An unsupervised approach to online noisy-neighbor detection in cloud data centers
作者：
Highlights：
• An unsupervised, online detection algorithm for the noisy neighbor effect.
• It occurs when Virtual Machines compete for the same physical resources.
• Based on Dirichlet Process Gaussian Mixture Models for modeling resource usage.
• Using statistical distances (Kullback–Leibler) to measure similarity between DPGMMs.
• An anomaly is a higher difference between short-term models vs long-term ones.
摘要
•An unsupervised, online detection algorithm for the noisy neighbor effect.•It occurs when Virtual Machines compete for the same physical resources.•Based on Dirichlet Process Gaussian Mixture Models for modeling resource usage.•Using statistical distances (Kullback–Leibler) to measure similarity between DPGMMs.•An anomaly is a higher difference between short-term models vs long-term ones.
论文关键词：Anomaly detection,Virtual machine,Cloud computing,DPGMM,Noisy-neighbor effect,Similarity distances
论文评审过程：Received 31 January 2017, Revised 22 July 2017, Accepted 24 July 2017, Available online 25 July 2017, Version of Record 29 July 2017.
论文官网地址：https://doi.org/10.1016/j.eswa.2017.07.038
