A Study on Interpretable Electric Load Forecasting Model with Spatiotemporal Feature Fusion Based on Attention Mechanism

• Published in: Technologies (Basel) Vol. 13; no. 6; p. 219
• Main Authors: Li, Shuaishuai, Chen, Weizhen
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.06.2025
• Subjects: Accuracy; Algorithms; Alternative energy sources; attention mechanism; China; Decision making; Decoupling; Deep learning; Electric power grids; Electric power systems; Electrical loads; Electricity; Electricity pricing; Feature extraction; Forecasting; High temperature; interpretability; Machine learning; Modelling; Neural networks; power load forecasting; Prediction theory; Renewable energy; Renewable resources; Root-mean-square errors; spatiotemporal feature fusion; Time series; Wind power; China
• DOI: 10.3390/technologies13060219
• ISSN: 2227-7080

Driven by the global “double carbon” goal, the volatility of renewable energy poses a challenge to the stability of power systems. Traditional methods have difficulty dealing with high-dimensional nonlinear data, and the single deep learning model has the limitations of spatiotemporal feature decoupling and being a “black box”. Aiming at the problem of insufficient accuracy and interpretability of power load forecasting in a renewable energy grid connected scenario, this study proposes an interpretable spatiotemporal feature fusion model based on an attention mechanism. Through CNN layered extraction of multi-dimensional space–time features such as meteorology and electricity price, BiLSTM bi-directional modeling time series rely on capturing the evolution rules of load series before and after, and the improved self-attention mechanism dynamically focuses on key features. Combined with the SHAP quantitative feature contribution and feature deletion experiment, a complete chain of “feature extraction time series modeling weight allocation interpretation and verification” is constructed. The experimental results show that the determination coefficient R2 of the model on the Australian electricity market data set reaches 0.9935, which is 84.6% and 59.8% higher than that of the LSTM and GRU models, respectively. The prediction error (RMSE = 105.5079) is 9.7% lower than that of TCN-LSTM model and 52.1% compared to the GNN (220.6049). Cross scenario validation shows that the generalization performance is excellent (R2 ≥ 0.9849). The interpretability analysis reveals that electricity price (average absolute value of SHAP 716.7761) is the core influencing factor, and its lack leads to a 0.76% decline in R2. The research breaks through the limitation of time–space decoupling and the unexplainable bottleneck of traditional models, provides a transparent basis for power dispatching, and has an important reference value for the construction of new power systems.