عملیاتی هوش مصنوعی: راهنمای بهترین شیوه‌ها برای پیاده‌سازی AIOps

Welcome to your hands-on guide to artificial intelligence for IT operations (AIOps). This book provides in-depth coverage, including operations and technical aspects. The fundamentals of machine learning (ML) and artificial intelligence (AI) that form the core of AIOps are explained as well as the implementation of multiple AIOps uses cases using ML algorithms. The book begins with an overview of AIOps, covering its relevance and benefits in the current IT operations landscape. The authors discuss the evolution of AIOps, its architecture, technologies, AIOps challenges, and various practical use cases to efficiently implement AIOps and continuously improve it. The book provides detailed guidance on the role of AIOps in site reliability engineering (SRE) and DevOps models and explains how AIOps enables key SRE principles. The book provides ready-to-use best practices for implementing AIOps in an enterprise. Each component of AIOps and ML using Python code and templates is explained and shows how ML can be used to deliver AIOps use cases for IT operations. What You Will Learn Know what AIOps is and the technologies involved Understand AIOps relevance through use cases Understand AIOps enablement in SRE and DevOps Understand AI and ML technologies and algorithms Use algorithms to implement AIOps use cases Use best practices and processes to set up AIOps practices in an enterprise Know the fundamentals of ML and deep learning Study a hands-on use case on de-duplication in AIOps Use regression techniques for automated baselining Use anomaly detection techniques in AIOps Who This Book is For AIOps enthusiasts, monitoring and management consultants, observability engineers, site reliability engineers, infrastructure architects, cloud monitoring consultants, service management experts, DevOps architects, DevOps engineers, and DevSecOps experts Table of Contents About the Authors About the Technical Reviewer Acknowledgments Preface Introduction Chapter 1: What Is AIOps? Introduction to AIOps Data Ingestion Layer Data Processing Layer Data Representation Layer AIOps Benefits Summary Chapter 2: AIOps Architecture and Methodology AIOps Architecture The Core Platform Big Data Volume Velocity Variety Veracity Value Machine Learning The Three Key Areas in AIOps Observe Data Ingestion Integration Event Suppression Event Deduplication Rule-Based Correlation Machine Learning–Based Correlation Anomaly Detection Event Correlation Root-Cause Analysis Predictive Analysis Visualization Collaboration Feedback Engage Incident Creation Task Assignment Task Analytics Agent Analytics Change Analytics Process Analytics Visualization Collaboration Feedback Act Automation Recommendation Automation Execution Incident Resolution SR Fulfilment Change Orchestration Automation Analytics Visualization Collaboration Feedback Application Discovery and Insights Making Connections: The Value of Data Correlation Summary Chapter 3: AIOps Challenges Organizational Change Management Monitoring Coverage and Data Availability Rigid Processes Lack of Understanding of Machine Learning and AIOps Expectations Mismatch Fragmented Functions and the CMDB Challenges in Machine Learning Data Drift Predictive Analytics Challenges Cost Savings Expectations Lack of Domain Inputs Summary Chapter 4: AIOps Supporting SRE and DevOps Overview of SRE and DevOps SRE Principles and AIOps Principle 1: Embracing Risk Principle 2: Service Level Objectives Principle 3: Eliminating Toil Principle 4: Monitoring Principle 5: Automation Principle 6: Release Engineering Principle 7: Simplicity AIOps Enabling Visibility in SRE and DevOps Culture Automation of Processes Measurement of Key Performance Indicators (KPIs) Sharing Summary Chapter 5: Fundamentals of Machine Learning and AI What Is Artificial Intelligence and Machine Learning? Why Machine Learning Is Important Types of Machine Learning Machine Learning Supervised (Inductive) Learning Unsupervised Learning Reinforcement Learning Differences Between Supervised and Unsupervised Learning Choosing the Machine Learning Approach Natural Language Processing What Is Natural Language Processing? Syntactic Analysis Semantic Analysis NLP AIOps Use Cases Sentiment Analysis Language Translation Text Extraction Topic Classification Deep Learning Summary Chapter 6: AIOps Use Case: Deduplication Environment Setup Software Installation Launch Application Performance Analysis of Models Mean Square Error/Root Mean Square Error Mean Absolute Error Mean Absolute Percentage Error Root Mean Squared Log Error Coefficient of Determination-R2 Score Deduplication Summary Chapter 7: AIOps Use Case: Automated Baselining Automated Baselining Overview Regression Linear Regression Time-Series Models Time-Series Data Stationary Time Series Lag Variable ACF and PACF ARIMA Model Development Differencing (d) Autoregression or AR (p) Moving Average or MA (q) SARIMA Implementation of ARIMA and SARIMA Automated Baselining in APM and SecOps Challenges with Dynamic Thresholding Summary Chapter 8: AIOps Use Case: Anomaly Detection Anomaly Detection Overview K-Means Algorithms Correlation and Association Topology-Based Correlation Network Topology Correlation Application Topology Correlation Summary Chapter 9: Setting Up AIOps Step 1: Write an AIOps Charter Step 2: Build Your AIOps Team Step 3: Define Your AIOps Landscape Step 4: Define Integrations and Data Sources Step 5: Install and Configure the AIOps Engine Step 6: Configure AIOps Features Step 7: Deploy the Service Management Features Step 8: Deploy Automation Features Step 9: Measure Success Step 10: Celebrate and Share Success Guidelines on Implementing AIOps Hype vs. Clarity Be Goal and KPI Driven Expectations Time to Realize Benefits One Size Doesn’t Fit All Organizational Change Management Plan Big, Start Small, and Iterate Fast Continually Improve The Future of AIOps Summary Index