Session Chairs: Pedro Vergara Barrios, (TU Delft) and Fei Ding, (NLR)

This session examines how generative AI can support distribution systems planning and operation. Distribution systems differ from transmission systems in several ways: large amounts of data are available from consumers, while most distributed energy resources (for example, electric vehicles, solar panels, electric heat pumps) are connected to the electricity infrastructure at medium and low voltage levels. This creates the perfect context for AI: large amounts of data are available, while generalization is needed to handle the rapid pace of context change. Topics include the use of synthetic data generation for distribution systems’ hosting capacity, foundation models using graph-based power flow for scenario-based planning, and risk quantification.

Designing AI models for Intelligent Distribution Grid Operation

Speaker: Zita Vale – ISEP/IPP – Instituto Superior de Engenharia do Instituto Politécnico do Porto / Engineering Institute – Polytechnic of Porto

Power and energy systems transition towards more efficient and sustainable operation requires distribution grids to adopt new decision-making models. With energy resources becoming increasingly distributed and new active roles seen for consumers, virtual power producers, and energy communities service procurement is becoming increasingly important for distribution grids making decision-making an important challenge. Artificial Intelligence-based models are needed to face this challenge, ensuring not only adequate approaches for sustainable and efficient energy use but also enabling the fair and efficient participation of all the involved actors.
This talk will discuss the requirements and options for the design of AI models for distribution grid operation. Data driven and knowledge-based approaches that can ensure the required intelligent decision-making in the frame of current and future power and energy systems will be presented and discussed. Artificial Intelligence traditional paradigms and the boom of the new Large Language Models (LLM) and agentic approaches will be covered and the perspectives of their use will be discussed.

Foundation Models for the Distribution Grid: from Forecasting to Data Correction.

Speakers: Eline Raaijmakers and Evelin Miedema-Bakos – Alliander

We present Alliander’s work on Foundation Models. First, we discuss the S4Forecasting model, for which both the model code and training data have been open sourced, and which has reached pilot maturity (TRL 7). Alliander has also started investigating Foundation Models for correcting DSO-data. We share our initial approach, insights, and next steps.

Beyond Task-Specific AI: Toward Foundation Models for Distribution Grids

Speaker: Fei Ding – National Laboratory of the Rockies

This presentation will introduce ongoing research at the National Laboratory of the Rockies (NLR) toward developing foundation models for distribution grids. We will discuss the motivation, technical approaches, and key considerations in building models that can capture the complex characteristics of distribution systems while enabling knowledge transfer across networks, operating conditions, and applications. The presentation will highlight potential use cases, share preliminary findings and lessons learned from our ongoing research, and discuss challenges related to data availability, network heterogeneity, physical consistency, and model generalization. Finally, we will outline future research directions toward scalable, adaptable, and trustworthy foundation models for distribution grid applications.

E.ON AI Strategy

Speaker: Marina Fernández Fernández-Campoamor – E.ON Digital Technology

From Hype to Real Business Impact: How E.ON Is Building an AI Strategy for Its Distribution Grids.
Most grid operators have run AI pilots. Far fewer have turned them into a strategy that delivers measurable value at scale. In this session, Marina Fernández shares how E.ON approaches AI across its European distribution network operators: how priorities are set, how value is assessed, and how the organization is structured to move AI from isolated use cases into everyday grid operations.
Key topics:

• Strategic direction: how the energy transition, grid expansion and regulatory efficiency targets shape where E.ON invests in AI
• Prioritizing use cases: a business value framework for selecting and sequencing initiatives
• From pilot to production: data foundations, platforms and governance for operational technology environments
• Generative and agentic AI: where they add real value in a regulated, safety-critical context, and where they do not (yet)
• Organization: building a central Data & AI team that serves multiple DSOs
• Lessons learned: what worked, what did not, and what we would do differently