A compound of feature selection techniques to improve solar radiation forecasting

作者：

Highlights：

• The most relevant exogenous variables for predicting solar radiation are selected.

• Different machine learning models for solar radiation forecasting are evaluated.

• The Long Short-Term Memory neural network shows the best forecasting performance.

• Multivariate models are compared with their univariate counterparts.

• The adoption of exogenous inputs improves solar radiation forecasting performance.

摘要

•The most relevant exogenous variables for predicting solar radiation are selected.•Different machine learning models for solar radiation forecasting are evaluated.•The Long Short-Term Memory neural network shows the best forecasting performance.•Multivariate models are compared with their univariate counterparts.•The adoption of exogenous inputs improves solar radiation forecasting performance.

论文关键词：Solar radiation forecast,Photovoltaic system,Renewable energy,ANN,LSTM,1D-CNN

论文评审过程：Received 13 October 2020, Revised 25 January 2021, Accepted 27 March 2021, Available online 2 April 2021, Version of Record 20 April 2021.

论文官网地址：https://doi.org/10.1016/j.eswa.2021.114979