Data mining for predicting electricity consumption

September 14, 2007 by
Filed under: data mining application, electricity consumption 

Since I’m close to finishing my PhD, I’m looking around to find a new job in data mining. Actually, this is a nice opportunity to discover possible application areas for data mining methods. Indeed, I was recently invited by Girsberger Informatik AG (Switzerland) for an interview. They have a small sized company that proposes to make predictions of electricity consumption. Their customers include big and mid-range electricity suppliers in Switzerland. In a few words, they get data about electricity consumption from their customers, perform some predictions using their own software and give them back to customers.

They work in collaboration with MeteoSwiss for getting weather forecasts. This is obviously of importance since users will use more electricity if, for example, clouds are present during the day. Girsberger Informatik uses neural networks to train on data from previous years and make predictions for the following days. Every morning, after getting data from MeteoSwiss and having trained their neural net, an email is automatically sent to their customer with the predictions of electricity consumption for the following week.

Share

Comments

4 Comments on Data mining for predicting electricity consumption

  1. Anonymous on Sat, 15th Sep 2007 8:05 pm
  2. where’s the exploratory part there, pal?

  3. Will Dwinnell on Mon, 17th Sep 2007 11:15 am
  4. Best of luck in your job search!

  5. Sandro Saitta on Thu, 20th Sep 2007 1:14 pm
  6. Thanks! I hope to find a job in industry at least as interesting as my current research :-)

  7. Elham on Wed, 7th Jan 2015 8:16 am
  8. Hi
    Would you please send me your whole essay?
    I would be thank full

Tell me what you're thinking...





  • Swiss Association for Analytics

  • Most Popular Posts

  • T-shirts, Mugs & Mousepads


    All benefits given to a charity association
  • Data Mining Search Engine

    Supported by AnalyticBridge

  • Archives

  • Reading Recommandations