Chen Yu
Baidu
18 Papers
12 Citations
Chen Yu is an academic researcher from Baidu. The author has contributed to research in topics: Computer science & Kalman filter. The author has an hindex of 5, co-authored 15 publications.
Chat about Author
Papers
Syslog processing for switch failure diagnosis and prediction in datacenter networks
Shenglin Zhang,Weibin Meng,Jiahao Bu,Sen Yang,Ying Liu,Dan Pei,Jun Xu,Chen Yu,Hui Dong,Qu Xianping,Lei Song +10 more
- 14 Jun 2017
TL;DR: A frequent template tree (FT-tree) model is proposed in which frequent combinations of (syslog) words are identified and then used as message templates and empirically extracts message templates more accurately than existing approaches, and naturally supports incremental learning.
89
FUNNEL: Assessing Software Changes in Web-Based Services
Shenglin Zhang,Ying Liu,Dan Pei,Chen Yu,Qu Xianping,Shimin Tao,Zang Zhi,Xiaowei Jing,Mei Feng +8 more
TL;DR: An automated tool for rapid and robust impact assessment of software changes in large Internet-based services, FUNNEL, which achieves a 98.21 percent precision, high robustness, fast detection speed, and shows its capability in detecting unexpected behavior changes.
48
FluxRank: A Widely-Deployable Framework to Automatically Localizing Root Cause Machines for Software Service Failure Mitigation
Ping Liu,Chen Yu,Xiaohui Nie,Jing Zhu,Shenglin Zhang,Kaixin Sui,Ming Zhang,Dan Pei +7 more
- 01 Oct 2019
TL;DR: This paper presents FluxRank, a widely-deployable framework that can automatically and accurately localize the root cause machines, so that some actions can be triggered to mitigate the service failure.
46
Mining causality graph for automatic web-based service diagnosis
Xiaohui Nie,Youjian Zhao,Kaixin Sui,Dan Pei,Chen Yu,Qu Xianping +5 more
- 01 Dec 2016
TL;DR: An automatic diagnosis system based on causality graph to help system operators find the root causes of web-based services failure and controlled experiments show that theRoot causes can be ranked in top 3 with 100% accuracy after countable learning iterations.
24
Inter-country comparisons of energy system performance with the energy trilemma index: An ensemble ranking methodology based on the half-quadratic theory
TL;DR: In this article , the authors proposed an ensemble ranking methodology based on the half-quadratic theory for measuring and comparing country-wide energy system performance using the Energy Trilemma Index (ETI) data.
12