A tree-based clear sky model for DNI forecasting

Solar irradiance is a renewable energy that has been utilized by power plants. Direct normal irradiance (DNI) forecasting is a crucial approach to reduce the output uncertainty of solar power plants, and enhance reliability of power grids. According to statistics, the solar radiation of clear sky accounts for more than half of the total amount of radiation in a year. Hence, clear sky DNI forecasting models play a significant role in solar power systems. The existing clear sky models assume that the atmosphere is at rest and ignore the variation of aerosol optical depth in a day, which may reduce the accuracy of DNI forecasting. In this paper, a novel tree-based piecewise clear sky model is proposed to capture aerosol extinction coefficient varying with time in a day and forecast DNI when clouds are absent. Firstly, a linear model is deduced from a physical equation to represent the relationship of air mass and DNI approximately. Then, model trees with this linear mode at each leaf node are create. The database of the National Renewable Energy Laboratory (NREL) is used for experiments to evaluate the performance of the proposed model, compared with other clear sky models. The results of the experiments show that the proposed model provides more accurate forecast of DNI than other clear sky models.

[1]  C. Gueymard.  REST2: High-performance solar radiation model for cloudless-sky irradiance, illuminance, and photosynthetically active radiation – Validation with a benchmark dataset , 2008 .

[2]  Carlos F.M. Coimbra,et al.  Hybrid intra-hour DNI forecasts with sky image processing enhanced by stochastic learning , 2013 .

[3]  R. E. Bird,et al.  Review, Evaluation, and Improvement of Direct Irradiance Models , 1981 .

[4]  C. Gueymard.  Direct solar transmittance and irradiance predictions with broadband models. Part I: detailed theoretical performance assessment , 2003 .

[5]  R. Bird,et al.  Simplified clear sky model for direct and diffuse insolation on horizontal surfaces , 1981 .

[6]  Krista A. Ehinger,et al.  A novel graph-based optimization framework for salient object detection , 2017, Pattern Recognit..

[8]  Haikun Wei,et al.  Clear-sky model for wavelet forecast of direct normal irradiance , 2017 .

[9]  Peter Harrington,et al.  Machine Learning in Action , 2012 .

[10]  R. L. Hulstrom,et al.  Direct insolation models , 1980 .

[11]  Tingting Zhu,et al.  Short-term wind speed forecasting using empirical mode decomposition and feature selection , 2016 .

[12]  P. Ineichen.  A broadband simplified version of the Solis clear sky model , 2008 .

[13]  Fengfeng Li,et al.  Analysis of the stable operation of micro-grid based on PV, wind power and storage system , 2015, The 27th Chinese Control and Decision Conference (2015 CCDC).

[14]  P. Ineichen,et al.  A new airmass independent formulation for the Linke turbidity coefficient , 2002 .

[15]  Christopher M. Bishop,et al.  Pattern Recognition and Machine Learning (Information Science and Statistics) , 2006 .

[16]  Haikun Wei,et al.  A Gaussian process regression based hybrid approach for short-term wind speed prediction , 2016 .

[17]  Chen Gang,et al.  Cooperative solar tracking control of multiple dual-axis PV panels , 2015, The 27th Chinese Control and Decision Conference (2015 CCDC).

[18]  Robert A. Taylor,et al.  Direct normal irradiance forecasting and its application to concentrated solar thermal output forecasting - A review , 2014 .