@inproceedings{f9bf84c3bd4b40018d1b90583386c2b2,
title = "Identifying linked incidents in large-scale online service systems",
abstract = "In large-scale online service systems, incidents occur frequently due to a variety of causes, from updates of software and hardware to changes in operation environment. These incidents could significantly degrade system's availability and customers' satisfaction. Some incidents are linked because they are duplicate or inter-related. The linked incidents can greatly help on-call engineers find mitigation solutions and identify the root causes. In this work, we investigate the incidents and their links in a representative real-world incident management (IcM) system. Based on the identified indicators of linked incidents, we further propose LiDAR (Linked Incident identification with DAta-driven Representation), a deep learning based approach to incident linking. More specifically, we incorporate the textual description of incidents and structural information extracted from historical linked incidents to identify possible links among a large number of incidents. To show the effectiveness of our method, we apply our method to a real-world IcM system and find that our method outperforms other state-of-the-art methods.",
keywords = "Incident management, Link prediction, Linked incidents, Online service system",
author = "Yujun Chen and Xian Yang and Hang Dong and Xiaoting He and Hongyu Zhang and Qingwei Lin and Junjie Chen and Pu Zhao and Yu Kang and Feng Gao and Zhangwei Xu and Dongmei Zhang",
note = "Funding Information: We thank our colleagues at Microsoft Azure groups who developed the incident management system and helped us learn the system: Feng Gao, Jeffery Sun, Pochian Lee, Li Yang, Zhangwei Xu. This work is supported by the National Natural Science Foundation of China (NSFC) under Grant No. 61702107. Hongyu Zhang{\textquoteright}s work is supported by Australian Research Council (ARC) DP200102940.; 28th ACM Joint Meeting European Software Engineering Conference and Symposium on the Foundations of Software Engineering, ESEC/FSE 2020 ; Conference date: 08-11-2020 Through 13-11-2020",
year = "2020",
month = nov,
day = "8",
doi = "10.1145/3368089.3409768",
language = "English",
series = "ESEC/FSE 2020 - Proceedings of the 28th ACM Joint Meeting European Software Engineering Conference and Symposium on the Foundations of Software Engineering",
publisher = "Association for Computing Machinery (ACM)",
pages = "304--314",
editor = "Prem Devanbu and Myra Cohen and Thomas Zimmermann",
booktitle = "ESEC/FSE 2020 - Proceedings of the 28th ACM Joint Meeting European Software Engineering Conference and Symposium on the Foundations of Software Engineering",
address = "United States",
}