LIU Yiyan, LI Guoliang, DAI Jie. Short-term Power Load Forecasting Based on VMD-TCN-BiLSTM-Attention[J]. 2025, 53(10): 87-94. DOI: 10.20204/j.sp.2025.10012.
Short-term Power Load Forecasting Based on VMD-TCN-BiLSTM-Attention
To address the issue of insufficient prediction accuracy caused by the nonlinear and volatile nature of short-term electrical load data, a novel forecasting model integrating variational mode decomposition (VMD), temporal convolutional network (TCN), bidirectional long short-term memory (BiLSTM), and attention mechanism is proposed. First, the VMD method is applied to decompose the electrical load data into multiple intrinsic mode functions at different frequencies. The TCN model is then used to extract temporal features from these modal components. Subsequently, the BiLSTM network further captures contextual dependencies within the sequences. Finally, an attention mechanism is introduced to adaptively weight the features output by BiLSTM. Experimental results demonstrate that the proposed model significantly improves prediction accuracy compared to other traditional models, showing high practical value in short-term electrical load forecasting.
SHU Z,YUHONG W. An improved software defect prediction model based on grey incidence analysis and Naive Bayes algorithm [J ] .Journal of Intelligent & Fuzzy Systems,2022,43(5):6047-6060.
YOUNESS M,ABDOULAYE K B,RACHID F,et al. A feature weighted K-nearest neighbor algorithm based on association rules [J ] .Journal of Ambient Intelligence and Humanized Computing,2024,15(7):2995-3008.
SICHAO C,LIEJIANG H,YUANJUN P,et al. Decision tree-based prediction approach for improving stable energy management in smart grids [J ] .Journal of High Speed Networks,2023,29(4):295-305.
HAN L,WANG X,YU Y,et al. Power load forecast based on CS-LSTM neural network [J ] .Mathematics,2024,12(9):1402-1402.
WANG D,LI S,FU X. Short-term power load forecasting based on secondary cleaning and CNN-BILSTM-Attention [J ] .Energies,2024,17(16):4142-4142.
PHAN B Q,NGUYEN T T. Enhancing wind speed forecasting accuracy using a GWO-nested CEEMDAN-CNN-BiLSTM model [J ] .ICT Express,2024,10(3):485-490.
YANG M,CHEN Y,FANG G,et al. A short-term power load forecasting method based on SBOA-SVMD-TCN-BiLSTM [J ] .Electronics,2024,13(17):3441-3441.
NADA M,HAMID O,ISMAEL J. Short-term electric load forecasting using an EMD-BI-LSTM approach for smart grid energy management system [J ] .Energy & Buildings,2023,288(8):466-325.
CHEN Q,JIANG C,LEI B. Improved load forecasting method based on TCN-BiGRU and attention mechanism [J ] .Journal of Physics:Conference Series,2024,2849(1):012049.
YANG M,CHEN Y,FANG G,et al. A short-term power load forecasting method based on SBOA-SVMD-TCN-BiLSTM [J ] .Electronics,2024,13(17):3441-3441.
LUO S,WANG B,GAO Q,et al. Stacking integration algorithm based on CNN-BiLSTM-Attention with XGBoost for short-term electricity load forecasting [J ] .Energy Reports,2024,122676-2689.