Skip to content

Latest commit

 

History

History
156 lines (124 loc) · 9.42 KB

README_zh-CN.md

File metadata and controls

156 lines (124 loc) · 9.42 KB
Raw

Aiops学习资源

English | 简体中文

AIOps(Artificial Intelligence for IT Operations)，即智能运维，是将人工智能的能力与运维相结合，通过机器学习的方法来提升运维效率。

笔者有幸在大学毕业加入世界领先的通信设备制造商，并与中国运营商深度合作，作为主要核心设计者设计了运营商大规模数据中心的多套AIOPS系统，在这将之前的资料分享出来，希望能尽自己的微薄之力推动社区发展。

最近更新日期为：2022/1

拒绝白嫖，欢迎star！

一个人可以走得很快，只有一群人才能走得更远。笔者组建了个AIOPS技术交流的群，群友遍布硅谷，新加坡，腾讯，阿里，浙大等等，欢迎志同道合的朋友与我联系加入！


           

1. Aiops系统落地实践

算法架构：https://zhuanlan.zhihu.com/p/466955597?
工程架构：https://zhuanlan.zhihu.com/p/511095084
API风险检测系统：https://zhuanlan.zhihu.com/p/548450688
相关资料收集：https://github.com/LiaoWenzhe/BigdataAi
相关技术专栏：https://www.zhihu.com/column/c_1471819989803700224

2. 时间序列分类

1. https://mp.weixin.qq.com/s/AjE7uP7ApVPyL_HdQDkk5g
2. Correlative Channel-Aware Fusion for Multi-View Time Series Classification
3. Learnable Dynamic Temporal Pooling for Time Series Classification
4. ShapeNet: A Shapelet-Neural Network Approach for Multivariate Time Series Classification
5. Joint-Label Learning by Dual Augmentation for Time Series Classification
6. Learning Representations for Incomplete Time Series Clustering
7. Explainable Multivariate Time Series Classification: A Deep Neural Network Which Learns To Attend To Important Variables As Well As Time Intervals
8. Temporal Phenotyping using Deep Predictive Clustering of Disease Progression
9.《Clustering Intrusion Detection Alarms to Support Root Cause Analysis》
10.《Robust and Rapid Clustering of KPIs for Large-Scale Anomaly Detection》
11.《A Density-Based Algorithm for Discovering Clusters》
12.《YADING: Fast Clustering of Large-Scale Time Series Data》
13.《k-Shape: Efficient and Accurate Clustering of Time Series》
14.《Probabilistic Alert Correlation》
15. 《Clustering Interval-Censored Time-Series for Disease Phenotyping》

3. 时间序列异常检测：

1. https://zhuanlan.zhihu.com/p/108843309
2. Time Series Anomaly Detection with Multiresolution Ensemble Decoding
3. Outlier Impact Characterization for Time Series Data
4. F-FADE: Frequency Factorization for Anomaly Detection in Edge Streams
5. Timeseries Anomaly Detection using Temporal Hierarchical One-Class Network
6.《Time-Series Anomaly Detection Service at Microsof》
7.《Unsupervised Anomaly Detection via Variational Auto-Encoder for Seasonal KPIs in Web Applications》
8.《Anomaly Detection in Streams with Extreme Value Theory》
9. https://github.com/yzhao062/anomaly-detection-resources
13. https://zr9558.com/2018/11/30/timeseriespredictionfbprophet/
15. Graph Neural Network-Based Anomaly Detection in Multivariate Time Series
10. https://zhuanlan.zhihu.com/p/150316014
11. https://www.zhihu.com/question/29507442/answer/1212624591
12. https://www.zhihu.com/question/283641524/answer/1211966582
16. https://keras.io/examples/timeseries/timeseries_transformer_classification/
17. https://blog.csdn.net/Liao_Wenzhe/article/details/119796325
18. https://blog.csdn.net/Liao_Wenzhe/article/details/119732579
19.《Robust Random Cut Forest Based Anomaly Detection On Streams》
20. https://mp.weixin.qq.com/s?__biz=MzA5NTQ5MzE5OQ%3D%3D&chksm=8b685c6cbc1fd57a27a476fe1f15a59b25f4928094b2a49b7e8f054ed0cc5dc29a243173bf2e&idx=1&mid=2653057356&scene=21&sn=85d82226c7f66685ec8cf486569976dc#wechat_redirect

4. 关联分析：

 1.《HotSpot: Anomaly Localization for Additive KPIs With Multi-Dimensional Attributes》
 2.《CoFlux: Robustly Correlating KPIs by Fluctuations for Service Troubleshooting》
 3.《Correlating Events with Time Series for Incident Diagnosis》
 4.《Detecting Leaders from Correlated Time Series》
 5. Deep reconstruction of strange attractors from time series
 6. High-recall causal discovery for autocorrelated time series with latent confounders
 7. Statistical control for spatio-temporal MEG/EEG source imaging with desparsified mutli-task Lasso
 8. Normalizing Kalman Filters for Multivariate Time Series Analysis

5. 告警收敛：

  1.《Clustering Intrusion Detection Alarms to Support Root Cause Analysis》
  2.《CMining Alarm Clusters to Improve Alarm Handling Efficiency》
  3.《Automatically and Adaptively Identifying Severe Alerts for Online Service Systems》
  4.《Understanding and Handling Alert Storm for Online Service Systems》
  5.《CoFlux: Robustly Correlating KPIs by Fluctuations for Service Troubleshooting》
  6.《Aggregation and Correlation of Intrusion-Detection Alerts》
  7.《Generic and Robust Localization of Multi-Dimensional Root Causes》
  8.《Probabilistic Alert Correlation》

6. 根因分析：

  1.《Clustering Intrusion Detection Alarms to Support Root Cause Analysis》
  2.《FluxRank: A Widely-Deployable Framework to Automatically Localizing Root Cause Machines for Software Service Failure Mitigation》
  3.《Adtributor: Revenue debugging in advertising systems》
  4.《HotSpot: Anomaly Localization for Additive KPIs With Multi-Dimensional Attributes》

7. 时间序列补全：

  1.《Dynamic Nonlinear Matrix Completion for Time-Varying Data Imputation》
  2. Generative Semi-Supervised Learning for Multivariate Time Series Imputation

8. 时间序列预测：

  1. Deep Switching Auto-Regressive Factorization: Application to Time Series Forecasting
  2. Dynamic Gaussian Mixture Based Deep Generative Model for Robust Forecasting on Sparse Multivariate Time Series
  3. Temporal Latent Autoencoder: A Method for Probabilistic Multivariate Time Series Forecasting
  4. Synergetic Learning of Heterogeneous Temporal Sequences for Multi-Horizon Probabilistic Forecasting
  5. Time-Series Event Prediction with Evolutionary State Graph
  6. Probabilistic Time Series Forecasting with Shape and Temporal Diversity
  7. Benchmarking Deep Learning Interpretability in Time Series Predictions
  8. Adversarial Sparse Transformer for Time Series Forecasting
  9. Deep Rao-Blackwellised Particle Filters for Time Series Forecasting

9. 时间关系因果

  1. Clinical Temporal Relation Extraction with Probabilistic Soft Logic Regularization and Global Inference
  2. Time Series Domain Adaptation via Sparse Associative Structure Alignment
  3. Transformer-Style Relational Reasoning with Dynamic Memory Updating for Temporal Network Modeling

10. 时间神经网络

  1. Bridging Towers of Multi-Task Learning with a Gating Mechanism for Aspect-Based Sentiment Analysis and Sequential Metaphor Identification
  2. C2F-FWN: Coarse-to-Fine Flow Warping Network for Spatial-Temporal Consistent Motion Transfer
  3. Inductive Graph Neural Networks for Spatiotemporal Kriging
  4. Temporal-Coded Deep Spiking Neural Network with Easy Training and Robust Performance
  5. Continuous-Time Attention for Sequential Learning
  6. Temporal Spike Sequence Learning via Backpropagation for Deep Spiking Neural Networks
  7. ARMA Nets: Expanding Receptive Field for Dense Prediction
  8. Learning Long-Term Dependencies in Irregularly-Sampled Time Series
  9. Temporal Spike Sequence Learning via Backpropagation for Deep Spiking Neural Networks
  10. Learnable Group Transform For Time-Series

11. 时空知识图谱/时空预测

  1. ChronoR: Rotation Based Temporal Knowledge Graph Embedding
  2. Learning from History: Modeling Temporal Knowledge Graphs with Sequential CopyGeneration Networks
  3. Neural Latent Space Model for Dynamic Networks and Temporal Knowledge Graphs
  4. CaSPR: Learning Canonical Spatiotemporal Point Cloud Representations
  5. ARMA Nets: Expanding Receptive Field for Dense Prediction
  6. Unsupervised Transfer Learning for Spatiotemporal Predictive Networks

12. 时间序列数据处理

  1. Set Functions for Time Series
  2. Learning from Irregularly-Sampled Time Series: A Missing Data Perspective

13. 其他资源：

  1.《Forecasting at Scale》
  2.《Box-Cox Transformation for Simple Linear Regression》
  3. https://github.com/NetManAIOps
  4. https://github.com/AI-Sphere/Awesome-Noah
  5. https://github.com/Tencent/Metis
  6. https://github.com/linjinjin123/awesome-AIOps
  7. 微信公众号：智能运维前沿
  8. 微信公众号：时序人
  9. https://blog.csdn.net/Liao_Wenzhe/article/details/119579709
  10. https://blog.csdn.net/Liao_Wenzhe/article/details/11933514