Research on Multi Feature Load Forecasting Method Based on Hybrid Convolutional Neural Network

• Published in: 2024 7th Asia Conference on Energy and Electrical Engineering (ACEEE) pp. 237 - 241
• Main Authors: Le, Li, Hao, Han, Zhivuan, Liu, Chaoran, Li, Xuejun, Wang, Xiaoxun, Zhu
• Format: Conference Proceeding
• Language: English
• Published: IEEE 20.07.2024
• Subjects: Accuracy; Analytical models; Environmental factors; feature fusion; Hybrid Convolutional Neural Network; Load forecasting; multi-feature factor; Power system stability; Predictive models; Stability analysis
• DOI: 10.1109/ACEEE62329.2024.10651752

This paper proposes a short-term power load forecasting method based on hybrid convolutional neural networks to address the challenges of accuracy, stability, and adaptability to environmental factors in load forecasting tasks. A multi-scale feature fusion method based on 1D-CNN was proposed, which captures the trend of load changes by fusing features of different scales, improving the recognition ability of load mutations and complex patterns; A multi-feature factor learning method based on 2D-CNN was designed to address the impact of various environmental characteristic factors on electricity loads, which improved the modeling ability of the model for complex relationships between environmental factors and loads; A hybrid network model was constructed to achieve a comprehensive load forecasting method that effectively associates spatiotemporal features through deep feature fusion and information propagation of 1D-CNN and 2D-CNN feature information. Specific case studies were conducted to analyze the impact of parameter optimization and fusion learning on model accuracy and efficiency, and compared with classical models. The results showed that the RMSE value of our model was 36.3, MAE value was 5.34, and MAPE value was 1.02%, effectively improving the accuracy and robustness of load forecasting.