Power load forecasting based on VMD and attention-LSTM

Han Chieh Chao, Fu Lin, Jeng Shyang Pan, Wei Che Chien, Chin Feng Lai

研究成果: Conference contribution

1 引文 斯高帕斯(Scopus)

摘要

Accurate forecasting of short-term load forecasting is of great help to demand-side response and power dispatching. In order to improve the accuracy of short-term power load prediction, the original power load data signals are decomposed by using the Variational Mode Decomposition (VMD) method. The decomposed sub-signals and the original signals form a new data set, which is then trained by the neural network. The decomposed sub-signals reflect the detailed features inside the power load that are difficult to be learned by the neural network. Through VMD analysis, the neural network can learn richer information, which is more effective than the superposition prediction method. The neural network prediction model selects an architecture based on Attention-long short term memory (Attention-LSTM). The addition of attention mechanism enables important decomposed information to be fully learned. The effectiveness of this method is proved by experiment.

原文English
主出版物標題Proceedings of the 3rd International Conference on Data Science and Information Technology, DSIT 2020
發行者Association for Computing Machinery
ISBN(電子)9781450376044
DOIs
出版狀態Published - 2020 七月 24
事件3rd International Conference on Data Science and Information Technology, DSIT 2020 - Xiamen, China
持續時間: 2020 七月 242020 七月 26

出版系列

名字ACM International Conference Proceeding Series

Conference

Conference3rd International Conference on Data Science and Information Technology, DSIT 2020
國家/地區China
城市Xiamen
期間20-07-2420-07-26

All Science Journal Classification (ASJC) codes

  • 軟體
  • 人機介面
  • 電腦視覺和模式識別
  • 電腦網路與通信

指紋

深入研究「Power load forecasting based on VMD and attention-LSTM」主題。共同形成了獨特的指紋。

引用此