Open AccessShort-term electricity price forecast based on long short-term memory neural network
Author(s) -
Lihong Dong,
Qian Xie
Publication year - 2020
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 - 10.1088/1742-6596/1453/1/012103
Subject(s) - artificial neural network , term (time) , computer science , electricity market , bidding , electricity price forecasting , recurrent neural network , function (biology) , econometrics , mean squared error , electricity , electric power system , artificial intelligence , power (physics) , economics , statistics , mathematics , engineering , microeconomics , physics , quantum mechanics , evolutionary biology , electrical engineering , biology
Effective short-term electricity price forecasting is of great significance to reduce bidding risk and obtain stable income. In order to predict the timing price, this paper proposes a short-term electricity price forecasting model based on Long Short-Term Memory (LSTM) neural network. The model uses pauta criterion and Lagrange interpolation polynomial to process the historical data of electricity price, normalize the obtained data and input it into the LSTM network layer, using the Mean Squared Error as the loss function to measure the model forecasting. The effect is based on the loss function, and the weight coefficient of the LSTM neural network is updated by the Adam algorithm. Finally, the timing of the LSTM neural network is predicted. Using the real-time data of the California power market and the real-time data of the US PJM power market, it is proved that the accuracy of this method is higher than that of BP neural network, Cart regression tree and polynomial regression.