IEEE Working Group on Energy Forecasting opened Global Energy Forecasting Competition 2017 termed: Hierarchical Probabilistic Load Forecasting. GEFCom2017 brought together state-of-the-art techniques and methodologies for hierarchical probabilistic energy forecasting. The competition featured a bi-level setup: a three-month qualifying match that included two tracks, and a one-month final match on a large-scale problem. In total 177 academic and company teams enrolled the competition. Qualifying match defined data track winners:
Ján Dolinský, Mária Starovská and Robert Toth
Andrew J. Landgraf
Slawek Smyl and Grace Hua
Gábor Nagy and Gergő Barta, Gábor Simon
Qualifying match open track winners:
Geert Scholma
Florian Ziel
Jingrui Xie
Final match winners:
Isao Kanda and Juan Quintana
Ján Dolinský, Mária Starovská and Robert Toth
Gábor Nagy and Gergő Barta, Gábor Simon
Older competitions
GEFCom 2014
GEFCom2014 was announced by Dr. Tao Hong in an article for The Oracle, a publication of the International Institute of Forecasters. The competition was scheduled to begin on August 15, 2014 and end on December 15, 2014. In addition to individual prizes, GEFCom2014 also featured institute prizes for institutes with multiple well-performing teams. The best performers in the competition were invited to submit papers for a special issue of the International Journal of Forecasting on probabilistic energy forecasting. According to the website, GEFCom2014 had additional tracks in 2014: in addition to the hierarchical load forecasting and wind energy forecasting tracks, there was a price forecasting track and solar energy forecasting track. The IEEE Power & Energy Society was a sponsor of the competition.
GEFCom 2012
GEFCom 2012 was organized by a team comprising Dr. Tao Hong, Dr. Shu Fan, and Dr. Pierre Pinson. Sponsors included the IEEE Working Group on Energy Forecasting, IEEE Power System Planning and Implementation Committee, IEEE Power and Energy Education Committee, IEEE Power and Energy Society, IEEE Transactions on Smart Grid, International Journal of Forecasting, WeatherBank Inc, and Kaggle. The competition was hosted on Kaggle, a service that runs data science competitions. It included two tracks: a hierarchical load forecasting track and a wind power forecasting track; both opened to contestants in September 2012. More than 200 teams submitted more than 2,000 entries focusing on hierarchical load forecasting and wind power forecasting. The winners were announced by the IEEE Power & Energy Society on September 30, 2013. The organizers of the competition described the results in an article in the April–June 2014 issue of the International Journal of Forecasting. Papers by the top performers in the competition describing their methods also appeared in the issue. According to competition Chair Dr. Tao Hong, GEFCom2012 had five main aims: