Deep Learning Based Frequency Stability Assessment in Power Grid with High Renewables
Paper
Paper/Presentation Title | Deep Learning Based Frequency Stability Assessment in Power Grid with High Renewables |
---|---|
Presentation Type | Paper |
Authors | Zhao, Yinfeng (Author), You, Shutang (Author), Mandich, Mirka (Author), Li, Hongyu (Author), Fabus, Summer (Author), Cui, Yi (Author), Xiao, Huangqing (Author), Zhu, Lin (Author), Zeng, Chujie (Author), Liu, Yilu (Author), Jiang, Huaiguang (Author), Yuan, Haoyu (Author), Zhang, Yingchen (Author) and Tan, Jin (Author) |
Journal or Proceedings Title | Proceedings of the 2022 IEEE Power and Energy Society General Meeting (PESGM) |
Number of Pages | 5 |
Year | 2022 |
Place of Publication | United States |
ISBN | 9781665408233 |
Digital Object Identifier (DOI) | https://doi.org/10.1109/pesgm48719.2022.9916751 |
Web Address (URL) of Paper | https://ieeexplore.ieee.org/document/9916751 |
Web Address (URL) of Conference Proceedings | https://ieeexplore.ieee.org/xpl/conhome/9916588/proceeding |
Conference/Event | 2022 IEEE Power and Energy Society General Meeting (PESGM) |
Event Details | 2022 IEEE Power and Energy Society General Meeting (PESGM) Event Date 17 to end of 21 Jul 2022 Event Location Denver, United States |
Abstract | Frequency stability assessment is one critical aspect of power system security assessment. Traditional N-1 screening method is based on the simulations of a few typical daily and seasonal operation scenarios. However, the increasing integration of inverter-based renewables and the retirement of conventional synchronous generators result in decreasing system inertia and growing complexity of system operating conditions. Selecting a few typical operation scenarios cannot cover all operating conditions, and the time-domain simulation of all operation conditions requires tremendous time. This paper proposes a more efficient frequency stability assessment method based on deep learning. The affinity propagation clustering algorithm is used to divide the dataset into different clusters, so the selected dataset for training can cover the diversified operating conditions as much as possible. Also, feature normalization is applied to both the training dataset and testing dataset in order to remove any unnecessary bias. Especially, trained model based on full dataset normalization has bounded error in the prediction. The case study on the reduced 240-bus WECC system demonstrates that the proposed method can predict accurate frequency nadir with limited training dataset. The deep learning model using the revised feature normalization can predict more accurate frequency nadir than that using the traditional feature normalization and has very small maximum prediction error. |
Keywords | Affinity propagation, deep learning, feature normalization, frequency nadir, frequency stability, neural network |
Contains Sensitive Content | Does not contain sensitive content |
ANZSRC Field of Research 2020 | 400808. Photovoltaic power systems |
400803. Electrical energy generation (incl. renewables, excl. photovoltaics) | |
460308. Pattern recognition | |
Public Notes | Files associated with this item cannot be displayed due to copyright restrictions. |
Institution of Origin | University of Southern Queensland |
Byline Affiliations | University of Tennessee, United States |
Oak Ridge National Laboratory, United States | |
National Renewable Energy Laboratory, United States |
https://research.usq.edu.au/item/q7wy4/deep-learning-based-frequency-stability-assessment-in-power-grid-with-high-renewables
47
total views3
total downloads1
views this month0
downloads this month