Название: Edge Intelligence: From Theory to PracticeАвтор: Javid Taheri, Schahram Dustdar, Albert Zomaya, Shuiguang Deng
Издательство: Springer
Год: 2023
Страниц: 254
Язык: английский
Формат: pdf (true)
Размер: 10.1 MB
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. The book starts from basics and gradually advances, step-by-step, to ways AI/ML concepts can help or benefit from edge computing platforms. Using practical labs, each topic is brought to earth so that students can practice their learned knowledge with industry-approved software packages.
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. TaL 1 shows how to install basic software packages (VirtualBox, Visual Studio Code) and programming environments (Node.js) and write sample programs (e.g., a “Hello, World” program) to perform all future TaLs. TaL 2 shows how to install a stand-alone Kubernetes (K8) platform, how to containerize and deploy a sample Node.js code, as well as how to deploy it on a K8 platform and consume its provided services. TaL 3 shows how to profile containers and develop an external auto-scaler to scale up/down K8 services. TaL 4 describes the placement algorithms and how they can be implemented for K8 platforms, as well as how to develop, containerize, and deploy a placement solver. TaL 5 shows how to build containers to emulate the behavior of various components of distributed computing continuum platforms (sensors, edge nodes, and cloud servers), as well as how to develop a basic fault detector to collect historic data from sensor and identify their faulty readings in the offline mode. TaL 6 shows how to develop, containerize, and deploy an ML algorithm on the edge nodes to detect faults in the online mode. TaL 7 demonstrates how to build a configurable service-level objective (SLO) controller for Kubernetes and trigger an elasticity strategy upon violation of the SLO.
The book comes with a website to help lecturers prepare the teaching materials, and students to access the provided videos, instructions, labs, etc.
Скачать Edge Intelligence: From Theory to Practice