This article explains practical approaches for time‑series anomaly detection, multi‑dimensional drill‑down analysis, alarm‑convergence root‑cause analysis, and future AIOps planning, combining statistical methods, unsupervised learning, and supervised models to improve monitoring accuracy and operational efficiency.
This article details JD.com’s database team’s evolution from manual operations to a fully automated, AI‑driven platform—covering metadata management, automated deployment, intelligent analysis, auto‑switching, backup & recovery, and the ContainerDB elastic scheduling system that powers future smart, fast, and cost‑effective database services.
This article details Alibaba's three‑year journey building a search middle platform, describing how DevOps, goal‑driven operations, and AI‑assisted automation (Sophon, Bahamut, and AIOps) were introduced to improve scalability, stability, and efficiency for large‑scale search services.
This article explores the emerging field of AIOps, comparing rule‑based operations with AI‑driven approaches, outlining a five‑level AIOps maturity model, and presenting several Tencent case studies that demonstrate cost reduction, quality improvement, root‑cause analysis, and automated scaling.
This article examines how intelligent operations—ranging from automated monitoring to AI‑driven AIOps—are essential yet often overlooked in the securities and fund industry, outlining their importance, complexity, evolution stages, feasibility, and practical recommendations for effective implementation.
Alibaba’s AIOps case study details how the Hawkeye intelligent diagnosis system and the Torch capacity governance platform jointly improve search platform efficiency, stability, and cost by leveraging algorithmic analysis, automated cloning, stress testing, and optimization across resource, performance, and smart Q&A dimensions.
This talk by Tencent’s monitoring R&D lead outlines a decade of evolution in large‑scale monitoring, covering real‑world incident cases, the three drivers behind architectural upgrades, the implementation of a three‑dimensional monitoring framework, and the application of AI‑powered AIOps for precise, rapid anomaly detection.
Alibaba’s search middle platform illustrates a three‑year journey from manual, labor‑intensive operations to a fully integrated DevOps and AIOps ecosystem, detailing the evolution of SOPHON, Bahamut, and related systems that enable end‑to‑end automation, stability, and cost‑effective scaling for massive search workloads.
This article explores Ctrip's adoption of AIOps—AI‑driven IT operations—detailing its concepts, typical use cases such as anomaly detection, intelligent fault diagnosis, and resource‑utilization improvement, and demonstrating how machine‑learning models like ARMA, FFT, and SVM have transformed operational efficiency, availability, and cost.
This article explains AIOps—Artificial Intelligence for IT Operations—its impact on traditional automation, and details how four key roles (Operations Engineer, Operations R&D Engineer, Platform R&D Engineer, and Operations AI Engineer) evolve in responsibilities and required skills within the AIOps era.
The DOIS DevOps International Summit in Beijing gathered over a hundred experts from finance, internet and telecom sectors to share DevOps, AIOps, SRE and automation practices, launch a new DevOps maturity model, and showcase how banks like Minsheng are applying these methods to modernize their operations.
Presented by JD Finance’s senior architect Wang Chao, this talk outlines the four‑quadrant operations framework (speed, quality, safety, cost), introduces DevOps concepts and principles, details lifecycle management, infrastructure‑as‑code, platform‑as‑code, and looks ahead to data‑driven operations and AIOps for scalable, secure, cost‑effective services.
This article introduces Ctrip's AIOps journey, explaining the AI‑driven operations concept, showcasing typical use cases such as anomaly detection, intelligent fault diagnosis, and resource utilization improvement, and detailing the underlying statistical and machine‑learning algorithms that enable these capabilities.
This article explains how the ELK stack (Elasticsearch, Logstash, Kibana) and Heka can be quickly integrated into mobile games to collect, store, analyze, and alert on log data, improving operational efficiency, troubleshooting speed, and overall service reliability.
This article explores the end‑to‑end design of an enterprise‑grade fault‑self‑healing solution, covering the basic workflow, abstraction of alert handling, CMDB‑based resource mapping, internal gateway integration, monitoring platform adapters like Zabbix and Open‑Falcon, convergence logic, complex alarm orchestration, and the overall technical architecture.
A mathematician‑turned‑engineer recounts his 2015‑2022 path from undocumented recommendation systems at Tencent, through high‑precision security models, reinforcement‑learning game AI, quantum‑ML studies, to large‑scale AIOps time‑series anomaly detection, offering practical lessons for anyone transitioning into machine learning.
This article presents a comprehensive guide to constructing a data‑driven AIOps platform, detailing its architecture, core components such as time‑series forecasting, anomaly detection, and pattern clustering, and recommending open‑source projects and practical considerations for implementing intelligent operations in enterprises.
The 2018 Gdevops Global Agile Operations Summit in Chengdu gathered industry experts who shared practical insights on AIOps implementation, sharding database ecosystems, DevOps adoption in traditional enterprises, large‑scale data management, ElasticSearch clustering, AWS blue‑green deployments, cloud database operations, Alibaba's double‑11 ops platform, 58 delivery mini‑program architecture, and scalable game service design.
At the 9th Global Operations Conference, Huawei Cloud’s chief architect Cai Xiaogang presented a three‑pronged AIOps strategy that combines large‑scale Kubernetes management, causal tracing in Serverless environments, multi‑source RCA analysis, and clustering‑based black‑box network packet inspection, showcasing how academia‑industry collaboration accelerates cloud‑native operations.
This article chronicles the author’s transition from a mathematics background to machine learning, detailing early challenges, hands‑on projects in recommendation systems, security, and AIOps, and sharing practical insights on feature engineering, model evaluation, and large‑scale anomaly detection.
This article summarizes Dr. Pei Dan's 2018 GOPS Shenzhen presentation on AIOps in traditional sectors, especially finance, covering industry outlook, AIOps concepts and value, practical deployment directions, common concerns, a recent challenge competition, and future prospects for autonomous IT operations.
Tencent’s integrated AIOps platform, ZhiYun, demonstrates how a unified operations PaaS—leveraging CMDB-driven object modeling, layered monitoring, and AI-powered data banking—can transform massive-scale service management from manual, fragmented processes into automated, business‑value‑focused operations across hundreds of thousands of devices.
This article outlines the concept, goals, principles, capability levels, platform architecture, team roles, common scenarios, and practical implementation path of AIOps, showing how AI can enhance quality, cost efficiency, and automation in modern IT operations.
This article examines Baidu's practical applications of machine‑learning‑driven intelligent operations, detailing three real‑world scenarios, the challenges of KPI anomaly labeling, the design of an automated detection framework, evaluation results across multiple datasets, and broader insights for scaling AIOps in production environments.
Operations professionals must align their skills with evolving market demands, recognize that the role will eventually be superseded by new technologies, and proactively transition toward longer‑lived technical domains like AI or higher‑value positions to stay relevant in the DevOps/AIOps era.
The article recounts the author’s 2017‑onward journey building an intelligent operations platform at Tencent, detailing challenges such as legacy thresholds, AIOps talent shortage, and lack of frameworks, and explains how a two‑stage hybrid unsupervised‑supervised model was devised to automatically detect anomalies across millions of KPI time‑series, enabling scalable root‑cause analysis and cost optimization.
This article outlines the challenges of modern IT operations, explains why traditional methods fall short, and presents a detailed AIOps roadmap—including anomaly detection, localization, root‑cause analysis, and prediction—drawn from Professor Pei Dan’s research and real‑world examples.
In this lecture, Prof. Pei Dan of Tsinghua University outlines the evolution of intelligent operations from rule‑based automation to machine‑learning‑driven AIOps, discusses data, feedback loops, and practical challenges, and calls for stronger collaboration between industry and academia to accelerate research and deployment.
In this comprehensive talk, Pei Dan outlines the technical and strategic roadmap for bringing AIOps to production, explains the challenges of anomaly detection, fault localization, root‑cause analysis and prediction, and demonstrates how to decompose complex operations problems into AI‑solvable tasks.
The article explains how AIOps—an AI‑powered IT operations platform that combines big‑data analytics, machine learning, and automation—revolutionizes traditional IT Ops by enabling rapid, accurate incident detection, root‑cause analysis, and self‑healing, thereby freeing CIOs to focus on strategic business value.
The article examines Alibaba's operations team responsibilities, traces its evolution from scripting tools to automated and AI‑enhanced practices, outlines a five‑step intelligent‑ops roadmap, and discusses the major technical and organizational challenges facing future large‑scale, unmanned operations.
This article explains how Alibaba has evolved its DevOps practice over a decade, detailing the layered architecture of its StarOps suite—including the foundational StarAgent, the Fortress (jump server), the Qingting file‑distribution system, and intelligent AIOps features—showing how automation, scalability, and AI‑driven monitoring enable stable, low‑cost operations for massive workloads such as Double 11.
This article examines the lifecycle of DevOps, its core principles, the rise of AIOps, the pivotal role of container technology, the emergence of SRE as a best‑practice, and how ChatOps represents the ultimate goal of simplifying complex operations through conversational interfaces.
This article details the challenges of traditional monitoring systems, the design and implementation of a custom high‑availability monitoring platform using a Golang‑based service tree, Raft‑backed storage, InfluxDB for time‑series data, and a modular architecture that supports Windows agents, third‑party reporting, and AI‑driven future enhancements.
At APMCon 2017, Tsinghua professor Pei Dan outlined the research challenges of intelligent operations, emphasizing the need to define clear algorithmic problems, foster open‑source collaboration between industry and academia, and build a problem‑library to accelerate AIOps adoption across enterprises.
Based on Gartner research, this article explains what AIOps is, how digital transformation drives its emergence, the platform’s big‑data and machine‑learning components, the factors and elements shaping it, and practical considerations for implementing AI‑powered IT operations.
Discover how integrating Heka with the ELK stack—Elasticsearch, Logstash, and Kibana—enables mobile game developers to efficiently collect, store, analyze, and visualize logs, offering rapid troubleshooting, automated alerts, and scalable AIOps capabilities that boost operational responsiveness and game performance.
