A Multivariate KPIs Anomaly Detection Framework With Dynamic Balancing Loss Training
- 28 November 2022
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Network and Service Management
- Vol. 20 (2) , 1418-1429
Abstract
Anomaly detection on multivariate KPIs (Key Performance Indicators, such as CPU utilization, sockets status, and HTTP requests per second) is of utmost importance to the systems’ reliability. Unsupervised methods have been of considerable interests and have significantly progressed due to their superior effectiveness. However, the state-of-art unsupervised anomaly detection methods still suffer from high false or missed alarm rates. To this end, in this paper, we propose MM, a practical Multivariate KPIs anomaly detection framework following the principles of Multi-task learning with the proposed dynamic balancing loss function. To capture KPIs’ characteristics to the most extent, we simultaneously train multiple sequential autoencoders with different connections based on a designed semi-Random Connection Recurrent Neural Network (sRC-RNN). These autoencoders can be treated as different reconstruction tasks while training. Furthermore, we propose a dynamic loss function to adaptively balance the tasks’ weights. Extensive experiments show that MM outperforms the state-of-art unsupervised multivariate KPIs anomaly detection algorithms and achieves an average F1-score of 0.95 on two public machine-level KPIs datasets and 0.96 on an internal container-level KPIs dataset.Keywords
Funding Information
- Hunan Young Talents Grant China (2020RC3027)
- Natural Science Foundation of Hunan Province, China (2021JJ40688)
- Training Program for Excellent Young Innovators of Changsha, China (kq2206001)
- General Scientific Research Project of Education Department of Hunan Province (19C0140)
This publication has 27 references indexed in Scilit:
- Anomaly Detection in Streams with Extreme Value Theory2017
- Online anomaly detection on the webscope S5 dataset: A comparative study2017
- Online and Scalable Unsupervised Network Anomaly Detection MethodIEEE Transactions on Network and Service Management, 2016
- Network Volume Anomaly Detection and Identification in Large-Scale Networks Based on Online Time-Structured Traffic Tensor TrackingIEEE Transactions on Network and Service Management, 2016
- Deep Residual Learning for Image Recognition2016
- Recurrent Residual Learning for Sequence Classification2016
- Opprentice2015
- Generic and Scalable Framework for Automated Time-series Anomaly Detection2015
- A provider-side view of web search response timeACM SIGCOMM Computer Communication Review, 2013
- Extreme Value Theory2012