Short-Term Solar Irradiance Forecasting Model Based on Artificial Neural Network Using Statistical Feature Parameters

Short-term solar irradiance forecasting (STSIF) is of great significance for the optimal operation and power predication of grid-connected photovoltaic (PV) plants. However, STSIF is very complex to handle due to the random and nonlinear characteristics of solar irradiance under changeable weather c...

Full description

Saved in:
Bibliographic Details
Published inEnergies (Basel) Vol. 5; no. 5; pp. 1355 - 1370
Main Authors Wang, Fei, Mi, Zengqiang, Su, Shi, Zhao, Hongshan
Format Journal Article
LanguageEnglish
Published Basel MDPI AG 01.05.2012
Subjects
Alternative energy sources
artificial neural network (ANN)
Climate change
Electric power
Electricity distribution
Energy resources
Forecasting
Neural networks
Renewable resources
Solar energy
solar irradiance
statistical feature
China
Online AccessGet full text

Cover

More Information
Summary:Short-term solar irradiance forecasting (STSIF) is of great significance for the optimal operation and power predication of grid-connected photovoltaic (PV) plants. However, STSIF is very complex to handle due to the random and nonlinear characteristics of solar irradiance under changeable weather conditions. Artificial Neural Network (ANN) is suitable for STSIF modeling and many research works on this topic are presented, but the conciseness and robustness of the existing models still need to be improved. After discussing the relation between weather variations and irradiance, the characteristics of the statistical feature parameters of irradiance under different weather conditions are figured out. A novel ANN model using statistical feature parameters (ANN-SFP) for STSIF is proposed in this paper. The input vector is reconstructed with several statistical feature parameters of irradiance and ambient temperature. Thus sufficient information can be effectively extracted from relatively few inputs and the model complexity is reduced. The model structure is determined by cross-validation (CV), and the Levenberg-Marquardt algorithm (LMA) is used for the network training. Simulations are carried out to validate and compare the proposed model with the conventional ANN model using historical data series (ANN-HDS), and the results indicated that the forecast accuracy is obviously improved under variable weather conditions.
ISSN:1996-1073
1996-1073
DOI:10.3390/en5051355