The competition is financially sponsored by IEEE Power & Energy Society. The top 1 place of the final leadership board will get $500. Competition award winners will be determined by the Award Committee of GEFCom2012 with break down of $4000, $2000 and $1000\r\n for 1st, 2nd and 3rd place respectively.
", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "rules", "content": "\r\n\t\r\nYou cannot sign up to Kaggle from multiple accounts and therefore you cannot submit from multiple accounts.
\r\n\r\n Privately sharing code or data outside of teams is not permitted.\r\n It's okay to share code if made available to all participants on the forums.\r\n
\r\nKaggle and the competition host have the right to publicly disseminate any entries or models.
\r\n\r\n Winning solutions need to be made available under\r\n a popular OSI-approved license\r\n in order to be eligible for recognition and prize money.\r\n
\r\n\r\n Prizes will be awarded after the winners have posted their solutions to the competition forum.\r\n Winners must post or link to their solutions within seven (7) days of being notified of their winning status.\r\n
\r\n\r\n Team mergers are allowed and can be performed by the team leader. In order to merge, the combined team must have a total submission count less than or equal to the maximum allowed as of the merge date. The maximum allowed is the number of submissions per day multiplied by the number of days the competition has been running.
\r\n
There is no maximum team size.
\r\nYou may submit a maximum of 2 entries per day.
\r\nYou may select up to 1 final submissions for judging.
\r\nStart Date: 9/1/2012 12:42 AM UTC
\r\nMerger Deadline: None
\r\nEntry Deadline: None
\r\nEnd Date: 10/31/2012 12:00 AM UTC
\r\n\t\r\nThe participants can refer to the US federal holidays as listed in US Office of Personnel Management website: http://www.opm.gov/Operating_Status_Schedules/fedhol/2008.asp.
\r\nAt each hour, sum of the 20 zonal level loads is required to be equal to the system level load. Submissions that voilate this requirement will be disqualified.
\r\nThe particpants should submit their algorithms, models, complete code and a detailed report via email to the General Chair of GEFCom2012 (Dr. Tao Hong, hongtao01@gmail.com) by 11/1/2012.
\r\nSelected entries will be invited to IEEE PES General Meeting 2013 at Vancouver, Canada to present their methodologies and results. The final winners will be determined by the GEFCom Award Committee after the presentations based on forecasting\r\n accuracy, clarity of documentation, rigors of the approach, interpretability of the models and practicality to the industry.
\r\nModels should be generated using software that is free and open source or is in the following list of exceptions: MATLAB, SAS, MS Excel. The particpants who are using other software packages should send a free evaluation copy of the software\r\n to GEFCom Award Committee to reproduce and evaluate the proposed models.
\r\n
In each of the 5 data files, there is a header row. Three columns of calendar variables: year, month of the year and day of the month. The last 24 columns are the 24 hours of the day.
\r\nIn "Load_history.csv", Column A is zone_id ranging from 1 to 20.
\r\nIn "Temperature_history.csv", Column A is station_id ranging from 1 to 11.
\r\nIn "submission_template.csv", "weights.csv", and "Benchmark.csv", Column A is id, the identifier for each row; Column B is zone_id ranging from 1 to 21, where the 21st "zone" represents system level, which is the sum of the other 20 zones.
\r\n"Benchmark.csv" shows the results from a benchmark model.
\r\nPlease make sure the submission strictly follow the format as indicated in "submission_template.csv", where the year was sorted in smallest to largest order first, then month, then day, and then zone_id.
", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Description", "content": "This is the Load Forecasting track of Global Energy Forecasting Competition 2012 (GEFCom2012).This competition will bring together the state-of-the-art techniques for energy forecasting, serve as the bridge to connect\r\n academic research and industry practice, promote analytics in power engineering education, and prepare the industry to overcome forecasting challenges in the smart grid world.
\r\nThe prize pool for the load forecasting track is $7,500. GEFCom is not a paper contest. Instead, this is a competition that requires participants to develop models and submit forecasts based on a given data set. Accuracy of the forecasts will be one evaluation\r\n criteria. In addition to accuracy, the participants are also required to submit a report describing the methodology, findings and models. Selected entries will be invited to IEEE PES General Meeting 2013 at Vancouver, Canada to present their methodologies\r\n and results. The team that finishes top of the leaderboard will win a cash prize. However an overall winner of the competition will be determined by the GEFCom Award Committee after the presentations based on forecasting accuracy, clarity of documentation,\r\n rigors of the approach, interpretability of the models and practicality to the industry. A few winning entries will be invited to submit the report in scientific paper format to prestigious scholarly journals, such as International Journal of Forecasting and\r\n IEEE Transactions on Smart Grid.
\r\nThe topic for the load forecasting track is a hierarchical load forecasting problem: backcasting and forecasting hourly loads (in kW) for a US utility with 20 zones. The participants are required to backcast and forecast at both zonal level (20 series) and\r\n system (sum of the 20 zonal level series) level, totally 21 series.
\r\nData (loads of 20 zones and temperature of 11 stations) history ranges from the 1st hour of 2004/1/1 to the 6th hour of 2008/6/30.
\r\nGiven actual temperature history, the 8 weeks below in the load history are set to be missing and are required to be backcasted. It's OK to use the entire history to backcast these 8 weeks.
\r\n2005/3/6 - 2005/3/12;
\r\n2005/6/20 - 2005/6/26;
\r\n2005/9/10 - 2005/9/16;
\r\n2005/12/25 - 2005/12/31;
\r\n2006/2/13 - 2006/2/19;
\r\n2006/5/25 - 2006/5/31;
\r\n2006/8/2 - 2006/8/8;
\r\n2006/11/22 - 2006/11/28;
\r\nIn addition, the particpants need to forecast hourly loads from 2008/7/1 to 2008/7/7. No actual temperatures are given for this week.
", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Evaluation", "content": "The forecasting accuracy will be evaluated by weighted root mean square error.
\r\nThe weights are assigned as following:
\r\nEach hour of the 8 backcasted weeks at zonal level: 1;
\r\nEach hour of the 8 backcasted weeks at system level: 20;
\r\nEach hour of the 1 forecasted week at zonal level: 8;
\r\nEach hour of the 1 forecasted week at system level: 160;
\r\nDetails of weight assignment are shown in data file: weights.csv.
", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false } ] }