IEEE-CIS Technical Challenge on Energy Prediction from Smart Meter Data

End Date:
11/15/2020
Citation Author(s):
Isaac
Triguero
University of Nottingham
Submitted by:
Isaac Triguero
Last updated:
Mon, 09/07/2020 - 11:46
DOI:
10.21227/2npg-c280
Data Format:
License:
Creative Commons Attribution

Abstract 

Imagine you just moved to your brand-new home and hired your energy provider. They tell you that based on the provided information they will set up a direct debit of €50/month. However, at the end of the year, that prediction was not quite accurate, and you end up paying a settlement amount of €300, or if you are lucky, they give you back some money. Either way, you will probably be disappointed with your energy provider and might consider moving on to another one.

Predicting energy consumption is currently a key challenge for the energy industry as a whole. Predicting the consumption in a certain area is massively complicated due to the sudden changes in the way that energy is being consumed and generated at the current point in time. However, this prediction becomes extremely necessary to minimize costs and to enable adjusting (automatically) the production of energy and better balance the load between different energy sources.

Smart meters are being rolled-out in many countries for domestic use, becoming powerful devices to track energy use. Smart meters will not only play an increasingly large role in the way customers consume energy but also in the way they choose a supplier. If energy providers developed new products for their customers that help them understand the potential benefits of smart meters (e.g. reducing bills or managing their finances better), this could be key to attracting and retaining customers. At a higher level, being able to use smart meter data to better manage demand will contribute to the increasing use of sustainable sources of power and reduce the demands on more traditional power generation.

Researchers from the IEEE Computational Intelligence Society (IEEE-CIS) want to improve energy prediction based on Smart meter data, while also improving the customer experience. IEEE-CIS works across a variety of Artificial Intelligence and machine learning areas, including deep neural networks, fuzzy systems, evolutionary computation, and swarm intelligence. Today they’re partnering with the leading international energy provider, E.ON UK plc., seeking the best solutions for energy prediction using Smart meters, and now you are invited to join the challenge.

From a machine learning point of view, the provided data is very challenging and may lead to the development of novel learning approaches. Some of the challenges include incomplete data (i.e. missing values), use of external data sources to handle seasonal effects, different kinds of households (e.g. families vs. single, old house vs. new built), or lack of sufficient information about the households. If successful, you will not only help many to automatically control their energy bills, but the proposed technical challenge may be applicable in many other similar fields facing time-series prediction problems.

Please report any issues or feedback to Isaac.Triguero@nottingham.ac.uk

Instructions: 

Data description and submission requirements

IMPORTANT: Data has been updated on September 7th, 2020 after finding a bug in the timestamps.

The goal of this competition is to predict the monthly electricity consumption for 3248 households in a coming year (January to December). You are provided with historical half-hourly energy readings for the 3248 smart meters. To simulate a realistic use case, we take the 1st of January of a given year as the day we want to make predictions. Thus, different smart-meters will have available a range of months’ worth of consumption, ranging from only last month (i.e. December) to the entire last year (January to December), acknowledging that customers may have joined at different times during the previous year. For example, we may have a few customers for which we only have data from last December, and we aim to predict January to December of the coming year, whilst for others, we may have the entire January-to-December time series. We would like to see how well we can predict the coming year depending on the amount of data that is available. 

For each meter_id in the provided dataset, you must predict the consumption in the following 12 months in kWh. In addition, you are requested to submit a draft description of your methodology (up to 1000 words).

Full description of the data and submission requirements can be downloaded here

Evaluation 

Our partner E.ON is interested in predicting with the least amount of data as possible a good estimate of the total year consumption for reasons of payment adequacy. In addition to that, an accurate monthly consumption prediction is also very valuable for Energy Trading teams, who need to be able to predict with some accuracy how much electricity to buy on the energy market. We will use the relative absolute error for monthly and yearly predictions. See the Leaderboard at the bottom of the page or alternatively here.

Details about the evaluation can be found here

Note that the Leader Board table is updated every 5 minutes. In case you submit a wrongly formatted submission, you will be listed at the top of the table with an empty row.

At the end of the competition, and looking at the aspects explained above, the Technical and Scientific Committees will shortlist the top 5 submissions. Shortlisted authors will be asked to provide a final description of their methodology (4 pages in IEEE format, more details will be provided at the time).

Final submissions will be carefully assessed according to the following criteria:

-        Performance in different scenarios, including annual and monthly predictions, as well as predictions with limited historical data of the user.

-        Novelty of the proposed approach and appropriate use of Computational Intelligence techniques if any (not required!). The Scientific committee will be asked to rank the shortlisted independently and this will be used to compute a score.

 Note that use of data other than the one provided is not allowed. If you do so, we will not consider your submission.

Timeline

-        August 15th, 2020 – Competition start.

-        November 15th, 2020 – Final submission deadline.

-        November 18th, 2020 – Shortlisting announcement.  

-        November 25th, 2020 – Deadline final description report.

-        December 1st, 2020 – Shortlisted solution presentations at the 2020 IEEE Symposium Series on Computational Intelligence (SSCI). The conference will be held virtually and registration for the 5 shortlisted submissions will be covered.

-        December 4th, 2020 – Awards ceremony

All deadlines are at 11:59 PM UTC on the corresponding day unless otherwise noted. The competition organisers reserve the right to update the contest timeline if they deem it necessary.

 

Prizes

Awarded by the Committee based on the criteria mentioned above.

-        1st Prize: $7,000

-        2nd Prize: $5,000

-        3rd Prize: $3,000

-     4th and 5th Prizes: $1,000

All teams, regardless of place, are also strongly encouraged and invited to publish a manuscript of their solution (and open source their code, if possible).

 

Technical Challenge Committee

•       Isaac Triguero (Chair, Associate Professor, University of Nottingham)

•       Catherine Huang (Principal Engineer, McAfee LLC)

•       Hussein Abbass (Professor, University of New South Wales)

•       Juan Bernabé-Moreno (Chief Data Officer E.ON SE)

•       Luis Magdalena (CIS VP TA, Universidad Politécnica de Madrid)

•       Manuel Roveri (Professor, Politecnico di Milano)

Scientific Committee

TBA

Acknowledgements

E.ON SE provided the dataset for this competition. E.ON is an international, privately owned energy supplier based in Essen, Germany. With a clear focus on two strong core businesses E.ON aim to become the partner of choice for energy and customer solutions. E.ON provide solutions for the new energy world.

The Chairs of the IEEE-CIS Technical Challenge Committee would like to extend our thanks to:

-      Dr Robert Eigenmann, Nicholas Harbour and Dr Stefan Birr from the E.ON team.

-        Selvi Ergen, KTP associate, funded by E.ON and Innovate UK under KTP project 11094.

-        Heda Song, PhD student and Researcher at the University of Nottingham.

Leaderboard

Comments

Dear participants,

Unfortunately, we have found a mistake in the data we uploaded initially, and I have just uploaded an updated version.

Please accept our apologies for this.

Thanks to Dr Jessa Bekker and her team for finding this.

Best wishes,
Isaac

Hi,

I am not able to download the Data.zip. Could you please check?

Regards
Anjanita

Dear all,

Someone asked about how we handled the potential missing values in the test set, and we didn't specify that above. So, just so you all are aware, the missing values in the test set (if any) were imputed using a simple linear interpolation on a daily level.

Best wishes,
Isaac

Competition Dataset Files

AttachmentSize
Package icon data.zip44.6 MB
ACCESS ON AWS

Documentation