GEFCom2012 Papers

Thanks to International Journal of Forecasting and IEEE Transactions on Smart Grid, our two publication sponsors of GEFCom2012, all of the invited GEFCom2012 papers have been published as of today. These papers, in many aspects, represent the state-of-the-art in load and wind forecasting. The citations in IEEE format and links to these papers are provided below.

The introduction and review paper covers about 10 top entries of each track. It also publishes the complete set of the competition data including the solution data. Anyone is welcome to use the data with proper citation to our paper below.

• T. Hong, P. Pinson, and S. Fan, "Global Energy Forecasting Competition 2012," International Journal of Forecasting, vol. 30, pp. 357-363, Apr.–Jun. 2014.

The following five papers are from the winners of the hierarchical load forecasting track. Notice that the winning team from EDF wrote two papers: one on hierarchical load forecasting based on the GEFCom2012 data; the other one on the application of the similar methodology to short and medium term load forecasting.

• N. Charlton and C. Singleton, "A refined parametric model for short term load forecasting," International Journal of Forecasting, vol. 30, pp. 364-368, Apr.-Jun. 2014. 
• J. R. Lloyd, "GEFCom2012 hierarchical load forecasting: gradient boosting machines and Gaussian processes," International Journal of Forecasting, vol. 30, pp. 369-374, Apr.-Jun. 2014.
• R. Nedellec, J. Cugliari, and Y. Goude, "GEFCom2012: Electric load forecasting and backcasting with semi-parametric models," International Journal of Forecasting, vol. 30, pp. 375-381, Apr.-Jun. 2014.
• Y. Goude, R. Nedellec, and N. Kong, "Local short and middle term electricity load forecasting with semi-parametric additive models," IEEE Trans. Smart Grid, vol. 5, pp. 440-446, Jan. 2014.
• S. B. Taieb and R. J. Hyndman, "A gradient boosting approach to the Kaggle load forecasting competition," International Journal of Forecasting, vol. 30, pp. 382-394, Apr.-Jun. 2014. 

The following three papers are from the winners of the wind power forecasting track.

• L. Silva, "A feature engineering approach to wind power forecasting: GEFCom 2012," International Journal of Forecasting, vol. 30, pp. 395-401, Apr.-Jun. 2014. 
• E. Mangalova and E. Agafonov, "Wind power forecasting using the -nearest neighbors algorithm," International Journal of Forecasting, vol. 30, pp. 402-406, Apr.-Jun. 2014. 
• D. Lee and R. Baldick, "Short-term wind power ensemble prediction based on Gaussian processes and neural networks," IEEE Trans. Smart Grid, vol. 5, pp. 501-510, Jan. 2014. 

This is very likely my last post dedicated to GEFCom2012. It was a great pleasure and fortune for me to work with an elite team of people and organizations to make GEFCom2012 a huge success. While we are diligently preparing for GEFCom2014, you are welcome to browse the other competition related posts in my blog. Rob Hyndman also has a recent blog post on the competitions including the evaluation method we will use for GEFCom2014.