AI Model Cuts Energy Forecasting Errors Nearly in Half for Large Facilities
Researchers have developed a machine learning system that predicts energy demand for parks and campuses with 29% greater accuracy than existing methods. The breakthrough could help facility managers reduce peak loads, lower utility costs, and improve grid stability as electrification increases demand.
Originaltitel: The Short-Term Load Prediction Method for Parks Based on CNN-LSTM-SAO-MHA
<p>Park-level load exhibiting nonlinearity, multi-coupling and stochastic fluctuations, which pose challenges for accurate load forecasting. To address these issues, this study proposes a hybrid short-term load forecasting model based on CNN-LSTM-SAO-MHA. In this model, Convolutional Neural Networks (CNN) extract local temporal features, while Long Short-Term Memory (LSTM) captures long-term dependencies. The Multi-Head Attention (MHA) mechanism strengthens the model’s ability to assign adaptive weights to different time steps, thereby enhancing feature representation and improving the capture of temporal dependencies. Additionally, the Snowmelt Optimisation Algorithm (SAO) is employed for hyperparameter optimisation, enabling automatic adjustment of key parameters to enhance prediction accuracy and computational efficiency. To validate the effectiveness of the proposed model, experiments were conducted using real-world cooling load data from a typical park. The results demonstrate that the proposed CNN-LSTM-SAO-MHA hybrid model significantly outperforms benchmark models, achieving reductions of 28.74% in RMSE and CV-RMSE compared to CNN-LSTM, highlighting its superior performance in short-term park-level load forecasting. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2026.</p>