### Abstract

Solar radiation is an important factor in forecasting outputs of photovoltaic power systems. A method for solar radiation prediction is proposed based on wavelet transform. The data, including solar radiation and potential input variables, are decomposed into several time-frequency areas via wavelet transform. Given that some variables are relevant in some areas of solar radiation but irrelevant in other areas, we extract input variables from candidates separately in each time-frequency area. We perform principal component analysis (PCA) to extract principal components from input variables and we find their relations to the solar radiation are linear by visualization. Thus, linear regression equation is built to each area respectively, and the final result is the summation of predicted solar radiation from each time-frequency area. A comparison with the method using the same input variables in all time-frequency areas is presented and the results of our proposed method are more accurate.

Original language | English |
---|---|

Title of host publication | SICE 2011 - SICE Annual Conference 2011, Final Program and Abstracts |

Pages | 712-717 |

Number of pages | 6 |

Publication status | Published - 2011 |

Event | 50th Annual Conference on Society of Instrument and Control Engineers, SICE 2011 - Tokyo, Japan Duration: Sep 13 2011 → Sep 18 2011 |

### Other

Other | 50th Annual Conference on Society of Instrument and Control Engineers, SICE 2011 |
---|---|

Country | Japan |

City | Tokyo |

Period | 9/13/11 → 9/18/11 |

### Fingerprint

### All Science Journal Classification (ASJC) codes

- Electrical and Electronic Engineering
- Control and Systems Engineering
- Computer Science Applications

### Cite this

*SICE 2011 - SICE Annual Conference 2011, Final Program and Abstracts*(pp. 712-717). [6060756]

**Daily solar radiation prediction based on wavelet analysis.** / Zhang, Peng; Takano, Hirotaka; Murata, Junichi.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

*SICE 2011 - SICE Annual Conference 2011, Final Program and Abstracts.*, 6060756, pp. 712-717, 50th Annual Conference on Society of Instrument and Control Engineers, SICE 2011, Tokyo, Japan, 9/13/11.

}

TY - GEN

T1 - Daily solar radiation prediction based on wavelet analysis

AU - Zhang, Peng

AU - Takano, Hirotaka

AU - Murata, Junichi

PY - 2011

Y1 - 2011

N2 - Solar radiation is an important factor in forecasting outputs of photovoltaic power systems. A method for solar radiation prediction is proposed based on wavelet transform. The data, including solar radiation and potential input variables, are decomposed into several time-frequency areas via wavelet transform. Given that some variables are relevant in some areas of solar radiation but irrelevant in other areas, we extract input variables from candidates separately in each time-frequency area. We perform principal component analysis (PCA) to extract principal components from input variables and we find their relations to the solar radiation are linear by visualization. Thus, linear regression equation is built to each area respectively, and the final result is the summation of predicted solar radiation from each time-frequency area. A comparison with the method using the same input variables in all time-frequency areas is presented and the results of our proposed method are more accurate.

AB - Solar radiation is an important factor in forecasting outputs of photovoltaic power systems. A method for solar radiation prediction is proposed based on wavelet transform. The data, including solar radiation and potential input variables, are decomposed into several time-frequency areas via wavelet transform. Given that some variables are relevant in some areas of solar radiation but irrelevant in other areas, we extract input variables from candidates separately in each time-frequency area. We perform principal component analysis (PCA) to extract principal components from input variables and we find their relations to the solar radiation are linear by visualization. Thus, linear regression equation is built to each area respectively, and the final result is the summation of predicted solar radiation from each time-frequency area. A comparison with the method using the same input variables in all time-frequency areas is presented and the results of our proposed method are more accurate.

UR - http://www.scopus.com/inward/record.url?scp=81255192254&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=81255192254&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:81255192254

SN - 9784907764395

SP - 712

EP - 717

BT - SICE 2011 - SICE Annual Conference 2011, Final Program and Abstracts

ER -