Abstract: Software-intensive systems provide various services to millions of users, thus requiring high availability and reliability. These systems often produce a large volume of logs to record runtime status and events. Log Intelligence, which utilizes AI/ML technologies to analyze systems logs for more effective system operation and maintenance, has drawn much attention from both researchers and practitioners in recent decades. In this talk, I will first introduce the research landscape of fault detection and Log Intelligence. I will then present a suite of Log Intelligence-based fault detection models. I will also discuss the challenges and opportunities in future research on Log Intelligence.

Ying Li is currently a professor in the school of Software and Microelectronics, Peking University, China. Before joining PKU in 2012, she worked as a STSM and senior manager leading the department of distributed computing in IBM China Research Lab. She conducted several global projects that the leading-edge technologies have been transformed to IBM commercial software products and was rewarded with "IBM Global Research Accomplishment Award" twice and "CIO Leadership Award". She filed 30+ US/CN granted patents and published 90+ academic papers and served as PC member of several international conferences.

Abstract: The continuous increase in complexity and scale of cloud platforms, together with the evolving diversity of services, are forcing AIOps to face platform characteristics that can significantly impact the availability of cloud services. This talk will start from how to understand the running behavior of cloud platforms and services in terms of resource usage and request execution, and then address issues of AIOps with a focus on how the field of operation engineering can become more efficient through streaming processing, active learning, and knowledge-enhanced dialogue generation.

Pinjia He is the Assistant Professor of The Chinese University of Hong Kong, Shenzhen. He has been a postdoctoral researcher in the Computer Science Department at ETH Zurich after receiving his PhD degree from the Chinese University of Hong Kong in 2018. His main research interests include software engineering, software testing, software security, AIOps, and Trustworthy AI. His research appeared in top computer science venues, such as ICSE, ESEC/FSE, ASE, ISSTA, and OSDI. He received the first IEEE Open Software Services Award, an ISSRE Most Influential Paper Award. The LogPAI project led by him has been starred 3,000+ times on GitHub and downloaded 80,000+ times by 380+ organizations.

Abstract: In recent decades, software logs have become imperative in the reliability assurance mechanism of many software systems. As modern software is evolving into a large scale, the volume of logs has increased rapidly. In the past ten years, we have developed LogPAI, an open-source automated log analysis toolkit. LogPAI provides log datasets and four main components: logging, log compression, log parsing, and log mining. LogPAI has been well recognized by both academia and industry. This talk intends to revisit automated log analysis by revealing the stories behind the scenes for LogPAI.