Spatio-Temporal Feature Fusion-Based Hybrid GAT-CNN-LSTM Model for Enhanced Short-Term Power Load Forecasting

Jia Huang, Qing Wei, Tiankuo Wang, Jiajun Ding, Longfei Yu, Diyang Wang and Zhitong Yu ()
Additional contact information
Jia Huang: Huadian Electric Power Research Institute Co., Ltd., Hangzhou 310027, China
Qing Wei: Huadian Electric Power Research Institute Co., Ltd., Hangzhou 310027, China
Tiankuo Wang: Huadian Electric Power Research Institute Co., Ltd., Hangzhou 310027, China
Jiajun Ding: Sichuan Energy Internet Research Institute, Tsinghua University, Chengdu 610213, China
Longfei Yu: Huadian Electric Power Research Institute Co., Ltd., Hangzhou 310027, China
Diyang Wang: Huadian Electric Power Research Institute Co., Ltd., Hangzhou 310027, China
Zhitong Yu: Department of Electrical Engineering, Tsinghua University, Beijing 100084, China

Energies, 2025, vol. 18, issue 21, 1-23

Abstract: Conventional power load forecasting frameworks face limitations in dynamic spatial topology capture and long-term dependency modeling. To address these issues, this study proposes a hybrid GAT-CNN-LSTM architecture for enhanced short-term power load forecasting. The model integrates three core components synergistically: Graph Attention Network (GAT) dynamically captures spatial correlations via adaptive node weighting, resolving static topology constraints; a CNN-LSTM module extracts multi-scale temporal features—convolutional kernels decompose load fluctuations, while bidirectional LSTM layers model long-term trends; and a gated fusion mechanism adaptively weights and fuses spatio-temporal features, suppressing noise and enhancing sensitivity to critical load periods. Experimental validations on multi-city datasets show significant improvements: the model outperforms baseline models by a notable margin in error reduction, exhibits stronger robustness under extreme weather, and maintains superior stability in multi-step forecasting. This study concludes that the hybrid model balances spatial topological analysis and temporal trend modeling, providing higher accuracy and adaptability for STLF in complex power grid environments.

Keywords: short-term power load forecasting; convolutional neural networks; long short-term memory networks; graph attention network (search for similar items in EconPapers)
JEL-codes: Q Q0 Q4 Q40 Q41 Q42 Q43 Q47 Q48 Q49 (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/1996-1073/18/21/5686/pdf (application/pdf)
https://www.mdpi.com/1996-1073/18/21/5686/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jeners:v:18:y:2025:i:21:p:5686-:d:1782478

Access Statistics for this article

Energies is currently edited by Ms. Cassie Shen

More articles in Energies from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().