Power Systems Engineering Research Center

S-87 Project Summary 

Machine Learning Approaches for Real-time Integration of Synchrophasor Data (S-87)

Summary Integration of phasor measurement units (PMUs) into power system operations has the potential to revolutionize the efficiency, resiliency, and security of the grid by offering operators an extremely detailed viewpoint into the system state. However, this integration has been slowed by the big-data challenges inherent in the use of PMU data. This proposal addresses these challenges by building data driven, machine learning (ML) models for the spatio-temporal dependencies in PMU data. These models will be used to develop advanced bad data detectors (BDDs), compression algorithms for long-term storage of PMU data, and to generate synthetic PMU data sets for use in an integrated energy management system (EMS) platform.
Academic Team Members Project Leader: Lalitha Sankar (Arizona State, lsankar@asu.edu)
Team Members: Le Xie (Texas A&M, le.xie@tamu.edu), Anamitra Pal (Arizona State, Anamitra.Pal@asu.edu
Industry Team Members Ruisheng Diao (GEIRINA), Xiaohu Zhang (GEIRINA), Phil Hart (GE); Liwei Hao (GE), Matthew Rhodes (SRP), Alan Engelmann (ComEd), Evangelos Farantatos (EPRI), Mahendra Patel (EPRI, mpatel@epri.com), George Stefopoulos (NYPA), Qiang Zhang (ISO-NE), Harvey Scribner (SPP), Yingchen Zhang (NREL), Santosh Veda (NREL), Mark Westendorf (MISO) 
Project Period July 1, 2019 to August 31, 2021