Electricity load forecasting contributes to the efficient operation of the grid system and plays a vital role in the proper scheduling of energy markets Power load data is affected by its own nonlinearity and a variety of factors, making the forecasting accuracy low. In this paper, we propose a combined prediction method based on the Variational mode decomposition (VMD) of convolutional-bidirectional long- and short-term memory network (CNN-BiLSTM). The raw load data are first decomposed into low-frequency components, mid-frequency components and high-frequency components by VMD, and the input different modal components are feature extracted by the CNN-BiLSTM network, and finally the prediction results of each modal component are reconstructed to obtain the prediction results. The experimental results show that the prediction effect of this method is better than the traditional model, which significantly improves the accuracy and effectiveness of the power load prediction model.
Research on CNN-BiLSTM Power Load Forecasting Based on VMD Algorithm
11.10.2023
3869232 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
BiLSTM- and GNN-Based Spatiotemporal Traffic Flow Forecasting with Correlated Weather Data
DOAJ | 2023
|