Book Image

Intelligent Workloads at the Edge

By : Indraneel Mitra, Ryan Burke
Book Image

Intelligent Workloads at the Edge

By: Indraneel Mitra, Ryan Burke

Overview of this book

The Internet of Things (IoT) has transformed how people think about and interact with the world. The ubiquitous deployment of sensors around us makes it possible to study the world at any level of accuracy and enable data-driven decision-making anywhere. Data analytics and machine learning (ML) powered by elastic cloud computing have accelerated our ability to understand and analyze the huge amount of data generated by IoT. Now, edge computing has brought information technologies closer to the data source to lower latency and reduce costs. This book will teach you how to combine the technologies of edge computing, data analytics, and ML to deliver next-generation cyber-physical outcomes. You’ll begin by discovering how to create software applications that run on edge devices with AWS IoT Greengrass. As you advance, you’ll learn how to process and stream IoT data from the edge to the cloud and use it to train ML models using Amazon SageMaker. The book also shows you how to train these models and run them at the edge for optimized performance, cost savings, and data compliance. By the end of this IoT book, you’ll be able to scope your own IoT workloads, bring the power of ML to the edge, and operate those workloads in a production setting.

Related Content you might be interested in

Current Title:

Small book image
Intelligent Workloads at the Edge
Indraneel Mitra | Ryan Burke
Jan, 2022 | 374 pages
Small book image
Designing Production-Grade and Large-Scale IoT Solutions.
Mohamed Alwan
May, 2022 | 412 pages
Small book image
Industrial IoT for Architects and Engineers
Joey Bernal | Bharath Sridhar
Jan, 2023 | 344 pages
Small book image
Internet of Things from Scratch
Renaldi Gondosubroto
Feb, 2024 | 438 pages
Table of Contents (17 chapters)
Preface
Preface
Who this book is for
What this book covers
Download the example code files
Download the color images
Conventions used
Get in touch
Share Your Thoughts
1
Section 1: Introduction and Prerequisites
Section 1: Introduction and Prerequisites
Free Chapter
2
Chapter 1: Introduction to the Data-Driven Edge with Machine Learning
Chapter 1: Introduction to the Data-Driven Edge with Machine Learning
Living on the edge
Bringing ML to the edge
Tools to get the job done
Demand for smart home and industrial IoT
Setting the scene: A modern smart home solution
Hands-on prerequisites
Summary
Knowledge check
References
3
Section 2: Building Blocks
Section 2: Building Blocks
4
Chapter 2: Foundations of Edge Workloads
Chapter 2: Foundations of Edge Workloads
Technical requirements
The anatomy of an edge ML solution
IoT Greengrass for the win
Checking compatibility with IoT Device Tester
Installing IoT Greengrass
Creating your first edge component
Summary
Knowledge check
References
5
Chapter 3: Building the Edge
Chapter 3: Building the Edge
Technical requirements
Exploring the topology of the edge
Reviewing common standards and protocols
Security at the edge
Connecting your first device – sensing at the edge
Connecting your second device – actuating at the edge
Summary
Knowledge check
References
6
Chapter 4: Extending the Cloud to the Edge
Chapter 4: Extending the Cloud to the Edge
Technical requirements
Creating and deploying remotely
Storing logs in the cloud
Synchronizing the state between the edge and the cloud
Deploying your first ML model
Summary
Knowledge check
References
7
Chapter 5: Ingesting and Streaming Data from the Edge
Chapter 5: Ingesting and Streaming Data from the Edge
Technical requirements
Defining data models for IoT workloads
Designing data patterns on the edge
A hands-on approach with the lab
Additional topics for reference
Summary
Knowledge check
References
8
Chapter 6: Processing and Consuming Data on the Cloud
Chapter 6: Processing and Consuming Data on the Cloud
Technical requirements
Defining big data for IoT workloads
Designing data patterns on the cloud
A hands-on approach with the lab
Summary
Knowledge check
References
9
Chapter 7: Machine Learning Workloads at the Edge
Chapter 7: Machine Learning Workloads at the Edge
Technical requirements
Defining ML for IoT workloads
Designing an ML workflow in the cloud
Data visualization and analytics
Hands-on with ML architecture
Summary
Knowledge check
References
10
Section 3: Scaling It Up
Section 3: Scaling It Up
11
Chapter 8: DevOps and MLOps for the Edge
Chapter 8: DevOps and MLOps for the Edge
Technical requirements
Defining DevOps for IoT workloads
Understanding the DevOps toolchain for the edge
MLOps at the edge
Hands-on with the DevOps architecture
Summary
Knowledge check
References
12
Chapter 9: Fleet Management at Scale
Chapter 9: Fleet Management at Scale
Technical requirements
Onboarding a fleet of devices globally
Managing your device fleet at scale
Getting hands-on with Fleet Hub architecture
Summary
Knowledge check
References
13
Section 4: Bring It All Together
Section 4: Bring It All Together
14
Chapter 10: Reviewing the Solution with AWS Well-Architected Framework
Chapter 10: Reviewing the Solution with AWS Well-Architected Framework
Summarizing the key lessons
Describing the AWS Well-Architected Framework
Reviewing the solution
Diving deeper into AWS services
Summary
References
15
Other Books You May Enjoy
Other Books You May Enjoy
Packt is searching for authors like you
Share Your Thoughts
Appendix 1 – Answer Key
Appendix 1 – Answer Key
Chapter 1
Chapter 2
Chapter 3
Chapter 4
Chapter 5
Chapter 6
Chapter 7
Chapter 8
Chapter 9
Why subscribe?

Knowledge check

Before moving on to the next chapter, test your knowledge by answering these questions. The answers can be found at the end of the book:

  1. What's the difference between a cyber-physical solution and an edge solution?
  2. At the time it was invented, the automobile was a self-contained mechanical entity, not a cyber-physical solution or an edge solution. At some point in the evolution of the automobile, it started meeting the definition of a cyber-physical solution, and then again meeting the definition of an edge solution. What are the characteristics of automobiles we can find today that meet our definition of an edge solution?
  3. Has the telephone always been a cyber-physical solution? Why or why not?
  4. What are the common components of an edge solution?
  5. What are the three primary types of tools needed to deliver intelligence workloads at the edge?
  6. What are the four key benefits in edge-to-cloud workloads that can be achieved with ML models running at the edge?
  7. Who is the primary persona at the heart of any smart home solution?
  8. Can you identify one more use case for the smart home vertical that ties in with one more of the key benefits for ML-powered edge solutions?
  9. Who is the primary persona at the heart of any industrial solution?
  10. Can you identify one more use case for any industrial vertical that ties in with one more of the key benefits of ML-powered edge solutions?
  11. Is the IoT architect of an ML-powered edge solution typically responsible for the performance accuracy (for example, confidence scores for a prediction) of the models deployed? Why or why not?
Previous Section
End of Section 9
Next Section