EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Decomposition–Ensemble Learning for Power Load Forecasting: Analysis of Noise Sensitivity and Algorithmic Stability

Rongrong Chen, Miaodan Cheng, Chia-Wei Huang, Wei-Tai Hsu, Chih-Chung Yang

Energies · 26.07.2026 · 19 (15) · 3511

DOI: 10.3390/en19153511 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Energies, online erschienen am 26.07.2026. Verfasst von Rongrong Chen und 4 weiteren Autor:innen. Die Arbeit nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Guangdong Province Postgraduate Education Innovation Plan Funding Project, “Double-Hundred Action” University and Local Community Cooperation Joint-Construction Project.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Precise short-term load forecasting is critical for smart grid reliability, yet the resilience of predictive models against ambient noise and sensor degradation remains insufficiently explored. This study systematically evaluates the noise sensitivity and operational stability of three forecasting paradigms (baseline LSTM, EEMD-LSTM, and CEEMD-LSTM) across varying signal-to-noise ratios (0–25 dB SNR) and sampling densities. Empirical analyses reveal a critical operational paradox: despite its theoretical sophistication, the CEEMD-LSTM architecture exhibits severe algorithmic instability and vulnerability to residual noise artifacts, yielding an RMSE standard deviation of ±1918 MW under high-fidelity conditions. Conversely, the EEMD-LSTM framework demonstrates superior robustness. Acting as an effective noise-mitigating filter, it sustains a Mean Absolute Percentage Error (MAPE) below 3.5% across all noise regimes, notably achieving sub-3.0% errors under severe interference (5 dB SNR). Furthermore, evaluating memory-optimized sparse sampling exposes a predictive trade-off, whereby reduced sampling density substantially exacerbates forecasting errors. These findings indicate that the EEMD-LSTM model, underpinned by dense sampling, provides a highly stable, noise-resilient predictive mechanism for smart grids subjected to uncertain measurements.

Förderung

  • Guangdong Province Postgraduate Education Innovation Plan Funding Project
  • “Double-Hundred Action” University and Local Community Cooperation Joint-Construction Project

Zitieren

APA

Chen, R., Cheng, M., Huang, C., Hsu, W., & Yang, C. (2026). Decomposition–Ensemble Learning for Power Load Forecasting: Analysis of Noise Sensitivity and Algorithmic Stability. Energies, 19(15), 3511. https://doi.org/10.3390/en19153511

Vancouver

Chen R, Cheng M, Huang C, Hsu W, Yang C. Decomposition–Ensemble Learning for Power Load Forecasting: Analysis of Noise Sensitivity and Algorithmic Stability. Energies. 2026;19(15):3511. doi:10.3390/en19153511

BibTeX
@article{Chen2026,
  author = {Chen, Rongrong and Cheng, Miaodan and Huang, Chia-Wei and Hsu, Wei-Tai and Yang, Chih-Chung},
  title = {Decomposition–Ensemble Learning for Power Load Forecasting: Analysis of Noise Sensitivity and Algorithmic Stability},
  journal = {Energies},
  year = {2026},
  volume = {19},
  number = {15},
  pages = {3511},
  doi = {10.3390/en19153511}
}
Kostenlos starten →