Skip to main navigation Skip to search Skip to main content

PRAD: Unsupervised KPI Anomaly Detection by Joint Prediction and Reconstruction of Multivariate Time Series

  • Zhiying Xiong*
  • , Qilin Fan*
  • , Kai Wang
  • , Xiuhua Li*
  • , Xu Zhang
  • , Qingyu Xiong*
  • *Corresponding author for this work
  • Chongqing University
  • School of Computer Science and Technology, Harbin Institute of Technology
  • Harbin Institute of Technology Weihai
  • Haihe Laboratory of Information Technology Application Innovation
  • University of Exeter

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Detecting anomalies for key performance indicator (KPI) data is of paramount importance to ensure the quality and reliability of network services. However, building the anomaly detection system for KPI is challenging due to the scarcity of abnormal labels and highly dynamic or even unseen patterns. In this paper, we propose an unsupervised KPI anomaly detection framework named PRAD by jointly optimizing prediction-based and reconstruction-based modules. Specifically, PRAD employs two parallel graph attention networks (GATs) to learn metric-oriented and time-oriented relationships. A temporal convolutional attention network (TCAN) is used to capture complex long-term dependencies. Furthermore, to tackle the overfitting issue in the variational auto-encoder (VAE), PRAD designs a reconstruction-based module that combines VAE with a generative adversarial network (GAN). The experimental results on the two public datasets demonstrate that the proposed PRAD outperforms existing anomaly detection methods.

Original languageEnglish
Title of host publicationProceedings - 2022 IEEE SmartWorld, Ubiquitous Intelligence and Computing, Autonomous and Trusted Vehicles, Scalable Computing and Communications, Digital Twin, Privacy Computing, Metaverse, SmartWorld/UIC/ATC/ScalCom/DigitalTwin/PriComp/Metaverse 2022
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages384-391
Number of pages8
ISBN (Electronic)9798350346558
DOIs
StatePublished - 2022
Externally publishedYes
Event2022 IEEE SmartWorld, 19th IEEE International Conference on Ubiquitous Intelligence and Computing, 2022 IEEE International Conference on Autonomous and Trusted Vehicles Conference, 22nd IEEE International Conference on Scalable Computing and Communications, 2022 IEEE International Conference on Digital Twin, 8th IEEE International Conference on Privacy Computing and 2022 IEEE International Conference on Metaverse, SmartWorld/UIC/ATC/ScalCom/DigitalTwin/PriComp/Metaverse 2022 - Haikou, China
Duration: 15 Dec 202218 Dec 2022

Publication series

NameProceedings - 2022 IEEE SmartWorld, Ubiquitous Intelligence and Computing, Autonomous and Trusted Vehicles, Scalable Computing and Communications, Digital Twin, Privacy Computing, Metaverse, SmartWorld/UIC/ATC/ScalCom/DigitalTwin/PriComp/Metaverse 2022

Conference

Conference2022 IEEE SmartWorld, 19th IEEE International Conference on Ubiquitous Intelligence and Computing, 2022 IEEE International Conference on Autonomous and Trusted Vehicles Conference, 22nd IEEE International Conference on Scalable Computing and Communications, 2022 IEEE International Conference on Digital Twin, 8th IEEE International Conference on Privacy Computing and 2022 IEEE International Conference on Metaverse, SmartWorld/UIC/ATC/ScalCom/DigitalTwin/PriComp/Metaverse 2022
Country/TerritoryChina
CityHaikou
Period15/12/2218/12/22

Keywords

  • KPI anomaly detection
  • Multivariate time series
  • graph attention network
  • temporal convolutional attention network

Fingerprint

Dive into the research topics of 'PRAD: Unsupervised KPI Anomaly Detection by Joint Prediction and Reconstruction of Multivariate Time Series'. Together they form a unique fingerprint.

Cite this