Edge Intelligence In The Making

With the explosive growth of mobile computing and Internet of Things (IoT) applications, as exemplified by AR/VR, smart city, and video/audio surveillance, billions of mobile and IoT devices are being connected to the Internet, generating zillions of bytes of data at the network edge. Driven by this trend, there is an urgent need to push the frontiers of artificial intelligence (AI) to the network edge to fully unleash the potential of IoT big data. Indeed, the marriage of edge computing and AI has resulted in innovative solutions, namely edge intelligence or edge AI. Nevertheless, research and practice on this emerging inter-disciplinary field is still in its infancy stage. To facilitate the dissemination of the recent advances in edge intelligence in both academia and industry, this book conducts a comprehensive and detailed survey of the recent research efforts and also showcases the authors' own research progress on edge intelligence. Specifically, the book first reviews the background and present motivation for AI running at the network edge. Next, it provides an overview of the overarching architectures, frameworks, and emerging key technologies for deep learning models toward training/inference at the network edge. To illustrate the research problems for edge intelligence, the book also showcases four of the authors' own research projects on edge intelligence, ranging from rigorous theoretical analysis to studies based on realistic implementation. Finally, it discusses the applications, marketplace, and future research opportunities of edge intelligence. This emerging interdisciplinary field offers many open problems and yet also tremendous opportunities, and this book only touches the tip of iceberg. Hopefully, this book will elicit escalating attention, stimulate fruitful discussions, and open new directions on edge intelligence.

With the explosive growth of mobile computing and Internet of Things (IoT) applications, as exemplified by AR/VR, smart city, and video/audio surveillance, billions of mobile and IoT devices are being connected to the Internet, generating zillions of bytes of data at the network edge. Driven by this trend, there is an urgent need to push the frontiers of artificial intelligence (AI) to the network edge to fully unleash the potential of IoT big data. Indeed, the marriage of edge computing and AI has resulted in innovative solutions, namely edge intelligence or edge AI. Nevertheless, research and practice on this emerging inter-disciplinary field is still in its infancy stage. To facilitate the dissemination of the recent advances in edge intelligence in both academia and industry, this book conducts a comprehensive and detailed survey of the recent research efforts and also showcases the authors' own research progress on edge intelligence. Specifically, the book first reviews the background and present motivation for AI running at the network edge. Next, it provides an overview of the overarching architectures, frameworks, and emerging key technologies for deep learning models toward training/inference at the network edge. To illustrate the research problems for edge intelligence, the book also showcases four of the authors' own research projects on edge intelligence, ranging from rigorous theoretical analysis to studies based on realistic implementation. Finally, it discusses the applications, marketplace, and future research opportunities of edge intelligence. This emerging interdisciplinary field offers many open problems and yet also tremendous opportunities, and this book only touches the tip of iceberg. Hopefully, this book will elicit escalating attention, stimulate fruitful discussions, and open new directions on edge intelligence.

As an important enabler for changing people’s lives, advances in artificial intelligence (AI)-based applications and services are on the rise, despite being hindered by efficiency and latency issues. By focusing on deep learning as the most representative technique of AI, this book provides a comprehensive overview of how AI services are being applied to the network edge near the data sources, and demonstrates how AI and edge computing can be mutually beneficial. To do so, it introduces and discusses: 1) edge intelligence and intelligent edge; and 2) their implementation methods and enabling technologies, namely AI training and inference in the customized edge computing framework. Gathering essential information previously scattered across the communication, networking, and AI areas, the book can help readers to understand the connections between key enabling technologies, e.g. a) AI applications in edge; b) AI inference in edge; c) AI training for edge; d) edge computing for AI; and e) using AI to optimize edge. After identifying these five aspects, which are essential for the fusion of edge computing and AI, it discusses current challenges and outlines future trends in achieving more pervasive and fine-grained intelligence with the aid of edge computing.

This graduate-level textbook is ideally suited for lecturing the most relevant topics of Edge Computing and its ties to Artificial Intelligence (AI) and Machine Learning (ML) approaches. It starts from basics and gradually advances, step-by-step, to ways AI/ML concepts can help or benefit from Edge Computing platforms. The book is structured into seven chapters; each comes with its own dedicated set of teaching materials (practical skills, demonstration videos, questions, lab assignments, etc.). Chapter 1 opens the book and comprehensively introduces the concept of distributed computing continuum systems that led to the creation of Edge Computing. Chapter 2 motivates the use of container technologies and how they are used to implement programmable edge computing platforms. Chapter 3 introduces ways to employ AI/ML approaches to optimize service lifecycles at the edge. Chapter 4 goes deeper in the use of AI/ML and introduces ways to optimize spreading computational tasks along edge computing platforms. Chapter 5 introduces AI/ML pipelines to efficiently process generated data on the edge. Chapter 6 introduces ways to implement AI/ML systems on the edge and ways to deal with their training and inferencing procedures considering the limited resources available at the edge-nodes. Chapter 7 motivates the creation of a new orchestrator independent object model to descriptive objects (nodes, applications, etc.) and requirements (SLAs) for underlying edge platforms. To provide hands-on experience to students and step-by-step improve their technical capabilities, seven sets of Tutorials-and-Labs (TaLs) are also designed. Codes and Instructions for each TaL is provided on the book website, and accompanied by videos to facilitate their learning process.

The strategically sound combination of edge computing and artificial intelligence (AI) results in a series of distinct innovations and disruptions enabling worldwide enterprises to visualize and realize next-generation software products, solutions and services. Businesses, individuals, and innovators are all set to embrace and experience the sophisticated capabilities of Edge AI. With the faster maturity and stability of Edge AI technologies and tools, the world is destined to have a dazzling array of edge-native, people-centric, event-driven, real-time, service-oriented, process-aware, and insights-filled services. Further on, business workloads and IT services will become competent and cognitive with state-of-the-art Edge AI infrastructure modules, AI algorithms and models, enabling frameworks, integrated platforms, accelerators, high-performance processors, etc. The Edge AI paradigm will help enterprises evolve into real-time and intelligent digital organizations. Applied Edge AI: Concepts, Platforms, and Industry Use Cases focuses on the technologies, processes, systems, and applications that are driving this evolution. It examines the implementation technologies; the products, processes, platforms, patterns, and practices; and use cases. AI-enabled chips are exclusively used in edge devices to accelerate intelligent processing at the edge. This book examines AI toolkits and platforms for facilitating edge intelligence. It also covers chips, algorithms, and tools to implement Edge AI, as well as use cases. FEATURES The opportunities and benefits of intelligent edge computing Edge architecture and infrastructure AI-enhanced analytics in an edge environment Encryption for securing information An Edge AI system programmed with Tiny Machine learning algorithms for decision making An improved edge paradigm for addressing the big data movement in IoT implementations by integrating AI and caching to the edge Ambient intelligence in healthcare services and in development of consumer electronic systems Smart manufacturing of unmanned aerial vehicles (UAVs) AI, edge computing, and blockchain in systems for environmental protection Case studies presenting the potential of leveraging AI in 5G wireless communication

Recently, Tiny Machine Learning (TinyML) has gained incredible importance due to its capabilities of creating lightweight machine learning (ML) frameworks aiming at low latency, lower energy consumption, lower bandwidth requirement, improved data security and privacy, and other performance necessities. As billions of battery-operated embedded IoT and low power wide area networks (LPWAN) nodes with very low on-board memory and computational capabilities are getting connected to the Internet each year, there is a critical need to have a special computational framework like TinyML. TinyML for Edge Intelligence in IoT and LPWAN Networks presents the evolution, developments, and advances in TinyML as applied to IoT and LPWANs. It starts by providing the foundations of IoT/LPWANs, low power embedded systems and hardware, the role of artificial intelligence and machine learning in communication networks in general and cloud/edge intelligence. It then presents the concepts, methods, algorithms and tools of TinyML. Practical applications of the use of TinyML are given from health and industrial fields which provide practical guidance on the design of applications and the selection of appropriate technologies. TinyML for Edge Intelligence in IoT and LPWAN Networks is highly suitable for academic researchers and professional system engineers, architects, designers, testers, deployment engineers seeking to design ultra-lower power and time-critical applications. It would also help in designing the networks for emerging and future applications for resource-constrained nodes. This book provides one-stop solutions for emerging TinyML for IoT and LPWAN applications. The principles and methods of TinyML are explained, with a focus on how it can be used for IoT, LPWANs, and 5G applications. Applications from the healthcare and industrial sectors are presented. Guidance on the design of applications and the selection of appropriate technologies is provided.

This book examines whether the integration of edge intelligence (EI) and blockchain (BC) can open up new horizons for providing ubiquitous intelligent services. Accordingly, the authors conduct a summarization of the recent research efforts on the existing works for EI and BC, further painting a comprehensive picture of the limitation of EI and why BC could benefit EI. To examine how to integrate EI and BC, the authors discuss the BC-driven EI and tailoring BC to EI, including an overview, motivations, and integrated frameworks. Finally, some challenges and future directions are explored. The book explores the technologies associated with the integrated system between EI and BC, and further bridges the gap between immature BC and EI-amicable BC. Explores the integration of edge intelligence (EI) and blockchain (BC), including their integrated motivations, frameworks and challenges; Presents how BC-driven EI can realize computing-power management, data administration, and model optimization; Describes how to tailor BC to better support EI, including flexible consensus protocol, effective incentive mechanism, intellectuality smart contract, and scalable BC system tailoring; Presents some key research challenges and future directions for the integrated system.