GEFCom2014 Load Forecasting Data

The load forecasting track of GEFCom2014 was about probabilistic load forecasting. We asked the contestants to provide one-month ahead hourly probabilistic forecasts on a rolling basis for 15 rounds. In the first round, we provided 69 months of hourly load data and 117 months of hourly temperature data. Incremental load and temperature data was provided in each of the future rounds.

Where to download the data?

The complete data was published as the appendix of our GEFCom2014 paper. If you don't have access to Science Direct, you can downloaded from my Dropbox link HERE. Regardless where you get the data, you should cite this paper to acknowledge the source:

• Tao Hong, Pierre Pinson, Shu Fan, Hamidreza Zareipour, Alberto Troccoli and Rob J. Hyndman, "Probabilistic energy forecasting: Global Energy Forecasting Competition 2014 and beyond", International Journal of Forecasting, vol.32, no.3, pp 896-913, July-September, 2016.

What's in the package?

Unzip the file, you will see the folder "GEFCom2014 Data", which includes five zip files. The data for the probabilistic load forecasting track of GFECom2014 is in the file "GEFCom2014-L_V2.zip". Unzip it, you will see the folder "load", which includes an "Instructions.txt" file and 15 other subfolders. In each folder named as "Task n", there are two files, Ln-train.csv and Ln-benchmark.csv. The train file, together with the train files released in previous rounds, can be used to generate forecasts. The benchmark file includes the forecast generated from the benchmark method.

How to use the data?

Apparently the most straightforward way of using this dataset is to replicate the competition setup and compare results directly with the top entries. Because the data published through GEFCom2014 is quite long (totally 7 years of matching load and temperature data), we can also use this dataset to test methods and models for short term load forecasting.

GEFCom2014-E data

After GEFCom2014, I organized an in-class probabilistic load forecasting competition in Fall 2015 that was open to external participants. My in-class competition setup was very similar to that of GEFCom2014, so I denoted the data for this in-class load forecasting competition as GEFCom2014-E, where E is the abbreviation of "extended". In total, this dataset covers 11 years of hourly temperature and 9 years of hourly load. A top team Florian Ziel was invited to contribute a paper to IJF (see HERE). The readers may replicate the same competition setup and compare results with Ziel's.

Caution

Note that the data I used for GEFCom2014-E was created using ISO New England data. If you want to validate a method using two independent sources, you should not use GEFCom2014-E together with ISO New England data.

Back to Datasets for Energy Forecasting.

GEFCom2012 Load Forecasting Data

The load forecasting track of GEFCom2012 was about hierarchical load forecasting. We asked the contestants to forecast and backcast (check out THIS POST for the definitions of forecasting and backcasting) the electricity demand for 21 zones, of which the Zone 21 was the sum of the other 20 zones.

Where to download the data?

You can also download an incomplete dataset from Kaggle, which does not have the solution data. The complete data was published as the appendix of our GEFCom2012 paper. If you don't have access to Science Direct, you can downloaded from my Dropbox link HERE. Regardless where you get the data, you should cite this paper to acknowledge the source:

• Tao Hong, Pierre Pinson and Shu Fan, "Global energy forecasting competition 2012", International Journal of Forecasting, vol.30, no.2, pp 357-363, April-June, 2014. 

What's in the package?

Unzip the file, and navigate to "GEFCOM2012_Data\Load\" folder, you will see 6 files:

• load_history
• temperature_history
• holiday_list
• load_benchmark
• load_solution
• temperature_solution

Our GEFCom2012 paper has introduced the first five datasets but not the last one. The "temperature_solution" dataset includes the temperature data from 2008/6/30 7:00 to 2008/7/7 24:00, while the "load_solution" dataset does not include the load data from 2008/6/30 7:00 to 2008/6/30 24:00.

What's not working?

Before using the data, please understand that

there is no way to restore the exact Kaggle setup for you to make direct comparison on the error score. 

The main reason is that Kaggle pick a random subset of the solution data to calculate the scores for public leaderboard, and the rest for private leaderboard. We do not know which data was used for which leaderboard.

Nevertheless, it was never our intention to let you make comparisons in a Kaggle way. It is because the GEFCom2012 was set up more like a data mining competition than a forecasting competition. The contestants can submit their forecasts many times, while Kaggle was picking the best score. This is not a realistic forecasting process.

How to use the data?

Instead, we encourage you to use these 4.5 years of hourly data without considering the Kaggle setup. You can even keep 4 full calendar years and get rid of the last half a year in your case studies. With four years of data, you can perform one-year ahead ex post forecasting (see my weather station selection paper). You can also perform short term ex post forecasting on rolling basis (see my recency effect paper).

Then the question is whether the accuracy is "good enough". According to Table 3 of our GEFCom2012 paper, the winning teams improved the benchmark by about 30% - see the "test" column, which is the private leaderboard of Kaggle. In other words, if your model is getting about 30% error reduction comparing to the Vanilla benchmark on this dataset, it is a decent model.

Please also understand that this 30% is gained from a forecasting system with many bells and whistles, such as detailed modeling of temperature, and special treatment of holidays. If your research is focus on one components, the error reduction may be much smaller than 30%. You can find a more detailed arguments in my response to the second review comment in THIS POST.

It's been over two years since we published the GEFCom2012 data. Many researchers have already used it to test their models. You can also replicate the experiment setup in the recently published papers that used this GEFCom2012 data, and compare your results with the results on those papers.

Back to Datasets for Energy Forecasting.

Datasets for Energy Forecasting

Reproducible research is a key to advancing knowledge. In energy forecasting, it is necessary and crucial that researchers compare their models and methods using the same datasets. Five years ago when we founded the IEEE Working Group on Energy Forecasting, "lack of benchmark data pool" was one of the issues we identified. Fortunately, things have been changing toward the right direction over the past few years. More and more datasets are being made available to and recognized by the energy forecasting community.

This post will serve as the starting point of a blog series on datasets. In each post, I will feature a dataset and discuss how to use it. I will also host the datasets on Dropbox and provide the links in these posts. Meanwhile, I would like to take a crowd-sourcing approach to making a comprehensive and widely accessible data pool:

• If you can host the datasets through other channels, please contact me. 
• If you know of some public datasets that are not on my list, please contact me. 
• If you have some private datasets that can be made available to the energy forecasting community, please contact me. 

Here is a list of 9 posts with the publicly available data that I have used in my papers. I will update the list with links and additional data sources, so check this page from time to time to see if there is something you need.

Electric load forecasting

1. GEFCom2012
2. GEFCom2014
3. ISO New England
4. RWE npower forecasting challenge 2015

Gas load forecasting

1. RWE npower forecasting challenge 2015

Electricity price forecasting

1. GEFCom2014

Wind power forecasting

1. GEFCom2012
2. GEFCom2014

Solar power forecasting

1. GEFCom2014

Stay tuned...