Uncertainty-aware inverse modeling for federated scientific discovery across DOE facilities
Explore the source record for details and available documents.
Schotthoefer, Steffen [ORNL] (ORCID:00000002156965↗
Engineering topics
McDonnell, Marshall [ORNL] (ORCID:0000000237132117)
Publications and source records attributed to McDonnell, Marshall [ORNL] (ORCID:0000000237132117).
Automation for Grid Interconnected Laboratory Emulation
As computational capabilities improve, digital twins are becoming vital for evaluating equipment realistically in laboratories. This paper outlines a digital twin architecture for the power grid, employing electromagnetic transient (EMT) simulation alongside real-time simulation of power hardware and hierarchical control systems. EMT simulation occurs on a high-performance computing server for scalability. Additionally, the paper describes a workflow and real-time data streaming software facilitating connectivity among EMT simulation, hierarchical control systems, and power hardware. This software enables automated equipment connectivity in the laboratory for realistic evaluations, aiding in identifying necessary upgrades for both equipment control systems and the power grid.
Marthi, Phani Ratna Vanamali [ORNL] (ORCID:0000000↗
Privacy Preserving Federated Learning for Advanced Scientific Ecosystems
We present a framework to provide privacy preserving (PP) federating learning (FL) across multiple computational and experimental facilities. This work joins the compute capabilities of National Energy Research Scientific Computing Center (NERSC) and Oak Ridge National Laboratory Research Cloud (ORC) with simulated experimental data, such as those produced at the SLAC National Accelerator Laboratory and Spallation Neutron Source (SNS). We describe the software infrastructure developed to provide privacy for computational and experimental networks. We developed algorithmic privacy across the federated system by embedding database security, computation, and communication into the federation architecture, utilizing scientific tools developed by the experimental community.
Archibald, Rick [ORNL] (ORCID:0000000245389780)↗