Decision Support for the Low Voltage Distribution Grid; the Role of Electricity Consumption Time Series

18 November 2021, online
AI for Times Series seminar by Koen Vanthournout (Energyville/VITO)
VAIA, Flanders AI Research & KU Leuven STADIUS

The low voltage distribution grid delivers electricity to our houses and small businesses. Not only is it a critical infrastructure, on which our society depends, it is also a crucial component to realize the energy transition. As such, it is subject to radical (r)evolutions: distributed production (solar panels), electrification of transport and heating (electric cars and heat pumps). Nevertheless, our view on the state of the grid is limited at best, as it is a challenging environment, characterized by sparse and inaccurate data.

After an introduction to the field, we will discuss how the marriage of power systems engineering and artificial intelligence can aid to improve the visibility on the low voltage distribution grid. This enables optimized use of the presently installed assets and helps to limit future investments, so the distribution grid becomes an enabler of the energy transition, rather than a costly bottleneck.

Of special importance to this work are the consumption and production profiles of individual connections to the grid: time series that describe our use of the grid. Despite the rollout of smart metering throughout Europe, measurements remain limited. And these time series are characterized by high stochasticity – human behavior, and are unbalanced – few, yet for us all-important power peaks. We will discuss the properties of electricity profiles, and the work to statistically model and ultimately forecast them.

Koen Vanthournout received his Master degree in Electrical Engineering (1999) from Groep T Hogeschool in Leuven, Belgium, and his Master degree in Artificial Intelligence (2000) from KU Leuven, Belgium. He obtained a PhD in Electrical Engineering from KU Leuven in 2006. In 2020 he obtained the Postgraduate certificate School of Thinking from the Vrije Universiteit Brussel. From 2006 to 2009, he worked as a senior embedded software engineer for Icos Visions Systems/KLA-Tencor, after which he joined VITO, the Flemish Institute for Technological Research, and EnergyVille. In 2017, he co-founded ENION, a service provider for custom battery systems for SME’s, after which he returned to VITO and EnergyVille. He is currently working on smart grids, demand response, and the management of distribution grids.


  • 18 November 2021, 14.30-15.30h
  • Location: online streaming
    Due to the current rising covid infections, this lecture is exclusively online: physical attendance is no longer possible.
  • Contact: Philippe Dreesen & Katrien De Cock
  • Language: English
  • Target audience: anyone with an interest in AI and time series


  • Price: free
  • Registration is not necessary, you can simply join the seminar.
    However, if you would like to be reminded of this seminar, fill in your contact details below and you will receive a notification on the day of the seminar.

AI for Time Series Seminars

Several research groups in the Flanders AI Research Program (FLAIR) conduct world-class research on time series, both in the development of algorithms and tools, as in a wide area of application fields. In a recent poll in the Flanders AI community, ‘time series’ came up as the most wanted topic for future workshops or courses. With this seminar series, we bring together researchers that are interested in, or are conducting research related to, time series. We offer a varied program of national and international speakers.