Abstract
A two-stage machine learning-based approach for creating synthetic phasor measurement unit (PMU) data is proposed in this article. This approach leverages generative adversarial networks (GAN) in data generation and incorporates neural ordinary differential equation (Neural ODE) to guarantee underlying physical meaning. We utilize this approach to synthetically create massive eventful PMU data, which would otherwise be difficult to obtain from the real world due to the critical energy infrastructure information (CEII) protection. To illustrate the utility of such synthetic data for subsequent data-driven methods, we specifically demonstrate the application of using synthetic PMU data for event classification by scaling up the real data set. The addition of the synthetic PMU data to a small set of real PMU data is shown to have improved the event classification accuracy by 2 to 5 percent.
Highlights
P HASOR Measurement Units (PMU) have been deployed in the bulk transmission grid at an accelerated pace after the 2003 U.S Blackout [1]
It should be noted that all model-based event classification approaches would encounter certain difficulties when there is a significant gap between the available system model and the physical reality [3], [4]
3) Event Classification Improvement: We show that the created synthetic data can be used to enrich the training data set, thereby improving the event classification accuracy of four popular machine-learning based approaches, especially when the size of the training data set is very limited as is always true in the real practice
Summary
P HASOR Measurement Units (PMU) have been deployed in the bulk transmission grid at an accelerated pace after the 2003 U.S Blackout [1]. Even regardless of data quality issues, a major hurdle to apply these machine-learning based classifiers is usually a lack of a sufficient data set for training It is well-known that more eventful data usually lead to a better classification accuracy [5], [6]. As discussed above, an accurate system model in reality is currently not available for most bulk power systems, while this situation will most likely remain unchanged in the foreseeable future [3], [4] To this end, this article aims at improving the classification accuracy of machine learning-based event classifiers by scaling up the limited available eventful PMU data set.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
