Zhu Han

This book explores the integration of Mean Field Game (MFG) theory with machine learning (ML), presenting both theoretical foundations and practical applications. Drawing from extensive research, it provides insights into how MFG can improve various ML techniques, including supervised learning, reinforcement learning, and federated learning. MFG theory and ML are converging to address critical challenges in high-dimensional spaces and multi-agent systems. While ML has transformed industries by leveraging vast data and computational power, scalability and robustness remain key concerns. MFG theory, which models large populations of interacting agents, offers a mathematical framework to simplify and optimize complex systems, enhancing ML’s efficiency and applicability. By bridging these two fields, this book aims to drive innovation in scalable and robust machine learning. The integration of MFG with ML not only expands research possibilities but also paves the way for more adaptive and intelligent systems. Through this work, the authors hope to inspire further exploration and development in this promising interdisciplinary domain. With case studies and real-world examples, this book serves as a guide for researchers and students in communications and networks seeking to harness MFG’s potential in advancing ML. Industry managers, practitioners and government research workers in the fields of communications and networks will find this book a valuable resource as well.

This book covers the basic theory of mean field game (MFG) and its applications in wireless networks. It starts with an overview of the current and future state-of-the-art in 5G and 6G wireless networks. Then, a tutorial is presented for MFG, mean-field-type game (MFTG), and prerequisite fields of study such as optimal control theory and differential games. This book also includes a literature survey of MFG-based research in wireless network technologies such as ultra-dense networks (UDNs), device-to-device (D2D) communications, internet-of-things (IoT), unmanned aerial vehicles (UAVs), and mobile edge networks (MENs). Several applications of MFG and MFTG in UDNs, social networks, and multi-access edge computing networks (MECNs) are introduced as well.Applications of MFG covered in this book are divided in three parts. The first part covers three single-population MFG research works or case studies in UDNs including ultra-dense D2D networks, ultra-dense UAV networks, and dense-user MECNs. The second part centers on a multiple-population MFG (MPMFG) modeling of belief and opinion evolution in social networks. It focuses on a recently developed MPMFG framework and its application in analyzing the behavior of users in a multiple-population social network. Finally, the last part concentrates on an MFTG approach to computation offloading in MECN. The computation offloading algorithms are designed for energy- and time-efficient offloading of computation-intensive tasks in an MECN. This book targets advanced-level students, professors, researchers, scientists, and engineers in the fields of communications and networks. Industry managers and government employees working in these same fields will also find this book useful.

This book covers the basic theory of mean field game (MFG) and its applications in wireless networks. It starts with an overview of the current and future state-of-the-art in 5G and 6G wireless networks. Then, a tutorial is presented for MFG, mean-field-type game (MFTG), and prerequisite fields of study such as optimal control theory and differential games. This book also includes a literature survey of MFG-based research in wireless network technologies such as ultra-dense networks (UDNs), device-to-device (D2D) communications, internet-of-things (IoT), unmanned aerial vehicles (UAVs), and mobile edge networks (MENs). Several applications of MFG and MFTG in UDNs, social networks, and multi-access edge computing networks (MECNs) are introduced as well.Applications of MFG covered in this book are divided in three parts. The first part covers three single-population MFG research works or case studies in UDNs including ultra-dense D2D networks, ultra-dense UAV networks, and dense-user MECNs. The second part centers on a multiple-population MFG (MPMFG) modeling of belief and opinion evolution in social networks. It focuses on a recently developed MPMFG framework and its application in analyzing the behavior of users in a multiple-population social network. Finally, the last part concentrates on an MFTG approach to computation offloading in MECN. The computation offloading algorithms are designed for energy- and time-efficient offloading of computation-intensive tasks in an MECN. This book targets advanced-level students, professors, researchers, scientists, and engineers in the fields of communications and networks. Industry managers and government employees working in these same fields will also find this book useful.

This book presents a comprehensive introduction to well logging and the inverse problem. It explores challenges such as conventional data processing methods’ inability to handle local minima issues, and presents the explanations in an easy-to-follow way. The book describes statistical data interpretation by introducing the fundamentals behind the approach, as well as a range of sampling methods. In each chapter, a specific method is comprehensively introduced, together with representative examples. The book begins with basic information on well logging and logging while drilling, as well as a definition of the inverse problem. It then moves on to discuss the fundamentals of statistical inverse methods, Bayesian inference, and a new sampling method that can be used to supplement it, the hybrid Monte Carlo method. The book then addresses a specific problem in the inversion of downhole logging data, and the interpretation of earth model complexity, before concluding with a meta-technique called the tempering method, which serves as a supplement to statistical sampling methods. Given its scope, the book offers a valuable reference guide for drilling engineers, well logging tool physicists, and geoscientists, as well as students in the areas of petroleum engineering and electrical engineering.

This unique text helps make sense of big data in engineering applications using tools and techniques from signal processing. It presents fundamental signal processing theories and software implementations, reviews current research trends and challenges, and describes the techniques used for analysis, design and optimization. Readers will learn about key theoretical issues such as data modelling and representation, scalable and low-complexity information processing and optimization, tensor and sublinear algorithms, and deep learning and software architecture, and their application to a wide range of engineering scenarios. Applications discussed in detail include wireless networking, smart grid systems, and sensor networks and cloud computing. This is the ideal text for researchers and practising engineers wanting to solve practical problems involving large amounts of data, and for students looking to grasp the fundamentals of big data analytics.

The brief focuses on applying sublinear algorithms to manage critical big data challenges. The text offers an essential introduction to sublinear algorithms, explaining why they are vital to large scale data systems. It also demonstrates how to apply sublinear algorithms to three familiar big data applications: wireless sensor networks, big data processing in Map Reduce and smart grids. These applications present common experiences, bridging the theoretical advances of sublinear algorithms and the application domain. Sublinear Algorithms for Big Data Applications is suitable for researchers, engineers and graduate students in the computer science, communications and signal processing communities.

The book offers a succinct overview of the technical components of blockchain networks, also known as distributed digital ledger networks. Written from an academic perspective, it surveys ongoing research challenges as well as existing literature. Several chapters illustrate how the mathematical tools of game theory and algorithmic mechanism design can be applied to the analysis, design, and improvement of blockchain network protocols. Using an engineering perspective, insights are provided into how the economic interests of different types of participants shape the behaviors of blockchain systems. Readers are thus provided with a paradigm for developing blockchain consensus protocols and distributed economic mechanisms that regulate the interactions of system participants, thus leading to desired cooperative behaviors in the form of system equilibria. This book will be a vital resource for students and scholars of this budding field.

This book provides the state-of-the-art research on aerial communications coexisting with terrestrial networks from physical, MAC, network, and application layer perspectives. It includes thorough discussion of control issues, access techniques and resource sharing between cellular communication and aerial communications to accommodate larger volumes of traffic and to provide better service to users. Other challenges are explored in this text are: identification of services, radio resource allocation and resource management for aerial links, self-organizing aerial networks, aerial offloading, and performance evaluation of aerial communications. This volume will be a highly useful resource for students, researchers and engineers interested in obtaining comprehensive information on the design, evaluation, and applications of aerial access networks and communications.

Recently machine learning schemes have attained significant attention as key enablers for next-generation wireless systems. Currently, wireless systems are mostly using machine learning schemes that are based on centralizing the training and inference processes by migrating the end-devices data to a third party centralized location. However, these schemes lead to end-devices privacy leakage. To address these issues, one can use a distributed machine learning at network edge. In this context, federated learning (FL) is one of most important distributed learning algorithm, allowing devices to train a shared machine learning model while keeping data locally. However, applying FL in wireless networks and optimizing the performance involves a range of research topics. For example, in FL, training machine learning models require communication between wireless devices and edge servers via wireless links. Therefore, wireless impairments such as uncertainties among wireless channel states, interference, and noise significantly affect the performance of FL. On the other hand, federated-reinforcement learning leverages distributed computation power and data to solve complex optimization problems that arise in various use cases, such as interference alignment, resource management, clustering, and network control. Traditionally, FL makes the assumption that edge devices will unconditionally participate in the tasks when invited, which is not practical in reality due to the cost of model training. As such, building incentive mechanisms is indispensable for FL networks. This book provides a comprehensive overview of FL for wireless networks. It is divided into three main parts: The first part briefly discusses the fundamentals of FL for wireless networks, while the second part comprehensively examines the design and analysis of wireless FL, covering resource optimization, incentive mechanism, security and privacy. It also presents several solutions based on optimizationtheory, graph theory, and game theory to optimize the performance of federated learning in wireless networks. Lastly, the third part describes several applications of FL in wireless networks.

This book presents novel RIS-Based Smart Radio techniques, targeting at achieving high-quality channel links in cellular communications via design and optimization of the RIS construction. Unlike traditional antenna arrays, three unique characteristics of the RIS will be revealed in this book. First, the built-in programmable configuration of the RIS enables analog beamforming inherently without extra hardware or signal processing. Second, the incident signals can be controlled to partly reflect and partly transmit through the RIS simultaneously, adding more flexibility to signal transmission. Third, the RIS has no digital processing capability to actively send signals nor any radio frequency (RF) components. As such, it is necessary to develop novel channel estimation and communication protocols, design joint digital and RIS-based analog beamforming schemes and perform interference control via mixed reflection and transmission. This book also investigates how to integrate the RIS to legacy communication systems. RIS techniques are further investigated in this book (benefited from its ability to actively shape the propagation environment) to achieve two types of wireless applications, i.e., RF sensing and localization. The influence of the sensing objectives on the wireless signal propagation can be potentially recognized by the receivers, which are then utilized to identify the objectives in RF sensing. Unlike traditional sensing techniques, RIS-aided sensing can actively customize the wireless channels and generate a favorable massive number of independent paths interacting with the sensing objectives. It is desirable to design RIS-based sensing algorithms, and optimize RIS configurations. For the second application, i.e., RIS aided localization, an RIS is deployed between the access point (AP) and users. The AP can then analyze reflected signals from users via different RIS configurations to obtain accurate locations of users. However, this is a challenging task due to the dynamic user topology, as well as the mutual influence between multiple users and the RIS. Therefore, the operations of the RIS, the AP, and multiple users need to be carefully coordinated. A new RIS-based localization protocol for device cooperation and an RIS configuration optimization algorithm are also required. This book targets researchers and graduate-level students focusing on communications and networks. Signal processing engineers, computer and information scientists, applied mathematicians and statisticians, who work in RIS research and development will also find this book useful.

Recently machine learning schemes have attained significant attention as key enablers for next-generation wireless systems. Currently, wireless systems are mostly using machine learning schemes that are based on centralizing the training and inference processes by migrating the end-devices data to a third party centralized location. However, these schemes lead to end-devices privacy leakage. To address these issues, one can use a distributed machine learning at network edge. In this context, federated learning (FL) is one of most important distributed learning algorithm, allowing devices to train a shared machine learning model while keeping data locally. However, applying FL in wireless networks and optimizing the performance involves a range of research topics. For example, in FL, training machine learning models require communication between wireless devices and edge servers via wireless links. Therefore, wireless impairments such as uncertainties among wireless channel states, interference, and noise significantly affect the performance of FL. On the other hand, federated-reinforcement learning leverages distributed computation power and data to solve complex optimization problems that arise in various use cases, such as interference alignment, resource management, clustering, and network control. Traditionally, FL makes the assumption that edge devices will unconditionally participate in the tasks when invited, which is not practical in reality due to the cost of model training. As such, building incentive mechanisms is indispensable for FL networks. This book provides a comprehensive overview of FL for wireless networks. It is divided into three main parts: The first part briefly discusses the fundamentals of FL for wireless networks, while the second part comprehensively examines the design and analysis of wireless FL, covering resource optimization, incentive mechanism, security and privacy. It also presents several solutions based on optimizationtheory, graph theory, and game theory to optimize the performance of federated learning in wireless networks. Lastly, the third part describes several applications of FL in wireless networks.

This book presents novel RIS-Based Smart Radio techniques, targeting at achieving high-quality channel links in cellular communications via design and optimization of the RIS construction. Unlike traditional antenna arrays, three unique characteristics of the RIS will be revealed in this book. First, the built-in programmable configuration of the RIS enables analog beamforming inherently without extra hardware or signal processing. Second, the incident signals can be controlled to partly reflect and partly transmit through the RIS simultaneously, adding more flexibility to signal transmission. Third, the RIS has no digital processing capability to actively send signals nor any radio frequency (RF) components. As such, it is necessary to develop novel channel estimation and communication protocols, design joint digital and RIS-based analog beamforming schemes and perform interference control via mixed reflection and transmission. This book also investigates how to integrate the RIS to legacy communication systems. RIS techniques are further investigated in this book (benefited from its ability to actively shape the propagation environment) to achieve two types of wireless applications, i.e., RF sensing and localization. The influence of the sensing objectives on the wireless signal propagation can be potentially recognized by the receivers, which are then utilized to identify the objectives in RF sensing. Unlike traditional sensing techniques, RIS-aided sensing can actively customize the wireless channels and generate a favorable massive number of independent paths interacting with the sensing objectives. It is desirable to design RIS-based sensing algorithms, and optimize RIS configurations. For the second application, i.e., RIS aided localization, an RIS is deployed between the access point (AP) and users. The AP can then analyze reflected signals from users via different RIS configurations to obtain accurate locations of users. However, this is a challenging task due to the dynamic user topology, as well as the mutual influence between multiple users and the RIS. Therefore, the operations of the RIS, the AP, and multiple users need to be carefully coordinated. A new RIS-based localization protocol for device cooperation and an RIS configuration optimization algorithm are also required. This book targets researchers and graduate-level students focusing on communications and networks. Signal processing engineers, computer and information scientists, applied mathematicians and statisticians, who work in RIS research and development will also find this book useful.

This book discusses how to plan the time-variant placements of the UAVs served as base station (BS)/relay, which is very challenging due to the complicated 3D propagation environments, as well as many other practical constraints such as power and flying speed. Spectrum sharing with existing cellular networks is also investigated in this book. The emerging unmanned aerial vehicles (UAVs) have been playing an increasing role in the military, public, and civil applications. To seamlessly integrate UAVs into future cellular networks, this book will cover two main scenarios of UAV applications as follows. The first type of applications can be referred to as UAV Assisted Cellular Communications.Second type of application is to exploit UAVs for sensing purposes, such as smart agriculture, security monitoring, and traffic surveillance. Due to the limited computation capability of UAVs, the real-time sensory data needs to be transmitted to the BS for real-time data processing. The cellular networks are necessarily committed to support the data transmission for UAVs, which the authors refer to as Cellular assisted UAV Sensing. To support real-time sensing streaming, the authors design joint sensing and communication protocols, develop novel beamforming and estimation algorithms, and study efficient distributed resource optimization methods.This book targets signal processing engineers, computer and information scientists, applied mathematicians and statisticians, as well as systems engineers to carve out the role that analytical and experimental engineering has to play in UAV research and development. Undergraduate students, industry managers, government research agency workers and general readers interested in the fields of communications and networks will also want to read this book.

Do you have the tools to address recent challenges and problems in modern computer networks? Discover a unified view of auction theoretic applications and develop auction models, solution concepts, and algorithms with this multidisciplinary review. Devise distributed, dynamic, and adaptive algorithms for ensuring robust network operation over time-varying and heterogeneous environments, and for optimizing decisions about services, resource allocation, and usage of all network entities. Topics including cloud networking models, MIMO, mmWave communications, 5G, data aggregation, task allocation, user association, interference management, wireless caching, mobile data offloading, and security. Introducing fundamental concepts from an engineering perspective and describing a wide range of state-of-the-art techniques, this is an excellent resource for graduate and senior undergraduate students, network and software engineers, economists, and researchers.

This book discusses how to plan the time-variant placements of the UAVs served as base station (BS)/relay, which is very challenging due to the complicated 3D propagation environments, as well as many other practical constraints such as power and flying speed. Spectrum sharing with existing cellular networks is also investigated in this book. The emerging unmanned aerial vehicles (UAVs) have been playing an increasing role in the military, public, and civil applications. To seamlessly integrate UAVs into future cellular networks, this book will cover two main scenarios of UAV applications as follows. The first type of applications can be referred to as UAV Assisted Cellular Communications.Second type of application is to exploit UAVs for sensing purposes, such as smart agriculture, security monitoring, and traffic surveillance. Due to the limited computation capability of UAVs, the real-time sensory data needs to be transmitted to the BS for real-time data processing. The cellular networks are necessarily committed to support the data transmission for UAVs, which the authors refer to as Cellular assisted UAV Sensing. To support real-time sensing streaming, the authors design joint sensing and communication protocols, develop novel beamforming and estimation algorithms, and study efficient distributed resource optimization methods.This book targets signal processing engineers, computer and information scientists, applied mathematicians and statisticians, as well as systems engineers to carve out the role that analytical and experimental engineering has to play in UAV research and development. Undergraduate students, industry managers, government research agency workers and general readers interested in the fields of communications and networks will also want to read this book.

Discover the very latest game-theoretic approaches for designing, modeling, and optimizing emerging wireless communication networks and systems with this unique text. Providing a unified and comprehensive treatment throughout, it explains basic concepts and theories for designing novel distributed wireless networking mechanisms, describes emerging game-theoretic tools from an engineering perspective, and provides an extensive overview of recent applications. A wealth of new tools is covered - including matching theory and games with bounded rationality - and tutorial chapters show how to use these tools to solve current and future wireless networking problems in areas such as 5G networks, network virtualization, software defined networks, cloud computing, the Internet of Things, context-aware networks, green communications, and security. This is an ideal resource for telecommunications engineers, and researchers in industry and academia who are working on the design of efficient, scalable, and robust communication protocols for future wireless networks, as well as graduate students in these fields.

This SpringerBrief mainly focuses on effective big data analytics for CPS, and addresses the privacy issues that arise on various CPS applications. The authors develop a series of privacy preserving data analytic and processing methodologies through data driven optimization based on applied cryptographic techniques and differential privacy in this brief. This brief also focuses on effectively integrating the data analysis and data privacy preservation techniques to provide the most desirable solutions for the state-of-the-art CPS with various application-specific requirements. Cyber-physical systems (CPS) are the “next generation of engineered systems,” that integrate computation and networking capabilities to monitor and control entities in the physical world. Multiple domains of CPS typically collect huge amounts of data and rely on it for decision making, where the data may include individual or sensitive information, for e.g., smart metering, intelligent transportation, healthcare, sensor/data aggregation, crowd sensing etc. This brief assists users working in these areas and contributes to the literature by addressing data privacy concerns during collection, computation or big data analysis in these large scale systems. Data breaches result in undesirable loss of privacy for the participants and for the entire system, therefore identifying the vulnerabilities and developing tools to mitigate such concerns is crucial to build high confidence CPS.This Springerbrief targets professors, professionals and research scientists working in Wireless Communications, Networking, Cyber-Physical Systems and Data Science. Undergraduate and graduate-level students interested in Privacy Preservation of state-of-the-art Wireless Networks and Cyber-Physical Systems will use this Springerbrief as a study guide.

This book provides the fundamental knowledge of the classical matching theory problems. The potentials and challenges of implementing the semi-distributive matching theory framework into the wireless resource allocations are analyzed both theoretically and through implementation examples.

This book presents theoretical research between wireless communications, networking, and economics using the framework of contract theory. This work fills a void in the literature by closely combining contract theoretical approaches with wireless networks design problems. Topics covered include classification in contract theory, reward design, adverse selection, and moral hazard. The authors also explore incentive mechanisms for device-to-device communication in cellular networks, insurance plans for service assurance in cloud computing markets with incomplete information, multi-dimensional incentive mechanisms and tournament based incentive mechanisms in mobile crowdsourcing. Financial applications include financing contracts with adverse selection for spectrum trading in cognitive radio networks and complementary investment of infrastructure and service providers in wireless network visualization. This book offers a useful reference for engineers and researchers in the wireless communication community who seek to integrate the notions from contract theory and wireless engineering, while emphasizing on how contract theory can be applied in wireless networks. It is also suitable for advanced-level students studying information systems or communications engineering.

This SpringerBrief investigates cross layer resource allocation in unlicensed LTE (Long Term Evolution) HetNets. Specifically, the authors study and cover the radio access management of unlicensed LTE to allow efficient spectrum utilization and harmonious coexistence with other unlicensed systems in this brief. Efficient radio access protocols are developed to allow unlicensed LTE users to fair share channel access with unlicensed users in different systems, including Wi-Fi and unlicensed LTE of other operators. An analytical model is developed to study the performance of the proposed protocols. To achieve efficient spectrum sharing among various unlicensed users, the authors further formulate a resource allocation problem based on Nobel Prize winning game theory framework, and propose efficient algorithms to achieve the maximal user utility. Opportunistic traffic offloading from licensed band to unlicensed bands is also investigated, based on the network formation game. By exploiting the characteristics of mobile social networks, the offloading performance can be further enhanced. This brief targets researchers and engineers from both academia and industry interested in the development of LTE over unlicensed bands, as well as the design and implementation of cross layer radio resource management. Students studying electrical engineering and computer science will also find this brief useful for their studies.