期刊
SOLAR ENERGY
卷 220, 期 -, 页码 745-757出版社
PERGAMON-ELSEVIER SCIENCE LTD
DOI: 10.1016/j.solener.2021.04.004
关键词
Feature selection; Random forest; Principal component analysis; Photovoltaics; Prediction; Machine learning
Meteorological variables have a significant impact on the performance of grid-connected photovoltaic stations in desert areas. The study found clear interdependence and correlations between performance parameters and meteorological variables. A forecasting model using random forest method and preprocessing techniques showed promising results in predicting power production based on meteorological inputs, with evaluation based on computation time, accuracy, and statistical indicators.
Meteorological variables have an important effect on the performance of a grid-connected photovoltaic station, in this paper, the impact of meteorological variables on the 6 mWp grid-connected photovoltaic station in the desert of Adrar has been explored through performance assessment and output power forecasting. The impact of the meteorological variables on performance parameters has been investigated by performing interdependence and correlation studies. A clear interdependence between some variables has been observed, but the complete separation between each variable correlation effect has proven to be a difficult task. A combination of random forest method and pre-processing techniques namely feature selection and Principal component analysis has been developed in order to predict power production using meteorological variables as inputs. The forecasting models have been evaluated in terms of computation time, accuracy, and several statistical indicators.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据