U.S. Department of Energy

Pacific Northwest National Laboratory

Building the Analysis in Motion Infrastructure

Publish Date: 
Wednesday, June 3, 2015
Today the ability to make sense of data is foundational to all discoveries, innovations, and decision making; the outcome of our work often critically depends on the speed and adaptability of the analysis and interpretation processes we employ. While much progress has been made in automating the analysis of standard events, little is available to support complex or rare event analysis situations that require human knowledge and ingenuity in addition to high-speed, high-volume analytical and interpretive processes. Consider examples such as emergency response, scientific discovery, national security, or critical business decisions where humans play a key role in analyzing facts as the situation evolves. The Analysis in Motion (AIM) Initiative is developing streaming analysis applications and an infrastructure to support this new analysis paradigm for high-volume, high-velocity data situations. This report describes the first 12 months of AIM infrastructure development. The work discussed can be broken into three principal stages: selection of key enabling technologies and their initial integration, extension of the original design to support multiple users, and transition to the OpenStack-based Pacific Northwest National Laboratory (PNNL) Institutional Research Cloud to scale past the limitations of the initial single-server hosting model.
Kleese van Dam, K., Sharma, P., LaMothe, R.R., Zarzhitsky, D.V., Vishnu, A., Stephan, E., Smith, W.P., Elsethagen, T.D., Thomas, M. 2015. Building the Analysis in Motion Infrastructure. PNNL Technical Report, PNNL-24340, June 2015. DOI: 10.13140/RG.2.1.1701.1368.
| Pacific Northwest National Laboratory