• SLS machine learning best practice: batch timing anomaly detection


    1. High frequency detection scene 1.1 scenario I There are n machines in the cluster, and M timing indicators (CPU, memory, IO, traffic, etc.) in each machine. If you model each timing curve separately, you need to write too many repeated SQL, and the calculation consumption of the platform is particularly large. How to better […]

  • Fast implementation of anomaly inspection in SLS


    I. Research on Related Algorithms 1.1 Common Open Source Algorithms Yahoo:EGADS FaceBook:Prophet Baidu:Opprentice Twitter:Anomaly Detection Redhat:hawkular Ali+Tsinghua:Donut Tencent:Metis Numenta:HTM CMU:SPIRIT Microsoft:YADING Linkedin: Improved version of SAX Netflix:Argos NEC:CloudSeer NEC+Ant:LogLens MoogSoft: A start-up company. The content is very good for your reference. 1.2 Anomaly Detection Based on Statistical Method Based on the statistical method, the results […]

  • SLS Machine Learning Best Practice: Batch Sequence Anomaly Detection


    1. High Frequency Detection Scene Scenario 1.1 Cluster has N machines, each machine has M time series indicators (CPU, memory, IO, traffic, etc.). If we model each time series curve separately, we need to write too many repetitive SQL by hand, and the computing cost of the platform is very high. How to better use […]

  • Best Practice of SLS Machine Learning: Log Clustering + Abnormal Alarm


    1. What are the hammers in your hands? Around the logs, mining more value has always been our team’s concern. Based on the original log real-time query, SLS has improved the following functions in the field of DevOps this year: Context Query Real-time Tail and Intelligent Clustering to Improve Question Investigation Efficiency Providing anomaly detection […]