TY - JOUR
T1 - Selection of Characteristics by Hybrid Method
T2 - RFE, Ridge, Lasso, and Bayesian for the Power Forecast for a Photovoltaic System
AU - Cruz, Jose
AU - Mamani, Wilson
AU - Romero, Christian
AU - Pineda, Ferdinand
N1 - Publisher Copyright:
© 2021, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.
PY - 2021/5
Y1 - 2021/5
N2 - Currently, the generation of alternative energy from solar radiation with photovoltaic systems is growing, its efficiency depends on internal variables such as powers, voltages, currents; as well as external variables such as temperatures, irradiance, and load. To maximize performance, this research focused on the application of regularization techniques in a multiparametric linear regression model to predict the active power levels of a photovoltaic system from 14 variables that model the system under study. These variables affect the prediction to some degree, but some of them do not have so much preponderance in the final forecast, so it is convenient to eliminate them so that the processing cost and time are reduced. For this, we propose a hybrid selection method: first we apply the elimination of Recursive Feature Elimination (RFE) within the selection of subsets and then to the obtained results we apply the following contraction regularization methods: Lasso, Ridge and Bayesian Ridge; then the results were validated demonstrating linearity, normality of the error terms, without autocorrelation and homoscedasticity. All four prediction models had an accuracy greater than 99.97%. Training time was reduced by 71% and 36% for RFE-Ridge and RFE-OLS respectively. The variables eliminated with RFE were Total Energy, Daily Energy, and Irradiance, while the variable eliminated by Lasso was: “Frequency”. In all cases we see that the root mean square errors were reduced for RFE. Lasso by 0.15% while for RFE-Bayesian Ridge by 0.06%.
AB - Currently, the generation of alternative energy from solar radiation with photovoltaic systems is growing, its efficiency depends on internal variables such as powers, voltages, currents; as well as external variables such as temperatures, irradiance, and load. To maximize performance, this research focused on the application of regularization techniques in a multiparametric linear regression model to predict the active power levels of a photovoltaic system from 14 variables that model the system under study. These variables affect the prediction to some degree, but some of them do not have so much preponderance in the final forecast, so it is convenient to eliminate them so that the processing cost and time are reduced. For this, we propose a hybrid selection method: first we apply the elimination of Recursive Feature Elimination (RFE) within the selection of subsets and then to the obtained results we apply the following contraction regularization methods: Lasso, Ridge and Bayesian Ridge; then the results were validated demonstrating linearity, normality of the error terms, without autocorrelation and homoscedasticity. All four prediction models had an accuracy greater than 99.97%. Training time was reduced by 71% and 36% for RFE-Ridge and RFE-OLS respectively. The variables eliminated with RFE were Total Energy, Daily Energy, and Irradiance, while the variable eliminated by Lasso was: “Frequency”. In all cases we see that the root mean square errors were reduced for RFE. Lasso by 0.15% while for RFE-Bayesian Ridge by 0.06%.
KW - Bayesian Ridge
KW - Homoscedasticity
KW - Lasso
KW - Linear regression
KW - Regularization Shrinkage
KW - RFE
KW - Ridge
UR - http://www.scopus.com/inward/record.url?scp=85131827985&partnerID=8YFLogxK
U2 - 10.1007/s42979-021-00584-x
DO - 10.1007/s42979-021-00584-x
M3 - Article
AN - SCOPUS:85131827985
SN - 2662-995X
VL - 2
JO - SN Computer Science
JF - SN Computer Science
IS - 3
M1 - 202
ER -