EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Measurement Uncertainty and Deep Learning: A Metrology-Aware Framework for Load Forecasting

V. Negri, S. Mari, F. Ciancetta, A. Mingotti, R. Tinarelli, L. Peretto

IEEE Open Journal of Instrumentation and Measurement · 2026 · 5 · 2500408-2500408

DOI: 10.1109/ojim.2026.3711302 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Open Journal of Instrumentation and Measurement, 2026. Verfasst von V. Negri und 5 weiteren Autor:innen. Die Arbeit nennt 31 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate load forecasting is essential for power system operation, yet most deep learning (DL) pipelines neglect the measurement uncertainty affecting sensor-acquired input data. This article proposes a metrology-aware, data-centric, and architecture-agnostic framework that incorporates instrumental uncertainty into DL workflows without modifying the predictive model. Input uncertainty is modeled during training through guide to the expression of uncertainty in measurement (GUM)-consistent data augmentation (DA) and during inference through repeated perturbation of the test samples. The framework is validated on public Ausgrid substation data using a long short-term memory (LSTM) network for one-day-ahead and one-week-ahead forecasting. Representative results show that uncertainty-aware DA reduces the one-week-ahead mean absolute percentage error (MAPE) from 0.12 to 0.09 in the single-substation forecasting scenario and the one-week-ahead mean absolute error (MAE) from 1.80 to 1.59 MW in the cross-substation generalization scenario, corresponding to relative reductions of approximately 25% and 12%, respectively. The analysis also considers robustness under perturbed inputs, cross-substation generalization, computational cost, statistical significance, and comparisons with model-centric baselines based on deep ensembles and Monte Carlo Dropout. Repeated uncertainty-aware testing shows very small variability under realistic input perturbations, with standard deviations lower than $10^{-3}$ MW for MAE and root mean square error (RMSE) and lower than $10^{-4}$ for MAPE. The corresponding empirical interval widths remain limited, with mean prediction interval width (MPIW) values below 0.06 MW in all the considered cases. Conversely, model-centric baselines exhibit larger variability, up to 0.18 MW for MAE, 0.22 MW for RMSE, and 0.02 for MAPE in the ensemble configuration, confirming that model-related uncertainty dominates measurement-induced uncertainty in the considered case study. Overall, the proposed framework bridges metrological principles and DL-based forecasting, enabling more robust and traceable predictions for measurement-intensive power applications.

Zitieren

APA

Negri, V., Mari, S., Ciancetta, F., Mingotti, A., Tinarelli, R., & Peretto, L. (2026). Measurement Uncertainty and Deep Learning: A Metrology-Aware Framework for Load Forecasting. IEEE Open Journal of Instrumentation and Measurement, 5, 2500408-2500408. https://doi.org/10.1109/ojim.2026.3711302

Vancouver

Negri V, Mari S, Ciancetta F, Mingotti A, Tinarelli R, Peretto L. Measurement Uncertainty and Deep Learning: A Metrology-Aware Framework for Load Forecasting. IEEE Open Journal of Instrumentation and Measurement. 2026;5:2500408-2500408. doi:10.1109/ojim.2026.3711302

BibTeX
@article{Negri2026,
  author = {Negri, V. and Mari, S. and Ciancetta, F. and Mingotti, A. and Tinarelli, R. and Peretto, L.},
  title = {Measurement Uncertainty and Deep Learning: A Metrology-Aware Framework for Load Forecasting},
  journal = {IEEE Open Journal of Instrumentation and Measurement},
  year = {2026},
  volume = {5},
  pages = {2500408--2500408},
  doi = {10.1109/ojim.2026.3711302}
}
Kostenlos starten →