Interactive Physics Data Analysis Using Streaming Grid Technology

High Energy Physics (HEP) experiments face major challenges in building interactive analysis environments for the unprecedented volume of data that will be gathered in the next generation of experiments at the Large Hadron Collider (LHC) and other accelerators. The current generation of HEP Grid infrastructures is largely aimed at the initial event reconstruction and analysis phases and may not be able to provide the flexibility and interactivity to support distributed collaborative physics analysis. This project will combine a novel information architecture with a high-performance, fault-tolerant, Grid messaging infrastructure, in order to support an analysis environment built directly on data streaming rather than files. A Federated Hierarchical Filter Grid (FHFG) architecture, which has a variety of commercial and research applications and has been successfully implemented for information retrieval, will be used for this purpose. Phase I will produce and evaluate a prototype FHFG aimed at the initial data reduction problem for the LHC. Existing software will leveraged as far as possible. Lessons from the prototype will be combined with current best practices in Grid technology to produce a FHFG design that will support particle physics research and other identified applications. Commercial Applications And Other Benefits as described by the Applicant: A novel architecture for particle physics data analysis, which leverages existing DOE Grid and physics analysis investments, should also find commercial application in the conferencing and multi-media industry, information retrieval, homeland security (critical infrastructure), and bioinformatics.