What do you think?
Rate this book
Machine Learning for Network and Cloud Engineers: Get ready for the next Era of Network Automation
If you are a network or cloud engineer planning to strengthen your skills, continue reading.
We have applied network automation techniques for Network and Cloud Infrastructures for years. Network automation has focused so far on automating "actions". As an Industry, we have focused on the "how" and get it automated (how to automate a software upgrade, how to automate a configuration change, how to automate service provisioning, etc.).
We are about to enter a new Era in managing our network and cloud infrastructures, one where we will need to automate "decisions" . It is about automating the answers for the other remaining the when, the what, the why, and the where.
Network and Cloud infrastructures are more complex than ever but more critical than ever. This is the perfect storm for network and cloud engineers .
This book is about helping you gain knowledge, understanding, criteria, and practical application of multiple machine learning techniques to tackle the challenge described above. It is about how to help you become a better professional by expanding your expertise with applied machine learning use cases.
There are many books about machine learning techniques, no doubt about that. However, no other one will give you a comprehensive and contextualized description , with practical use cases for your infrastructure, with code. This is the book that will boost your skills as a network and cloud professional , and give you a broad and deep understanding of a wide range of techniques, use cases, and examples that are relevant to your daily activities.
The book contains both theory and practice .
The theory addresses a wide spectrum of techniques and algorithms, from traditional statistical methods like clustering, anomaly detection, and time series forecasting, to bleeding edge architectures based on deep neural networks such as GANs and Language Models. All are presented with application examples for networks and clouds. Many books will give you in-depth descriptions of algorithms, but you will have to buy multiple of them to cover the spectrum addressed in this book, and still, they will not be contextualized.
This book gives you the big picture with the level of detail you need to elevate your game as a network and cloud engineer.
The practice section contains ten different use cases solving relevant pain points identified in network and cloud infrastructures. For each, various strategies are described and demonstrated with code in Python notebooks that you use as blueprints.
Why is AI/ML relevant for network and cloud engineers?
May the Force be with you What is specific to networking?
Will AI/ML replace people?
Introduction to AI/ML concepts
Types of problems to be solved with ML
Types of Machine Learning techniques
Unsupervised learning
Supervised learning
Neural Networks
Generative vs. discriminative techniques
Generation techniques
Reinforcement Learning
Causal Inference
Natural Language Processing (NLP)
A strategic view of deep learning for network and cloud AIOps
“It is the data, stupid!”
How to explain what is in the “black box”?
MLOps
How Machine Learning learns from Nature
Machine Learning Frameworks and tools
Practical use cases with code
UC1. Is there something wrong with my network subscribers?
UC2. Are my SD-WAN edge devices behaving as expected?
UC3. What different types of SD-WAN devices do I have deployed?
UC4. How many subscribers will be up in my network next week?
UC5. Is the cabling in my network correct? UC6. What are the driving factors for problems in my network?
UC7. What is the severity of this log message?
UC8. What log message is expected next?
UC9. Let’s generate some new “fake” logs
UC10. That router is not properly configured
We have applied network automation techniques for Network and Cloud Infrastructures for years. Network automation has focused so far on automating "actions". As an Industry, we have focused on the "how" and get it automated (how to automate a software upgrade, how to automate a configuration change, how to automate service provisioning, etc.).
We are about to enter a new Era in managing our network and cloud infrastructures, one where we will need to automate "decisions" . It is about automating the answers for the other remaining the when, the what, the why, and the where.
Network and Cloud infrastructures are more complex than ever but more critical than ever. This is the perfect storm for network and cloud engineers .
This book is about helping you gain knowledge, understanding, criteria, and practical application of multiple machine learning techniques to tackle the challenge described above. It is about how to help you become a better professional by expanding your expertise with applied machine learning use cases.
There are many books about machine learning techniques, no doubt about that. However, no other one will give you a comprehensive and contextualized description , with practical use cases for your infrastructure, with code. This is the book that will boost your skills as a network and cloud professional , and give you a broad and deep understanding of a wide range of techniques, use cases, and examples that are relevant to your daily activities.
The book contains both theory and practice .
The theory addresses a wide spectrum of techniques and algorithms, from traditional statistical methods like clustering, anomaly detection, and time series forecasting, to bleeding edge architectures based on deep neural networks such as GANs and Language Models. All are presented with application examples for networks and clouds. Many books will give you in-depth descriptions of algorithms, but you will have to buy multiple of them to cover the spectrum addressed in this book, and still, they will not be contextualized.
This book gives you the big picture with the level of detail you need to elevate your game as a network and cloud engineer.
The practice section contains ten different use cases solving relevant pain points identified in network and cloud infrastructures. For each, various strategies are described and demonstrated with code in Python notebooks that you use as blueprints.
Why is AI/ML relevant for network and cloud engineers?
May the Force be with you What is specific to networking?
Will AI/ML replace people?
Introduction to AI/ML concepts
Types of problems to be solved with ML
Types of Machine Learning techniques
Unsupervised learning
Supervised learning
Neural Networks
Generative vs. discriminative techniques
Generation techniques
Reinforcement Learning
Causal Inference
Natural Language Processing (NLP)
A strategic view of deep learning for network and cloud AIOps
“It is the data, stupid!”
How to explain what is in the “black box”?
MLOps
How Machine Learning learns from Nature
Machine Learning Frameworks and tools
Practical use cases with code
UC1. Is there something wrong with my network subscribers?
UC2. Are my SD-WAN edge devices behaving as expected?
UC3. What different types of SD-WAN devices do I have deployed?
UC4. How many subscribers will be up in my network next week?
UC5. Is the cabling in my network correct? UC6. What are the driving factors for problems in my network?
UC7. What is the severity of this log message?
UC8. What log message is expected next?
UC9. Let’s generate some new “fake” logs
UC10. That router is not properly configured
531 pages, Paperback
Published January 26, 2023
10 people are currently reading
22 people want to read
Ratings & Reviews
Friends & Following
Create a free account to discover what your friends think of this book!
Community Reviews
No one has reviewed this book yet.