Solar radiation prediction using statistical approaches

Statistical approach is often used in time series analysis. One of its uses is to predict the future trend of a time series. This can be applied in many applications such as solar radiation, economics and other researches related to time series. In this paper, we use several classic statistical mode...

Full description

Saved in:
Bibliographic Details
Main Authors: Wu Ji, Chan, C., Loh, J., Choo, F., Chen, L.H.
Format: Conference Proceeding
Language:English
Subjects:
Data acquisition
Data mining
Kernel
Linear regression
Nearest neighbor searches
Predictive models
Smoothing methods
Solar energy
Solar radiation
solar radiation prediction
statistical approach
Time series analysis
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Statistical approach is often used in time series analysis. One of its uses is to predict the future trend of a time series. This can be applied in many applications such as solar radiation, economics and other researches related to time series. In this paper, we use several classic statistical models to fit the solar radiation time series. The goal is to find a suitable radiation model in predicting the trend of solar radiation time series. The simulation result shows that linear regression has better performance than other models such as the auto regression, auto regression integrate moving average. The linear regression method requires a number of previous data for prediction. Simulation shows that a list of 10 to 15 past data values yields optimal result.
DOI:10.1109/ICICS.2009.5397540