 2020. She is currently a research scientist at King Abdullah University of Science and Technology (KAUST).
Abdulrahman Alabbasi (Abbasi) joined Ericsson in 2018 and working as a master researcher. His focus is on enabling AI in RAN via solidifying a unified effort across Ericsson to address this area. This includes all aspects of AI application for RAN parameters optimization and the innovation of AI-native RAN. He envisions a Telecom future where AI deployment in the network (and UE nodes) enables the realization of the 6G-driven use-cases and corresponding KPIs. Abbasi holds a master's degree in electronics engineering, Tokyo, Japan, and a Ph.D. degree in electrical engineering from KAUST in Saudi Arabia.
Pegah Alizadeh is a senior researcher at Ericsson Research in Paris, specializing in reinforcement learning, generative decision-making, optimization, and large-scale artificial intelligence systems. Her work bridges offline and multi-agent reinforcement learning, decision transformers, and diffusion models, with applications to telecommunications, natural language processing, and autonomous systems. Before joining Ericsson, she was an Assistant Professor at the De Vinci Research Center (Paris), leading work on meta-learning, learning-augmented optimization, and reinforcement learning for sequential decision-making and urban mobility. She holds a Ph.D. in Computer Science from Sorbonne Paris Nord University (LIPN), where she developed methods for planning in Markov Decision Processes with unknown rewards. Author of more than 30 peer-reviewed publications and several patents on AI-driven network management, she focuses on developing robust, adaptive, safe, and explainable learning systems that connect optimization, reasoning, and real-world decision-making.
Samad Ali received the Ph.D. degree in wireless communications engineering from the University of Oulu, Finland. He is currently a Senior Staff Research Specialist at Nokia and an Adjunct Professor (Docent) at the University of Oulu. His main research interests include the applications of AI/ML in wireless communication networks.
Ender Ayanoglu received his Ph.D. degree in electrical engineering from Stanford University in 1986. He was with Bell Laboratories from 1996to 1999. From 1999 to 2002, he was a systems architect with Cisco Systems Inc. Since 2002, he has been a professor in the Department of Electrical Engineering and Computer Science, University of California, Irvine. He was a recipient of the IEEE Communications Society Stephen O. Rice Prize Paper Award in 1995, the IEEE Communications Society Best Tutorial Paper Award in 1997, and the IEEE Communications Society Joseph L. LoCicero Award in 2023. He has been an IEEE Fellow since 1998.
Eren Balevi received the Ph.D. degree in Electrical and Electronics Engineering from Middle East Technical University, Ankara, Turkey, in 2016. He was employed as an Adjunct Professor and Post-doctoral Research Scholar in the Department of Electrical Engineering at the University of South Florida in 2017. He worked as a Post-doctoral Research Scholar in the Department of Electrical and Computer Engineering at The University of Texas at Austin between 2018 and 2020. He also served as an Adjunct Professor for the Fall 2019 semester at the University of Texas at Austin. He started working at the Qualcomm Research Center in 2020. He was an Assistant Professor at the Middle East Technical University between 2021 and 2024. He is now an Editor in the IEEE Transactions on Wireless Communications. His current research interests lie mainly in the intersection between machine learning and communication theory. He is also interested in distributed edge artificial intelligence (AI).
Abdulkadir Celik received the Ph.D. degrees in electrical engineering and computer engineering (double major) from Iowa State University, Ames, IA, USA, in 2016. He is currently an Associate Professor at the University of Sharjah.
Nam H. Chu received the B.E. degree in electronics and telecommunications engineering from Hanoi University of Science and Technology, Hanoi, Vietnam, in 2009, the master's degree in software engineering from the University of Canberra, Canberra, ACT, Australia, in 2014, and the Ph.D. degree in electrical and computer engineering from the University of Technology Sydney, Sydney, NSW, Australia, in 2023. He is currently with the School of Information Technology, Crown Institute of Higher Education, Australia. He is also with the School of Electrical and Data Engineering, University of Technology Sydney, Australia and the Department of Telecommunications Engineering, University of Transport and Communications, Vietnam. His research interests include applying advanced machine learning and optimization methods for enhancing and securing wireless communications. He was the co-recipient of the Computer Networks 2021 Best Paper Award. He serves as a TPC and reviewer for top venues, such as IEEE JSAC, IEEE TWC, IEEE TMC, IEEE IoTJ, IEEE GLOBECOM, IEEE ICC, and IEEE WCNC.
Kemal Davaslioglu is a principal scientist at Nexcepta Inc., where he leads R&D efforts in wireless communications, wireless networking, radar signal processing, generative AI, and computer vision. He received his Ph.D. degree in electrical and computer engineering from the University of California, Irvine. He previously worked at Broadcom, Intelligent Automation/BlueHalo, and University Technical Services. His research focuses on AI/ML for communications, radar, computer vision, and anomaly detection with emphasis on AI security and robust learning. He is a senior IEEE member and recipient of the IEEE HST Best Paper Award.
Kaushik Dey is a Senior Research Manager at Ericsson Research, leading the AI/ML research unit in India. With more than two decades of experience at Ericsson and IBM, he has worked across AI research and product development, driving innovations in Zero-Touch Networks, multi-agent systems, and energy-efficient AI. His research interests include Reinforcement Learning, Autonomous Agents, and AI-driven communication networks. He holds 20+ international patents and a Ph.D. in Computer Science from Indian Institute of Technology, Kharagpur.
Zhi Ding holds the position of Distinguished Professor in the Department of Electrical and Computer Engineering at the University of California, Davis. He received his Ph.D. degree from Cornell University in 1990. His major research interests cover wireless networking, signal processing, multimedia, and learning. He is a Fellow of IEEE. He served as an Associate Editor for IEEE Trans. Signal Processing from 1994 to 1997 and 2001 to 2004, and for IEEE Signal Processing Letters from 2002 to 2005. He was the General Chair of the 2016 IEEE Int'l. Conf. Acoustics, Speech, and Signal Processing and the Technical Program Chair of the IEEE Globecom 2006. He is a coauthor of the textbook: Modern Digital and Analog Communication Systems, 5th edition, Oxford University Press, 2019. He received the IEEE Communication Society's WTC Award in 2012 and the IEEE Communication Society's Education Award in 2020.
Ahmed M. Eltawil received the Ph.D. degree in electrical engineering from the University of California, Los Angeles, CA, USA, in 2003. He is currently a Full Professor at King Abdullah University of Science and Technology (KAUST).
Tugba Erpek is a Principal Scientist at Nexcepta, Inc. Prior to Nexcepta, Dr. Erpek was a Research Associate Professor with Virginia Tech National Security Institute, Blacksburg; a Lead Scientist and Network Communications Technical Area Lead with the Intelligent Automation, Inc., Rockville, MD, USA; and a Senior Communications Systems Engineer with the Shared Spectrum Company, Vienna, VA, USA. She received the Ph.D. degree in electrical and computer engineering from Virginia Tech, Blacksburg, VA, USA, in 2019. Her research interests include wireless communications and networking, 5G and beyond, dynamic spectrum sharing, cognitive radio, radar systems, IoT, security, machine learning, adversarial machine learning, optimization, network protocol design, and implementation. Dr. Erpek has published extensively in these areas. She has served as a TPC member and reviewer for major IEEE conferences and journals.
Paria Mohammadzadeh Hesar received the B.Sc. degree in Electrical Engineering from Urmia University, Urmia, Iran, in 2015, and the M.Sc. degree in Electrical Engineering (Communication Systems) from the University of Tabriz, Tabriz, Iran, in 2018. She is currently pursuing the Ph.D. degree in Electrical Engineering (Communication Systems) at York University, Toronto, ON, Canada, where she is a Research Assistant with the Next Generation Wireless Networks (NGWN) Lab, supervised by Dr. Hina Tabassum. Her research interests include generative AI for wireless communications, radio-map reconstruction, and electromagnetic field (EMF) exposure modelling in next-generation networks.
Dinh Thai Hoang (M'16, SM'22) is currently a faculty member at the School of Electrical and Data Engineering, University of Technology Sydney, Australia. He received the Ph.D. degree in Computer Science and Engineering from Nanyang Technological University, Singapore, in 2016. His research interests include emerging wireless communications and networking topics, especially machine learning applications in networking, edge computing, and cybersecurity. He has received several prestigious awards, including the Australian Research Council Discovery...
System requirements
File format: ePUB
Copy protection: Adobe-DRM (Digital Rights Management)
System requirements:
- Computer (Windows; MacOS X; Linux): Install the free reader Adobe Digital Editions prior to download (see eBook Help).
- Tablet/smartphone (Android; iOS): Install the free app Adobe Digital Editions or the app PocketBook before downloading (see eBook Help).
- E-reader: Bookeen, Kobo, Pocketbook, Sony, Tolino and many more (not Kindle).
The file format ePub works well for novels and non-fiction books – i.e., „flowing” text without complex layout. On an e-reader or smartphone, line and page breaks automatically adjust to fit the small displays.
This eBook uses Adobe-DRM, a „hard” copy protection. If the necessary requirements are not met, unfortunately you will not be able to open the eBook. You will therefore need to prepare your reading hardware before downloading.
Please note: We strongly recommend that you authorise using your personal Adobe ID after installation of any reading software.
For more information, see our ebook Help page.