Energy forecasting service helps energy industry companies overcome the challenges in the shift towards renewables. VTT EnergyTeller is an AI-powered service for forecasting future energy needs and market developments more accurately.
Key facts about VTT EnergyTeller energy forecasting service
VTT EnergyTeller is an AI-powered energy forecasting service that uses state-of-the-art hybrid modelling
Optimise prices and production with more accurate behaviour models of the energy market
Apply forecasts in different states of the electricity sector: production, distribution and consumption
Why the need for energy forecasting service?
The energy sector is undergoing a profound shift towards renewables and carbon neutral production of electricity. Simultaneously, the reliability requirements for power systems are becoming stricter reliability requirements for energy supply and the grid – the backbones of an effective energy market.
The shift also adds to the complexity of the operational environment and decreases the accuracy of energy forecasts. The volatility of market prices increases in response to changing weather conditions and their impact on energy demand.
At the same time, we now have more data available than ever. With the right energy forecasting service, you can leverage the market and grid data to create accurate forecasts. You can use the forecasts to optimise the transition towards renewables and ensure reliable energy availability in any situation.
In Finland, a 1% error in wind power forecasting costs roughly €300,000/year in imbalance settlements
VTT EnergyTeller uses AI to enable better energy forecasts
VTT EnergyTeller is an AI-powered solution that combines physics-based models and expert knowledge. It is an energy forecasting software designed to help optimise the production, distribution and consumption of electricity.
The solution can be used to benchmark your existing energy and load forecasts against state-of-the-art methods and the latest research. Just as importantly, the software works as a rapid forecasting solution for getting on top of your unsolved forecasting challenges.
Cost-savings and optimisation for electricity generators
More comprehensive models of the behaviour of the energy market enables producers to
- Predict energy prices according to historical data and weather forecasts
- Optimize your bidding strategy
- identify the best energy markets for your own generation profile
Among others, VTT EnergyTeller provides accurate forecasts of the weather and temperature, available generation capacity and the capacity need for battery-electricity storage systems. It can also be used to optimise the operations of combined heat and power (CHP) plants through storage and sector coupling.
More efficient and reliable electricity distribution
Combining data-based and physical models through hybrid modelling enables the optimisation of different energy applications, such as reactive power compensation and grid congestion issues.
Forecasting consumer behaviour and changes in power profiles throughout the day enables the effective compensation of reactive power.
VTT EnergyTeller can also help to identify potential grid congestion issues by spotting energy demand increases in specific areas. Power flow can be optimised when demand is high in specific areas.
Accurately predict the tomorrow’s energy demand
VTT EnergyTeller helps you optimise the use of your energy resources.
You can for example predict future demand in large buildings, industrial applications and energy communities to make full use of their flexible energy resources:
- Bid your flexibility in the energy markets
- Enable demand-response and optimise your demand according to forecasted prices.
Profound energy market and AI expertise
At VTT, we have combined the expertise of energy systems and markets modelling with expertise in state-of-the-art AI technology. This winning combination is here to help you identify the optimisation potential hidden in your data.
Our solution is versatile and fully customizable to your needs. As a research centre, we are a neutral partner committed to the improvement of society.
VTT EnergyTeller is already used by major players in the energy industry. Get in touch and we can share some of the stunning results that the more accurate energy forecasts have yielded.
CapFor Online for Fingrid: taking power generation capacity forecasts to a whole new level
Providing an accurate power capacity forecast is no easy task. And it gets even harder in a modern market that includes a diverse mix of generation sources and requires detailed forecasts. The CapFor Online software created in collaboration with Fingrid – Finland’s transmission system operator (TSO) – helps solving this challenge that is well known by many grid operators.
How to work with us
Our lean process delivers results fast
-
Specification
VTT’s experts collaborate with you to create a specification of the challenge and check existing results. -
Proof-of-Concept
Data pre-processing, modelling and evaluation to assess the potential of the solution before full investment. -
Customisation
Scripts and models are turned into concrete operational software, full-scale tool that meets your needs. -
Delivery
Handing over the forecasting software as an integration to your infrastructure or a standalone tool. -
Continuous improvement
VTT’s experts monitor and maintain optimal performance with retraining and updates.
Contact us here!
VTT’s energy forecasting experts
To provide you with optimal forecasts, our energy forecasting team combines expertise in smart grids and artificial intelligence.
Sergio Motta is the Research Team Leader of the Smart Grids team at VTT. He has international experience in teaching, product development and research in Smart Grids related topics. His research activities are focused on Artificial Intelligence applications in Power Systems, Microgrids, Integration of DER and e-mobility infrastructure, and Reliability of Power Systems.
Dr. Jussi Kiljander (M) is a Senior Scientist at VTT. He received his M.Sc. (Technology) in 2010 and PhD in 2016 from University of Oulu. His current research focuses on machine learning and its applications on smart grids and consumer flexibility management. In particular, his research interest includes deep learning for time series data, model-predictive-control and hybrid-modelling. He has been a project manager, technical coordinator and work package leader, in several EU and national projects. He has co-authored over 35 publications.
