During the last few years, businesses across geographies and industries have faced an explosion of IT complexity driven by the implementation of new digital businesses and the drive for digitalization. Technology vendors have responded by providing public cloud platforms and the introduction of microservices.

Anomaly detection for a time timeseries. Figure: Martin Tveten

This has allowed businesses the tools to implement new solutions faster making applications no longer monolith applications deployed to a few physical servers. Now, applications consist of complex combinations of custom applications, packaged vendor applications, microservices, and containers with dependencies spanning industry value chains. Hence, any performance degradation in even a single component (out of thousands) can have ripple effects that disrupt a full value chain and massive financial consequences. 

Project Goal 

1) Find a way to combine numerical time series data and text-based log events to create insight into the performance of IT systems and alert about potential problems and its root cause, and 2) Do it in a completely automatic and general way such that the framework can be adapted and used with any kind of business, time series, and log data, with no additional tuning. 

FoU Challenges for NR in the project: 

– Multivariate anomaly detection algorithms using time series data across a vast array of IT processes; 

– Unsupervised event (log) analysis and prediction using natural language processing; and  

– Combination of time series and event (log) data to detect and predict anomalies. 

Name: PReVENT: PRediction + eVENT

Partner: AIMS Innovation

Period: 2021-2023

Funding: AIMS Innovation, The Research Council of Norway