Open Access

ARTICLE

Attention-Enhanced CNN-GRU Method for Short-Term Power Load Forecasting

Zheng Yin, Zhao Zhang^*

School of Computer Science and Software Engineering, University of Science and Technology Liaoning, Anshan, 114051, China

* Corresponding Author: Zhao Zhang. Email:

Journal on Artificial Intelligence 2025, 7, 633-645. https://doi.org/10.32604/jai.2025.074450

Received 11 October 2025; Accepted 21 November 2025; Issue published 24 December 2025

Abstract

Power load forecasting load forecasting is a core task in power system scheduling, operation, and planning. To enhance forecasting performance, this paper proposes a dual-input deep learning model that integrates Convolutional Neural Networks, Gated Recurrent Units, and a self-attention mechanism. Based on standardized data cleaning and normalization, the method performs convolutional feature extraction and recurrent modeling on load and meteorological time series separately. The self-attention mechanism is then applied to assign weights to key time steps, after which the two feature streams are flattened and concatenated. Finally, a fully connected layer is used to generate the forecast. Under a training setup with mean squared error as the loss function and an adaptive optimization strategy, the proposed model consistently outperforms baseline methods across multiple error and fitting metrics, demonstrating stronger generalization capability and interpretability. The paper also provides a complete data processing and evaluation workflow, ensuring strong reproducibility and practical applicability.

---

Keywords

---