Sinnott Murphy is research engineer and machine learning lead in the Cybersecurity Science and Simulation Group in NREL's Energy Security and Resilience Center. He has been at NREL since 2019.
Murphy's research is at the intersection of machine learning, cybersecurity, and power systems. He leads efforts to detect and mitigate cybersecurity risks to power systems through the application of verifiable computation methods from cryptography. He also leads modeling efforts to quantify meteorological dependence of natural gas supply, thermal generator outages, and load. Together this work is being used to improve assessment of power system adequacy and resilience risks on both planning and operational timescales.
Murphy has contributed to multiple NREL packages related to probabilistic resource adequacy assessment, including the Probabilistic Resource Adequacy Suite, and has been awarded software records for capabilities developed under the North American Energy Resilience Model project.
Machine learning applications for grid reliability, security, and resilience
Online learning and optimization in distributed energy systems
Verifiable computation for cybersecurity threat mitigation
Ph.D., Engineering and Public Policy, Carnegie Mellon University
M.S., Transportation Technology and Policy, University of California, Davis
M.S., Agricultural and Resource Economics, University of California, Davis
B.S., Biochemistry and Molecular Biology, University of California, Davis
Contractor, PJM Interconnection (2017–2019)
Contractor, North American Electric Reliability Corporation (2015–2016)
Researcher, Institute of the Environment and Sustainability, University of California, Los Angeles (2012–2014)
Resource Adequacy Implications of Temperature-Dependent Electric Generator Availability, Applied Energy (2020)
Resource Adequacy Risks to the Bulk Power System in North America, Applied Energy (2018)