Prediction Method of Photovoltaic Power Generation Based on LSTM Using Weather Information 


Vol. 44,  No. 12, pp. 2231-2238, Dec.  2019
10.7840/kics.2019.44.12.2231


PDF Full-Text
  Abstract

Recently, fossil fuel depletion and global warming problems are emerging. To solve these problems, solar energy comes into the limelight which is eco-friendly and has unlimited energy sources. For efficient operation and improving economic efficiency in managing solar power, accurate prediction of photovoltaic power generation is needed. This study proposes a technique to predict solar power in time units through Long Short-Term Memory (LSTM) and weather information such as temperature, humidity, cloud coverage, and ultraviolet index. The proposed technique is highly available by predicting the solar power generation of the desired section instead of the fixed time point, and the accuracy of the solar power generation prediction is increased by predicting insolation that is most closely related to photovoltaic power. The power generation prediction results of the LSTM based forecast model show that the error rates of MAE and NMAE are 1.5424 and 0.0454, respectively, and the error rates are lower than those of MAE and NMAE of the DNN based forecast model, 1.9347, 0.0569.

  Statistics
Cumulative Counts from November, 2022
Multiple requests among the same browser session are counted as one view. If you mouse over a chart, the values of data points will be shown.


  Cite this article

[IEEE Style]

Y. Kim, S. Lee, H. Kim, "Prediction Method of Photovoltaic Power Generation Based on LSTM Using Weather Information," The Journal of Korean Institute of Communications and Information Sciences, vol. 44, no. 12, pp. 2231-2238, 2019. DOI: 10.7840/kics.2019.44.12.2231.

[ACM Style]

Yongsu Kim, Sanghyun Lee, and Howon Kim. 2019. Prediction Method of Photovoltaic Power Generation Based on LSTM Using Weather Information. The Journal of Korean Institute of Communications and Information Sciences, 44, 12, (2019), 2231-2238. DOI: 10.7840/kics.2019.44.12.2231.

[KICS Style]

Yongsu Kim, Sanghyun Lee, Howon Kim, "Prediction Method of Photovoltaic Power Generation Based on LSTM Using Weather Information," The Journal of Korean Institute of Communications and Information Sciences, vol. 44, no. 12, pp. 2231-2238, 12. 2019. (https://doi.org/10.7840/kics.2019.44.12.2231)

Search
(IN TITLE, AUTHOR, ABSTRACT,KEYWORDS)

Advanced Search ▼

POPULAR KEYWORDS
(TOP 10 KEYWORDS)

Recent Publications
(LAST 3 YEARS)






pISSN : 1226 - 4717
eISSN : 2287 - 3880