Networking Research & Infrastructure
Panorama 360
Description
The Panorama 360 project provides a resource for the collection, analysis, and sharing of performance data about end-to-end scientific workflows executing on Department of Energy facilities. In order to foster collaboration with other program participants and the broader community, the project will develop and publicize data formats and APIs to upload, download and query data. All data captured and analysis tools developed in this project are released open source and made available in GitHub.
RENCI's Role
Panorama 360 is an expansion of PANORAMA. RENCI has collaborated on both projects with the University of Southern California (the lead institution) and other partners.
For Panorama 360, the RENCI team is initially focusing on automating workflows for three U.S. Department of Energy applications that process streaming data, combine data streams, and perform large-scale calculations emblematic of parameter sweeps. The team is also advancing systems to adapt infrastructure and workflows in response to detected anomalies.
Panorama 360 uses supervised and unsupervised machine learning approaches to analyze, synthesize, and characterize the performance of various elements of the scientific workflow. These tools can bring value by detecting anomalies, identifying bottlenecks and sources of failure, and guiding adaptations and performance optimizations.
To foster collaboration with program participants and the broader community, the project will support an open source community repository for multiple research functions and develop and publicize data formats and APIs to upload, download, and query data. Collaborators will also share their experiences and best practices through discussions, demonstrations, and tutorials so that others can leverage the data, tools, and methodologies.
