EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

CatBoost-enhanced convolutional neural network framework with explainable artificial intelligence for smart-grid stability forecasting

Stephanie Ness

Frontiers in Smart Grids · 2025

DOI: 10.3389/frsgr.2025.1617763 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Frontiers in Smart Grids, 2025. Verfasst von Stephanie Ness. Die Arbeit wurde bisher 20-mal zitiert (Crossref) und nennt 22 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Universität Wien.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Introduction

Mobile robots increasingly support inspection and emergency response in smart-grid infrastructure but require accurate, interpretable backend diagnostics. This work is proposing a hybrid model that integrates CatBoost (for tabular features) with a deep 1D-CNN (for spatial feature extraction) and integrates Local Interpretable Model-agnostic Explanations (LIME) to provide transparent, instance-level rationales.

Methods

We evaluate on a synthetic DSGC-based stability dataset (14 features) and externally on the IEEE PES 2018 fault-clearing corpus. The hybrid concatenates CatBoost output probabilities with a three-layer CNN feature vector, followed by dense layers (ReLU and Sigmoid). Models are trained using the Adam optimizer. Performance is reported via Accuracy, Precision, Recall, F1, confusion matrices, ROC-AUC, and LIME explanations.

Results

On the generated synthetic data, the hybrid achieved 98.23% accuracy (F1 = 97.56%), outperforming ANN, DNN and CNN baselines. External validation on IEEE PES 2018 yielded F1 = 97.6%.

Discussion

Combining gradient-boosted trees with deep convolutional features improves discrimination while and it is preserving local explainability. This way it can be supporting both grid operations and stability-aware robotic mission planning. Future work will extend to multiclass/regression settings and compare XAI methods (e.g., SHAP) alongside additional tabular learners (XGBoost/LightGBM).

Förderung

  • Universität Wien

Zitieren

APA

Ness, S. (2025). CatBoost-enhanced convolutional neural network framework with explainable artificial intelligence for smart-grid stability forecasting. Frontiers in Smart Grids. https://doi.org/10.3389/frsgr.2025.1617763

Vancouver

Ness S. CatBoost-enhanced convolutional neural network framework with explainable artificial intelligence for smart-grid stability forecasting. Frontiers in Smart Grids. 2025. doi:10.3389/frsgr.2025.1617763

BibTeX
@article{Ness2025,
  author = {Ness, Stephanie},
  title = {CatBoost-enhanced convolutional neural network framework with explainable artificial intelligence for smart-grid stability forecasting},
  journal = {Frontiers in Smart Grids},
  year = {2025},
  doi = {10.3389/frsgr.2025.1617763}
}
Kostenlos starten →