Data-driven Approach to Resilient Online Service Systems

点击翻译按钮获取中文摘要

This project aims to develop a data-driven approach to improving the resilience of online service systems. Many software systems are now provided as online services via the Internet on a 24/7 basis. Although a lot of effort has been devoted to service quality assurance, in reality, online service systems still encounter many incidents and fail to satisfy user requests. This project expects to develop innovative data-driven methods for effective fault identification, fault localization, and failure prediction. Expected outcomes of this project include novel techniques and tools for maintaining online service systems. This project will provide significant benefits, such as improving the resilience and reliability of our cyber infrastructure.