Intelligent Cloud Operations using Event Streams and Analytics
OpenStack is an open source platform for building public and private clouds. It controls pools of compute, storage, and networking resources. With the ever growing amount of monitoring alerts, warnings, and complex errors generated by large data centres, cloud operators are turning to AIOps and NoOps as a paradigm which advocates that humans should only solve new complex problems while machines should resolve known, repetitive, and recognizable problems. This talk discusses two applications which use machine learning, data mining, analytics, and event stream processing to operate OpenStack. The first application looks into platform stability analysis using pattern matching, tracing, event streams, and time-series analysis. The second discusses an efficient damage detection technique which uses unit tests, abstract syntax trees, IDF, and the set cover algorithm to automatically generate decision trees to efficiently diagnose cloud platforms.
Short bio: Dr. Jorge Cardoso is Chief Architect for Cloud Operations and Analytics at Huawei’s German Research Center in Munich. Previously he worked for several major companies such as SAP Research (Germany) on the Internet of Services and the Boeing Company in Seattle (USA) on Enterprise Application Integration. He also gave lectures at the Karlsruhe Institute of Technology (Germany), University of Georgia (USA), University of Coimbra and University of Madeira (Portugal). He recently published his latest book titled “Fundamentals of Service Systems” with Springer. His current research involves the development of the next generation of Cloud Operations and Analytics using AI, Cloud Reliability and Resilience, and High Performance Business Process Management systems. More information can be found at http://jorge-cardoso.github.io/