Open AccessShort-term power generation load forecasting based on LSTM neural network
Author(s) -
Bicheng Huang,
Langxing Tong,
Yu Zuo
Publication year - 2022
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/2247/1/012033
Subject(s) - artificial neural network , term (time) , computer science , power (physics) , electricity generation , electric power system , recurrent neural network , power grid , reliability engineering , real time computing , artificial intelligence , engineering , physics , quantum mechanics
With the gradual deepening of power market reform, power generation enterprises’ prediction of their future short-term power generation load is conducive to affecting the load distribution of power grid dispatching to power generation enterprises, so as to achieve the purpose of power marketing. In this regard, this paper proposes a power generation load forecasting method based on long and short-term memory (LSTM) neural network, which takes the power generation load sequence data as the model input to predict the future short-term power generation load of power generation enterprises, and proves that compared with the traditional Neural network method, LSTM neural network has higher prediction accuracy.