Write a Blog >>
ICSE 2023
Sun 14 - Sat 20 May 2023 Melbourne, Australia

Incident management for cloud services is a complex process involving several steps and has a huge impact on both service health and developer productivity. Oncall engineers require significant amount of domain knowledge and manual effort for root causing and mitigation of production incidents. Recent advances in artificial intelligence has resulted in state-of-the-art large language models like GPT-3, which have been used to solve a variety of problems ranging from question answering to text summarization. In this work, we do the first large-scale study to evaluate the effectiveness of these models for helping engineers root cause and mitigate production incidents. We do a rigorous study on more than 40,000 incidents and compare several large language models in zero-shot, fine-tuned and multi-task setting using semantic and lexical metrics. Lastly, our human evaluation with actual incident owners show the efficacy and future potential of using artificial intelligence for resolving cloud incidents.

Fri 19 May

Displayed time zone: Hobart change

11:00 - 12:30
11:00
15m
Talk
Heterogeneous Anomaly Detection for Software Systems via Semi-supervised Cross-modal Attention
Technical Track
Cheryl Lee The Chinese University of Hong Kong, Tianyi Yang The Chinese University of Hong Kong, Zhuangbin Chen Chinese University of Hong Kong, China, Yuxin Su Sun Yat-sen University, Yongqiang Yang Huawei Technologies, Michael Lyu The Chinese University of Hong Kong
Pre-print
11:15
15m
Talk
Recommending Root-Cause and Mitigation Steps for Cloud Incidents using Large Language Models
Technical Track
Toufique Ahmed University of California at Davis, Supriyo Ghosh Microsoft, Chetan Bansal Microsoft Research, Thomas Zimmermann Microsoft Research, Xuchao Zhang Microsoft, Saravanakumar Rajmohan Microsoft 365
Pre-print
11:30
15m
Talk
Eadro: An End-to-End Troubleshooting Framework for Microservices on Multi-source Data
Technical Track
Cheryl Lee The Chinese University of Hong Kong, Tianyi Yang The Chinese University of Hong Kong, Zhuangbin Chen Chinese University of Hong Kong, China, Yuxin Su Sun Yat-sen University, Michael Lyu The Chinese University of Hong Kong
Pre-print
11:45
15m
Talk
LogReducer: Identify and Reduce Log Hotspots in Kernel on the Fly
Technical Track
Guangba  Yu Sun Yat-Sen University, Pengfei Chen Sun Yat-Sen University, Pairui Li Tencent Inc., Tianjun Weng Tencent Inc., Haibing Zheng Tencent, Yuetang Deng Tencent, Zibin Zheng School of Software Engineering, Sun Yat-sen University
Pre-print
12:00
15m
Talk
TraceArk: Towards Actionable Performance Anomaly Alerting for Online Service Systems
SEIP - Software Engineering in Practice
Zhengran Zeng Southern University of Science and Technology, Yuqun Zhang Southern University of Science and Technology, Yong Xu Microsoft Research, Minghua Ma Microsoft Research, Bo Qiao Microsoft Research, Wentao Zou , Qingjun Chen , Meng Zhang , Xu Zhang Microsoft Research, Hongyu Zhang The University of Newcastle, Xuedong Gao , Hao Fan , Saravan Rajmohan Microsoft 365, Qingwei Lin Microsoft Research, Dongmei Zhang Microsoft Research
12:15
7m
Talk
ActivFORMS: A Formally-Founded Model-Based Approach to Engineer Self-Adaptive Systems
Journal-First Papers
Danny Weyns KU Leuven, M. Usman Iftikhar KU Leuven / Linnaeus University
12:22
7m
Talk
Auto-Logging: AI-centred Logging Instrumentation
NIER - New Ideas and Emerging Results
Jasmin Bogatinovski Technical University Berlin, Odej  Kao Technische Universität Berlin
Pre-print