A novel method based on similarity for hourly solar irradiance forecasting

Emre Akarslan and Fatih Onur Hocaoglu

Renewable Energy, 2017, vol. 112, issue C, 337-346

Abstract: In this study, a novel short-term prediction methodology is developed. This methodology considers the past records of data to predict solar irradiance value for the desired hours. To predict next hour’s solar irradiance data, a day similar to the prediction day is sought in the history. For this purpose, a search vector including solar irradiance data measured from the early morning until the desired prediction hour is built for each prediction day. First data of this vector are calculated according to the extraterrestrial irradiance. Prediction is then performed using the information of the deviation of the data belonging to a similar day. Once an arbitrary hour’s data has been predicted, the measured value corresponding to this prediction is incorporated in the search vector. Thus, the length of this vector is increased at each prediction. The similarity is determined based on Euclidean distance metric and the similar day is able to be changed for each prediction. Finally, the performance of the proposed method is tested on measured data. Around 18–19% prediction error in terms of nRMSE is obtained. It is concluded that, proposed similarity approach can be used to predict solar radiation values and it is open for improvement.

Keywords: Solar irradiance forecasting; Similarity; Extraterrestrial irradiance (search for similar items in EconPapers)
Date: 2017
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (6)

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0960148117304445
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:renene:v:112:y:2017:i:c:p:337-346

DOI: 10.1016/j.renene.2017.05.058

Access Statistics for this article

Renewable Energy is currently edited by Soteris A. Kalogirou and Paul Christodoulides

More articles in Renewable Energy from Elsevier
Bibliographic data for series maintained by Catherine Liu ().