Skip to content

alliander-opensource/Light-Learning-Estimator

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

17 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Light EDGE Learning Estimator challenge

Alliander shapes the energy future of the Netherlands

We stand for an energy supply that gives everyone access to reliable, affordable and sustainable energy under equal conditions. That's what we work on every day. By continuously improving our network, we prepare for the future. A future in which everyone can use, produce and share sustainable energy.

Alliander develops and manages energy networks. More than three million Dutch households and businesses receive electricity, gas and heat via our cables and pipelines. We manage more than 90,000 km of electricity grid and 40,000 km of gas grid and are proud that our grids are among the most reliable in the world. Our 7000 colleagues ensure that the light is on, the houses are warm and the businesses are running. We do this in the interests of society to keep energy reliable, affordable and accessible for everyone.

This assignment has been drawn up by the research center and directly contributes to the reliability of our energy grid. The Research Center for Digital Technologies is shaping the digital networking company of the future. Through this challenge we investigate how we can use small forecasts, namely those of the individual householdns, added together to make a better forecast and for the consumptionof tomorrow. With a better forecast, weare better able torespond to anyproblems. Through this challenge you contribute directly to the energy transition!

The Light Learning Estimator

The Light Learning Estimator (LLE) periodically makes a forecast for each individual household. These households provide cumulative insight into any problems at district level. This software should be able to operate on light weight hardware, for our test this will be a Raspberry Pi 4. The software generates a forecast of your and energy consumption and energy twice a day. When something changes in your use, for example, by purchasing solar panels or a charging station at home, the estimator adjusts within a few days and the forecast becomes accurate again.

The LLE is a continuous learning, predictive algorithm that runs on light hardware located at the ends of the network. The advantages for users and Alliander/Liander at a glance:

Advantages of Alliander:

  • Better insight into expected energy consumption of households, and therefore district and the electricity grid
  • And thus being able to better remedy malfunctions

Benefits for users:

  • Privacy-sensitive data stays within the household's smart meter

In this challenge you will work to develop this piece of software. Of course, there is also something in return: In addition to eternal fame, the first prize is €1,000,-.The deadline for submission is February 13th 2022, 23:59. Evaluation will be finished at the end of March

Further instructions for the challenge can be found here. If you have any questions or things are unclear, let us know.

Enjoy!

N.B.

  1. Sign up HERE for the challenge.
  2. After signing up, you will get an NDA and processing agreement. Because you will get access to real user data, these have to be signed.
  3. After signing these agreements, you will get access to data and further instructions, and you can start solving the problem.

Contact: Leon de Jong

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages