Development of Clear sky models for solar energy using Machine Learning

- Indicates paper has been withdrawn from meeting
- Indicates an Award Winner
Wednesday, 5 February 2014: 9:45 AM
Room C204 (The Georgia World Congress Center )
Guido Cervone, Pennsylvania State University, University Park, PA; and J. Lin, T. C. McCandless, and S. Haupt

This presents the use of machine learning techniques for the development of a clear sky model that can be used for solar energy production. We developed a multi-strategy approach based on machine learning classification and time series analysis techniques.

The methodology was validated using 1 year of solar radiation data for Sacramento, CA. The data has a very high temporal resolution of 3 minutes, and it can be used for short term prediction.