Song Guo

This book aims at the tiny machine learning (TinyML) software and hardware synergy for edge intelligence applications. This book presents on-device learning techniques covering model-level neural network design, algorithm-level training optimization and hardware-level instruction acceleration.Analyzing the limitations of conventional in-cloud computing would reveal that on-device learning is a promising research direction to meet the requirements of edge intelligence applications. As to the cutting-edge research of TinyML, implementing a high-efficiency learning framework and enabling system-level acceleration is one of the most fundamental issues. This book presents a comprehensive discussion of the latest research progress and provides system-level insights on designing TinyML frameworks, including neural network design, training algorithm optimization and domain-specific hardware acceleration. It identifies the main challenges when deploying TinyML tasks in the real world and guides the researchers to deploy a reliable learning system.This book will be of interest to students and scholars in the field of edge intelligence, especially to those with sufficient professional Edge AI skills. It will also be an excellent guide for researchers to implement high-performance TinyML systems.

This book aims at the tiny machine learning (TinyML) software and hardware synergy for edge intelligence applications. This book presents on-device learning techniques covering model-level neural network design, algorithm-level training optimization and hardware-level instruction acceleration.Analyzing the limitations of conventional in-cloud computing would reveal that on-device learning is a promising research direction to meet the requirements of edge intelligence applications. As to the cutting-edge research of TinyML, implementing a high-efficiency learning framework and enabling system-level acceleration is one of the most fundamental issues. This book presents a comprehensive discussion of the latest research progress and provides system-level insights on designing TinyML frameworks, including neural network design, training algorithm optimization and domain-specific hardware acceleration. It identifies the main challenges when deploying TinyML tasks in the real world and guides the researchers to deploy a reliable learning system.This book will be of interest to students and scholars in the field of edge intelligence, especially to those with sufficient professional Edge AI skills. It will also be an excellent guide for researchers to implement high-performance TinyML systems.

Discover this multi-disciplinary and insightful work, which integrates machine learning, edge computing, and big data. Presents the basics of training machine learning models, key challenges and issues, as well as comprehensive techniques including edge learning algorithms, and system design issues. Describes architectures, frameworks, and key technologies for learning performance, security, and privacy, as well as incentive issues in training/inference at the network edge. Intended to stimulate fruitful discussions, inspire further research ideas, and inform readers from both academia and industry backgrounds. Essential reading for experienced researchers and developers, or for those who are just entering the field.

This book introduces the software defined system concept, architecture, and its enabling technologies such as software defined sensor networks (SDSN), software defined radio, cloud/fog radio access networks (C/F-RAN), software defined networking (SDN), network function virtualization (NFV), software defined storage, virtualization and docker. The authors also discuss the resource allocation and task scheduling in software defined system, mainly focusing on sensing, communication, networking and computation. Related case studies on SDSN, C/F-RAN, SDN, NFV are included in this book, and the authors discuss how these technologies cooperate with each other to enable cross resource management and task scheduling in software defined system. Novel resource allocation and task scheduling algorithms are introduced and evaluated. This book targets researchers, computer scientists and engineers who are interested in the information system softwarization technologies, resource allocation and optimization algorithm design, performance evaluation and analysis, next-generation communication and networking technologies, edge computing, cloud computing and IoT. Advanced level students studying these topics will benefit from this book as well.

This book introduces two basic big data processing paradigms for batch data and streaming data. Representative programming frameworks are also presented, as well as software defined networking (SDN) and network function virtualization (NFV) technologies as key cloud networking technologies. The authors illustrate that SDN and NFV can be applied to benefit the big data processing by proposing a cloud networking framework. Based on the framework, two case studies examine how to improve the cost efficiency of big data processing. Cloud Networking for Big Data targets professionals and researchers working in big data, networks, wireless communications and information technology. Advanced-level students studying computer science and electrical engineering will also find this book valuable as a study guide.

This book introduces two basic big data processing paradigms for batch data and streaming data. Representative programming frameworks are also presented, as well as software defined networking (SDN) and network function virtualization (NFV) technologies as key cloud networking technologies. The authors illustrate that SDN and NFV can be applied to benefit the big data processing by proposing a cloud networking framework. Based on the framework, two case studies examine how to improve the cost efficiency of big data processing. Cloud Networking for Big Data targets professionals and researchers working in big data, networks, wireless communications and information technology. Advanced-level students studying computer science and electrical engineering will also find this book valuable as a study guide.

This brief examines current research on cooperative device-to-device (D2D) communication as an enhanced offloading technology to improve the performance of cognitive radio cellular networks. By providing an extensive review of recent advances in D2D communication, the authors demonstrate that the quality of D2D links significantly affects offloading performance in cellular networks, which motivates the design of cooperative D2D communication. After presenting the architecture of cooperative D2D communication, the challenges of capacity maximization and energy efficiency are addressed by optimizing relay assignment, power control and resource allocation. Furthermore, cooperative D2D communication is enhanced by network coding technology, and then is extended for broadcast sessions. Along with detailed problem formulation and hardness analysis, fast algorithms are developed by exploiting problem-specific characteristics such that they can be applied in practice.