Research on Prediction of Solar Power Considering the Methods of Statistical and Machine Learning – Based on the Data of Australian Solar Power Market

📝 Abstract

In this paper, we use the methods of machine learning and traditional time series to predict solar power generation, based on the Australia Market Data. We analyze Ausgrid's Solar data using Long Short-Term Memory (LSTM) methods and time series models (multiple regression models with correlated errors) to accurately estimate the parameters of photovoltaic (PV) array models, using household electricity consumption data from July 1, 2010 to June 30, 2013. The results show that the regression model with correlated errors outperforms the machine learning-based LSTM algorithm based on differential MSE performance.

📋 BibTeX Citation

@inproceedings{zhao2022solar,
  title     = {Research on Prediction of Solar Power Considering 
               the Methods of Statistical and Machine Learning -- 
               Based on the Data of Australian Solar Power Market},
  author    = {Zhao, Puyang and Tian, W.},
  booktitle = {IOP Conference Series: Earth and Environmental Science},
  volume    = {1046},
  number    = {1},
  pages     = {012006},
  year      = {2022},
  month     = {jun},
  publisher = {IOP Publishing},
  doi       = {10.1088/1755-1315/1046/1/012006}
}

🔗 Related Publications