AI Modelling and Time-series Forecasting Systems for Trading Energy Flexibility in Distribution Grids

TL;DR

This paper presents AI-based modeling and forecasting systems that assist distribution grid operators in managing renewable energy integration by predicting congestion and energy flexibility needs, demonstrated across European sites.

Contribution

It introduces novel AI tools for probabilistic grid modeling and scalable time-series forecasting, supporting renewable integration in distribution grids.

Findings

Effective congestion prediction using probabilistic graphs.

Scalable short-term energy demand and generation forecasts.

Successful deployment at multiple European sites.

Abstract

We demonstrate progress on the deployment of two sets of technologies to support distribution grid operators integrating high shares of renewable energy sources, based on a market for trading local energy flexibilities. An artificial-intelligence (AI) grid modelling tool, based on probabilistic graphs, predicts congestions and estimates the amount and location of energy flexibility required to avoid such events. A scalable time-series forecasting system delivers large numbers of short-term predictions of distributed energy demand and generation. We discuss the deployment of the technologies at three trial demonstration sites across Europe, in the context of a research project carried out in a consortium with energy utilities, technology providers and research institutions.