TY - GEN
T1 - PRAD
T2 - 2022 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
AU - Xiong, Zhiying
AU - Fan, Qilin
AU - Wang, Kai
AU - Li, Xiuhua
AU - Zhang, Xu
AU - Xiong, Qingyu
N1 - Publisher Copyright:
© 2022 IEEE.
PY - 2022
Y1 - 2022
N2 - 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.
AB - 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.
KW - KPI anomaly detection
KW - Multivariate time series
KW - graph attention network
KW - temporal convolutional attention network
UR - https://www.scopus.com/pages/publications/85168126228
U2 - 10.1109/SmartWorld-UIC-ATC-ScalCom-DigitalTwin-PriComp-Metaverse56740.2022.00075
DO - 10.1109/SmartWorld-UIC-ATC-ScalCom-DigitalTwin-PriComp-Metaverse56740.2022.00075
M3 - 会议稿件
AN - SCOPUS:85168126228
T3 - Proceedings - 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
SP - 384
EP - 391
BT - Proceedings - 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
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 15 December 2022 through 18 December 2022
ER -