Open AccessShort-term Power Prediction of Wind Farm Power Based on BP Neural Network
Author(s) -
Yaming Ren
Publication year - 2019
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 - 10.1088/1742-6596/1302/4/042053
Subject(s) - artificial neural network , wind power , randomness , volatility (finance) , computer science , term (time) , predictive power , power (physics) , power network , wind speed , electric power system , set (abstract data type) , control theory (sociology) , econometrics , artificial intelligence , mathematics , statistics , engineering , meteorology , electrical engineering , geography , philosophy , physics , control (management) , epistemology , quantum mechanics , programming language
With the proportion of wind power in the power systems increasing, consideration must be given to the fact that the randomness and volatility of wind power output will inevitably affect the stable operation of power grid. One of the effective ways to solve this problem is to forecast the output of wind power. In this paper, we employ the method of BP neural network to predict the wind power output in a period of time. To discuss the predictive performance of BP neural networks, we set different number of input variables to observe the prediction effect of BP neural network. We find that it’s not that the more input information, the better the prediction effect. The data with strong correlation can be used as input to achieve better results.