Stacking integration algorithm based on CNN-BiLSTM-Attention with XGBoost for short-term electricity load forecasting

Improving the accuracy of electric load forecasting is critical for grid stability, industrial production, and residents' daily lives. Traditional short-term load forecasting methods often struggle to fully capture the long-term dependencies and deep-seated features in unknown datasets, thus li...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Energy reports Jg. 12; S. 2676 - 2689
Hauptverfasser: Luo, Shucheng, Wang, Baoshi, Gao, Qingzhong, Wang, Yibao, Pang, Xinfu
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Elsevier Ltd 01.12.2024
Schlagworte:
BiLSTM
CNN
Electricity load forecasting
Stacking integration algorithm
CNN
BiLSTM
Electricity load forecasting
Stacking integration algorithm
ISSN:2352-4847, 2352-4847
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Improving the accuracy of electric load forecasting is critical for grid stability, industrial production, and residents' daily lives. Traditional short-term load forecasting methods often struggle to fully capture the long-term dependencies and deep-seated features in unknown datasets, thus limiting their generalization ability. In this paper, we propose an algorithm for short-term power load forecasting based on the stacking integration algorithm of Convolutional Neural Network-Bidirectional Long Short-Term Neural Network-Attention Mechanism (CNN-BiLSTM-Attention) with Extreme Gradient Tree (XGBoost). First, an adaptive hierarchical clustering algorithm (AHC) selects a dataset with similar day characteristics. Then, combined with influencing factors, the Stacking integrated algorithm based on CNN-BiLSTM-Attention and XGBoost is employed for forecasting short-term load data. Finally, the integrated algorithm model was applied to the multi-feature load dataset in the Quanzhou area from 2016 to 2018. Comparative analysis showed that MAPE could be reduced by 5.88–69.40 % in the four selected typical days compared to the comparative algorithm, significantly improving load forecasting accuracy. •AHC is used to select similar daily samples.•Presented a Stacking ensemble algorithm based on CNN-BiLSTM-Attention and XGBoost.•Designed and conducted comparison experiments.•Conducted sensitivity analysis experiments.
ISSN:2352-4847
2352-4847
DOI:10.1016/j.egyr.2024.08.078