AI@IFIC Hackday: Predicting renewable energy outputs using Machine Learning

1001-Primera-135 - Nave Exp. Sala de Audiovisuales (Universe)

1001-Primera-135 - Nave Exp. Sala de Audiovisuales



This is the first of AI@IFIC hackdays, this time focusing on an issue important to climate change, the accurate prediction of variable energy sources such as wind and solar. 

During this half-day we will explore the use of Machine Learning techniques to forecast variable low-carbon energy sources. We will start by using public sources such as 

Photovoltaic UK data

and correlate them with weather measurements and projections to predict future production. 

The idea is to explore a range of methods such as RNNs and LSTMs as well as regular NNs.

Previous to the meeting, we ask participants to register in Google Colab and/or setup their computers to run jupyter notebooks and conda. We may release a docker for this meeting.

    • 10:00 10:30
      Introduction to the problem: computing framework and data sources
    • 10:30 13:30
    • 13:30 14:00
      Presentation of results
Your browser is out of date!

Update your browser to view this website correctly. Update my browser now