Research on Short-term Time Series Forecasting Method Based on Feature Fusion of Electric Power
- Authors
- Type
- Published Article
- Journal
- Journal of Physics Conference Series
- Publisher
- IOP Publishing
- Publication Date
- Mar 01, 2023
- Volume
- 2449
- Issue
- 1
- Identifiers
- DOI: 10.1088/1742-6596/2449/1/012035
- Source
- ioppublishing
- Keywords
- Disciplines
- License
- Unknown
Abstract
In the power industry, time series forecasting has many application scenarios, such as accurate electricity consumption forecasting and load forecasting, which can provide a reference for power grid staff and reduce decision-making costs. To improve the accuracy of short-term load forecasting, this paper proposes a hybrid forecasting model based on an improved encoder-decoder architecture model and a Temporal Convolutional Network. Based on the gate recurrent unit, the model in this paper introduces the encoder-decoder architecture, adds the attention mechanism for improving the prediction accuracy, and performs feature fusion with the Temporal Convolutional Network, building a dual-feature fusion model finally. Experiments show that the method proposed in this paper reduces the evaluation metrics RMSE, MAPE and MAE by 7.7%, 15.2%, and 13.9% respectively compared to the Long Short-Term Memory Networks. Compared with the Temporal Convolutional Network, it is reduced by 2.6%, 4.8%, and 4%.
