Applied AI for IT Operations (AIOps)

Course details

IT operations is one of the key business functions for modern enterprises. As data centers become large, distributed, and integrated, the need to monitor and manage hardware, software, networks, and data increases exponentially. And while the elements in a network generate tons of data in terms of logs and events, the need to collect and understand this data to predict future outcomes is also increasing. In this course, learn how to solve common challenges in IT operations using the power of AI. Instructor Kumaran Ponnambalam reviews the key issues that IT ops teams face in their day-to-day operations. He then goes over several uses cases in the world of IT ops, explaining in detail how AI technology can speed up processes like root cause analysis, improve response times at your IT help desk, and more. Along the way, he uses Python, Jupyter Notebooks, Keras, and deep learning techniques to step through practical solutions.

Concepts

0. Introduction

01 - Artificial intelligence and its many uses
02 - What you should know

1. IT Operations and AI

03 - Introduction to ITOps
04 - ITOps challenges
05 - AI and ITOps
06 - ITOps use cases overview
07 - Setting up the exercise files

2. Use Case 1 - Root Cause Analysis

08 - What is root cause analysis
09 - Classification with deep learning
10 - Data for root cause analysis (RCA)
11 - Preprocessing RCA data
12 - Building a classification model with Keras
13 - Predicting root causes with Keras

3. Use Case 2 - Self-Help Service Desk

14 - Automating helpdesk functions
15 - Latent semantic analysis (LSA) and latent semantic indexing (LSI)
16 - Data for the help desk
17 - Building a document vector
18 - Creating the LSI model
19 - Recommending FAQs

4. Use Case 3 - Service Load Forecasting

20 - Time series forecasting
21 - Recurrent neural network (RNN) and long short-term memory (LSTM)
22 - Preparing sequence data
23 - Building an LSTM model with Keras
24 - Testing the time series model
25 - Forecasting future service loads with Keras

5. Other ITOps Use Cases

26 - Anomaly detection
27 - Predicting alerting
28 - Incident categorization
29 - Spam filtering
30 - Network traffic analysis

6. Generative AI for ITOps

31 - Generative AI review
32 - Text generation with LLMs
33 - Log data extraction
34 - Incident summarization
35 - Documentation self-help chatbot
36 - Code generation for scripts
37 - Code generation example

7. ITOps Best Practices

38 - Model development best practices
39 - Using machine learning platforms
40 - Model serving best practices
41 - Security and privacy best practices

Conclusion

42 - Next steps