EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Time–Frequency Fusion GAN-Based Method for Power System Oscillation Risk Scenario Generation

Bo Zhou, Yunyang Xu, Xinwei Sun, Xi Wang, Baohong Li, Congkai Huang

Electricity · 01.04.2026 · 7 (2) · 30

DOI: 10.3390/electricity7020030 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Electricity, online erschienen am 01.04.2026. Verfasst von Bo Zhou und 5 weiteren Autor:innen. Die Arbeit nennt 24 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: State Grid Sichuan Electric Power Research Institute Science and Technology Project.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

With the large-scale integration of renewable energy and the increasing use of power electronics, the issue of wide-band oscillations in power grids has become increasingly prominent. The scarcity and uneven distribution of oscillation samples pose significant challenges for training data-driven models, and traditional generative models struggle to ensure fidelity in both time and frequency domains. To address this, this paper proposes a Time–Frequency Fusion Generative Adversarial Network (TFF-GAN) for generating power grid oscillation risk scenarios. The method constructs a dual-path generation and discrimination framework, where the generator decomposes the signal using Short-Time Fourier Transform (STFT), with time-domain features extracted by a convolutional neural network (CNN) and frequency-domain features extracted from the STFT representation by a dedicated spectral network. These features are then fused using a U-Net structure. The discriminator simultaneously evaluates the authenticity of both the time-domain waveform and the frequency-domain spectrum. A composite loss function, incorporating time-domain loss, frequency-domain loss, and adversarial loss, is used for joint optimization. Experimental results demonstrate that the proposed method generates oscillation scenarios with high fidelity in both time-domain waveforms and frequency-domain spectra, effectively supporting power grid oscillation risk assessment and control strategy validation.

Förderung

  • State Grid Sichuan Electric Power Research Institute Science and Technology Project

Zitieren

APA

Zhou, B., Xu, Y., Sun, X., Wang, X., Li, B., & Huang, C. (2026). A Time–Frequency Fusion GAN-Based Method for Power System Oscillation Risk Scenario Generation. Electricity, 7(2), 30. https://doi.org/10.3390/electricity7020030

Vancouver

Zhou B, Xu Y, Sun X, Wang X, Li B, Huang C. A Time–Frequency Fusion GAN-Based Method for Power System Oscillation Risk Scenario Generation. Electricity. 2026;7(2):30. doi:10.3390/electricity7020030

BibTeX
@article{Zhou2026,
  author = {Zhou, Bo and Xu, Yunyang and Sun, Xinwei and Wang, Xi and Li, Baohong and Huang, Congkai},
  title = {A Time–Frequency Fusion GAN-Based Method for Power System Oscillation Risk Scenario Generation},
  journal = {Electricity},
  year = {2026},
  volume = {7},
  number = {2},
  pages = {30},
  doi = {10.3390/electricity7020030}
}
Kostenlos starten →