LF Energy Summit Europe 2026: Full Schedule

15 - 16 September | Berlin, Germany
View More Details & Registration Information
Note: The schedule is subject to change.

The Sched app allows you to build your schedule but is not a substitute for your event registration. You must be registered for LF Energy Summit Europe 2026 to participate in the sessions. If you have not registered but would like to join us, please go to the event registration page to purchase a registration.

This schedule is automatically displayed in CEST(UTC/GMT +2). To see the schedule in your preferred timezone, please select from the drop-down menu to the right, above "Filter by Date."

10:30 CEST

OpenSTEF 4 Launch: A new way of building energy forecasting solutions - Daan van Es, Alliander; Jan Maarten van Doorn, Sigholm & Paula Passet, SIA Partners

Tuesday September 15, 2026 10:30 - 11:00 CEST

Seebühne

At this year’s LF Energy Summit, we will officially launch OpenSTEF 4. A major milestone for the project and its growing community!

OpenSTEF 4 introduces a more modular and flexible approach to energy forecasting. The strength is in its versatility: a comprehensive toolbox that can support a wide range of forecasting use cases across the energy domain.

Whether you are exploring new ideas as a researcher or working in a high-stakes scaled up environment, OpenSTEF adapts to your needs. From data preparation and feature engineering to custom models, ensembles, and benchmarking, it enables you to shape your forecasting workflow in a way that fits your data, your systems, and
your use case.

OpenSTEF is also deliberately open and unopinionated. You decide how and where to deploy it, and which tools you use around it.

During this session, we will present the key changes in OpenSTEF 4, present a genAI pipeline that creates new documentation for this and future releases, and present a testimonial from a community member migrating from version 3 to 4. Following the presentation, we invite interested participants to join a dedicated tutorial, where you can explore the new setup in more detail and gain hands-on experience with OpenSTEF 4: https://events.linuxfoundation.org/lfenergysummit-europe/program/schedule/

Whether you are already working with OpenSTEF or just getting started with energy forecasting, this session marks the beginning of the next phase of the project.

Speakers

Jan Maarten van Doorn

Data Scientist, Sigholm Tech AB

Paula Passet

Data Science Consultant, Sia Partners

Paula Passet is a Data Science Consultant at Sia with expertise in AI/ML and GenAI. She is currently running a proof of concept to explore how GenAI can support documentation generation and maintenance for open-source energy forecasting projects.

Daan van Es

Chair, OpenSTEF Technical Steering Committee | Alliander, Alliander

I work at Alliander on forecasting energy load across the electricity grid for the upcoming hours to days. As Chair of the OpenSTEF Technical Steering Committee, I help guide the development of open source forecasting tools and foster collaboration across the energy sector.

Tuesday September 15, 2026 10:30 - 11:00 CEST
Seebühne

Data + AI, Session Presentation

11:05 CEST

Redispatch Without Black Boxes: Load Forecasting With OpenSTEF at E.ON - Alexander Geiseler, E.ON Digital Technology

Tuesday September 15, 2026 11:05 - 11:35 CEST

Seebühne

For reliable and cost-efficient distribution grid operation and redispatch management, accurate short-term forecasting is a core prerequisite. At E.ON, we originally relied on vendor-built “black box” forecasting solutions and experienced the familiar trade-offs: slow iteration cycles, limited transparency, and dependence on external roadmaps. In this talk, I’ll share our journey to an open-source target picture for transformer load forecasting in a redispatch context. After a quick intro to the redispatch problem and our system setup, I’ll walk through our OpenSTEF-based approach. I’ll then present results from a real benchmark against an external model and the practical lessons learned; what mattered, what didn’t, and where open source helped us move faster. Finally, I’ll cover the organizational path: how we navigated compliance and governance with our Open Source Office to turn from user into contributor.

Speakers

Alexander Geiseler

AI Software Engineer, E.ON Digital Technology GmbH

Alexander Geiseler is a seasoned AI Software Engineer at E.ON Digital Technology, focusing on forecasting and data-driven solutions for grid operations. He currently works on transformer-level load forecasting in the context of redispatch management and is actively driving the adoption... Read More →

Tuesday September 15, 2026 11:05 - 11:35 CEST
Seebühne

Data + AI, Session Presentation

13:10 CEST

Predico: A Collaborative Forecasting Market for the Energy Sector - José Ricardo Andrade, INESC TEC

Tuesday September 15, 2026 13:10 - 13:40 CEST

Waldbühne

Predico is a collaborative forecasting platform developed by INESC TEC that turns energy forecasting into a daily market with two sides: buyers procure forecasts for the assets they operate, and multiple forecast suppliers compete to provide them, rewarded based on their accuracy. Their submissions are combined into a single, sharper forecast by Predico's open-source forecasting engine. This session introduces the platform and shares what we have learned from more than a year of running Predico in real operational pilots.

Speakers

José Ricardo Andrade

Researcher, INESC TEC

José Andrade obtained an M.Sc. degree in Electrical and Computer Engineering from the Faculty of Engineering of the University of Porto (FEUP), Portugal, in 2016. He currently works as a researcher at the Centre for Power and Energy Systems at INESC TEC, where he actively contributes... Read More →

Tuesday September 15, 2026 13:10 - 13:40 CEST
Waldbühne

Data + AI

13:45 CEST

How To Orchestrate RL Agents for Topological Remedial Actions Using PowSyBl’s Operator Strategy - Harald Jendrian, TUM School of Engineering and Design

Tuesday September 15, 2026 13:45 - 14:15 CEST

Waldbühne

We bring LF Energy's PowSyBl into the control room as a decision support tool, combining grid analysis with Reinforcement Learning to solve post-contingency problems immediately. Increasing complexity amplifies overloads, demanding corrective actions beyond what manual operator heuristics and existing tools can deliver in time. Open-source RL agents backed by PowSyBl learn curative topology reconfigurations for the Simbench EHV network in Node-Breaker representation. Agents observe bus voltages, line loadings, injection profiles, and switching states. The action space controls breakers and disconnectors via valid action masks for node splitting, busbar re-assignment, and line (dis)connection. Remedial actions are injected as Operator Strategy actions inside PowSyBl's Security Analysis, faithfully reproducing N-1 assessment in training. We discuss reward design, bonuses, penalties, and action-masking. The talk ends with a live demo: a Leaflet map with colour-coded loadings, interactive single-line diagrams, forecast plots, and a control panel triggering Security Analysis and visualising corrective actions via PowSyBl's Operator Strategy in real time.

Speakers

Harald Jendrian

Scientific Staff & Founding Engineer, Technische Universität München

With a strong background in power systems, Harald is currently working on Reinforcement Learning applications for transmission grid operation. At Nodus Software, he helps TSOs and DSOs with the deeper integration of the next generation of grid analysis tools. At TUM, he focuses on... Read More →

Tuesday September 15, 2026 13:45 - 14:15 CEST
Waldbühne

Data + AI, Session Presentation

14:20 CEST

AINETUS - AI for Safety-Critical Network Infrastructures - Gil Sampaio, INESC TEC

Tuesday September 15, 2026 14:20 - 14:30 CEST

Waldbühne

This talk will present the LF Energy project AINETUS, which implements AI-based decision-support (AI assistant) capabilities for power system operations, addressing the increasing complexity of modern grids driven by high levels of renewable energy integration. Traditional tools are often limited in their ability to anticipate system dynamics and support operators under rapidly changing conditions. AINETUS tackles this gap by combining data-driven techniques with domain knowledge to provide proactive, explainable, and operator-centric support.
It will show a set of components designed to work together or independently within existing operational environments, in particular: (1) Human-AI interaction tools that enhance situational awareness. (2) Reinforcement learning agents that identify optimal operational strategies, capable of adapting to evolving grid conditions while respecting physical constraints.
(3) Explainability tools and uncertainty estimation that help to provide transparent recommendations to support informed decision-making.
AINETUS is designed to integrate with existing platforms and workflows, leveraging environments such as Grid2Op for training and validation.

Speakers

Gil Sampaio

Researcher, INESC TEC

Tuesday September 15, 2026 14:20 - 14:30 CEST
Waldbühne

Data + AI, Lightning Talk

14:30 CEST

Towards Industrial Grid Foundation Models With PowSyBl and GridFM - Nicolas Lair, Artelys

Tuesday September 15, 2026 14:30 - 14:40 CEST

Waldbühne

This lightning talk presents the integration of the PowSyBl framework into the datakit of GridFM, two flagship LF Energy projects, to bridge foundation models and industrial-grade power system simulation. GridFM relies on large-scale synthetic data generation, such as load flows, to train a foundation model, where training data quality directly impacts model performance during inference.
The integration of PowSyBl brings several key benefits. It extends GridFM to realistic and industrial-grade network models by supporting multiple formats (CIM, CGMES, PSS/E), enabling the use of richer and more representative datasets. It provides access to an industrial-grade load flow solver through Open Load Flow, improving the physical consistency and accuracy of generated data. Finally, it enables the generation of dynamic simulation data through Dynawo, opening the way to foundation models trained on both static and dynamic grid behaviours.
Overall, this integration is a key step toward the industrialization of grid foundation models, enabling their application to real-world power system studies.

Speakers

Nicolas Lair

AI Project Director, Artelys

Nicolas Lair is an AI & Data Science Project Manager at Artelys, specializing in the application of AI, optimization, and advanced analytics to complex systems, particularly in the energy sector. He holds an engineering degree from École Polytechnique and a PhD in computer science... Read More →

Tuesday September 15, 2026 14:30 - 14:40 CEST
Waldbühne

Data + AI, Lightning Talk

14:40 CEST

OpenSynth Dataset Extension - 7K Challenge - Pierre Olivier Cayetanot, CRESYM & Josh Cooney Mercadal, eRoots Analytics

Tuesday September 15, 2026 14:40 - 14:50 CEST

Waldbühne

Last year, the LF Energy project OpenSynth expanded with the launch of D-GITT, an open data hub featuring the RTE7K dataset: a dataset of the whole French transmission grid, including topological changes over three years. Striking the interest of other actors in opening their own dataset, RTE7K demonstrated its values as a realistic, open benchmark for grid analysis.

Now, RTE, CRESYM, eRoots and IRT SystemX joined forces to launch the 7K Challenges, a series of challenges centered around the dataset. The first one, kicking off at this summit, focuses on tackling the "missing piece" for running powerflows on the RTE7K dataset: power injection data. Participants are tasked with producing realistic, synthetic injections using whatever public data and methodology they can come up with. As well as being an enticing challenge for participants, the outcome will be a critical extension to the RTE7K dataset that will enable further users to test and validate tools using data comparable to what was previously exclusive to TSOs.

Future challenges will explore topics like AI-driven grid topology management, power flow analysis and more, pushing the boundaries of what’s possible with open grid data.

Speakers

Josh Cooney Mercadal

Power Systems Engineer, eRoots Analytics

Josh is a power systems engineer at eRoots Analytics based in Barcelona. He is applying his background in high energy physics to the modelling of large grids, in particular the digital twin of the Iberian power grid built at eRoots.

Pierre-Olivier Cayetanot

IT Asset & Project Manager, CRESYM

IT Asset and Project Manager at CRESYM, I bridge data engineering and energy systems to advance open-source solutions.

Coordinating CRESYM's Infrastructure Asset Management focus group, I drive FOSS projects to accelerate the energy transition.

Tuesday September 15, 2026 14:40 - 14:50 CEST
Waldbühne

Data + AI, Lightning Talk

15:20 CEST

Predicting Grid Faults Before They Happen: AI for Weather-Driven Grid Resilience - Sebastian Gerber, Sia

Tuesday September 15, 2026 15:20 - 15:50 CEST

Seebühne

Severe weather is the single largest driver of unplanned outages on distribution networks, and climate change is making it less predictable, just as renewable penetration raises the stakes for supply continuity. This session shares how SP Energy Networks (SPEN) and Sia built P4R, a probabilistic system that forecasts the location and expected volume of network faults up to five days ahead, giving control rooms time to pre-position crews and protect customers.

We go under the hood of an open-source ML stack: weather ensemble forecasts (50 members per feature) stored in Zarr, feature pipelines in the Python scientific stack, and XGBoost quantile-regression models that turn weather uncertainty into calibrated probabilistic fault predictions, orchestrated on Kubernetes. We share a hard-won lesson the whole community faces: how to build consistent historical backtests when your most predictive variables (like CAPE, a key thunderstorm indicator) only became available as ensembles recently, and how we reconstruct synthetic historical ensembles to close the gap across 2017-2024.

We close with an invitation: weather-driven reliability forecasting is a shared challenge, a natural candidate for an open LF Energy building block, complementary to forecasting projects like OpenSTEF.

Speakers

Sebastien Gerber

Managing Director, Sia

Sebastien Gerber is Managing Director for Energy, Utilities, Data & AI at Sia UK & Ireland, where he leads strategic programmes helping utilities accelerate digital transformation and improve power system resilience. With over 20 years of experience in the energy sector, he has worked... Read More →

Tuesday September 15, 2026 15:20 - 15:50 CEST
Seebühne

Data + AI

15:20 CEST

Towards GridFM: GENCO – a Unified Neural Solver for Steady-state Grid Analysis - Thomas Brunschwiler & Alban Puech, IBM Research

Tuesday September 15, 2026 15:20 - 15:50 CEST

Waldbühne

Last year, we introduced a basic Grid Foundation Model (GridFM) for power flow. This year we released GENCO – the GEometric Neural Corrective Optimizer, a neural solver for steady-state transmission-grid analysis. It unifies three grid-analysis tasks that are typically handled by separate pipelines: power flow (PF), optimal power flow (OPF), and state estimation (SE). GENCO represents the grid as a heterogeneous graph and iteratively refines solutions using task-specific physical decoders, box constraints, and explicit power-balance residuals. GENCO achieves state-of-the-art performance against specialized model baselines and classical solvers, with 5× and 200× speedup for AC-PF and AC-OPF respectively, as well as improved robustness in SE under sparse observability conditions. Beyond the model, we released gridfm-datakit for realistic grid data generation, gridfm-graphkit for low-code training and evaluation, and benchmark datasets spanning PF and OPF instances. By unifying model architecture, data generation, training, inference, and benchmarking, this end-to-end framework shortens innovation cycles and reduces integration efforts for the LFE community.

Speakers

Thomas Brunschwiler

Principal Research Scientist and Manager, IBM Research - Europe

Dr. Brunschwiler is a Principal Researcher and Research Manager at IBM Research – Zurich, where he leads the AI for Climate Impact team. His research advances the frontier of large-scale Foundation Models for Earth sciences. In this context, he spearheads IBM’s efforts exploring... Read More →

Alban Puech

PhD Researcher, IBM Research

Alban Puech is a PhD candidate at IBM Research and ETH Zurich, developing GENCO. He is a lead contributor to the Linux Foundation’s GridFM project. He previously conducted visiting research at Harvard in Prof. Xie’s lab and holds an M.S. from EPFL and a B.S. in Mathematics and... Read More →

Tuesday September 15, 2026 15:20 - 15:50 CEST
Waldbühne

Data + AI, Session Presentation

15:55 CEST

From Open Data To Foundation Models: Building GridSFM for Power Grid Analysis - Andrea Britto Mattos Lima, Microsoft Research

Tuesday September 15, 2026 15:55 - 16:25 CEST

Waldbühne

We present GridSFM, an open-source dataset and foundation model that enables building and operating transmission-scale power grid models from open data to machine learning inference.

Starting from publicly available sources in the United States (OpenStreetMap, U.S. EIA, and U.S. Census), our pipeline constructs geographically grounded, AC-OPF-solvable U.S. power grid models at continental scale. Importantly, our modeling pipeline can be extended to other locations where similar open data is available.

On top of this data layer, GridSFM introduces a physics-informed foundation model trained across a diverse mix of grid topologies and operating scenarios to predict AC-OPF solutions in milliseconds, enabling fast feasibility screening and solver acceleration.

This session will walk through the full stack: from open data ingestion and model construction to ML training and deployment. We will share lessons learned building reproducible, large-scale grid datasets and integrating physics constraints into learning systems.

Speakers

Andrea Britto Mattos Lima

Senior Research Software Engineer, Microsoft Research

Andrea Britto Mattos Lima holds B.Sc. and M.Sc. degrees in Computer Science from the Institute of Mathematics and Statistics at the University of São Paulo, Brazil. She joined Microsoft Research in 2021 and is currently part of the Catalyst Lab.

Tuesday September 15, 2026 15:55 - 16:25 CEST
Waldbühne

Data + AI, Session Presentation

16:30 CEST

EnerGNN: A Graph Neural Network Library for Real-life Complex Energy Systems. - Balthazar Donon, RTE (Réseau de Transport d'Électricité)

Tuesday September 15, 2026 16:30 - 17:00 CEST

Waldbühne

EnerGNN is an open-source python package that aims at bridging the gap between research on Graph Neural Networks (GNNs) and industrial operation of energy networks.

This package includes:
- A faithful and adaptive data representation tailored for large scale industrial systems made of interacting entities.
- A modular library of GNN implementations designed to handle such data.
- A clear interface for business-driven use-case.
- A modular training loop for training GNNs on your specific use-case.

It is the result of 8+ years of research at RTE (Réseau de Transport d'Électricité) and academical partners (Université Paris-Saclay & Université de Liège). It is currently being used for multiple use-cases at RTE, and has shown its ability to scale to the full HV-EHV French system, and to output meaningful and high-precision predictions.

This presentation aims at showing the potential of our open-source package EnerGNN, and to attract potential users and contributors to help us on the following topics :
- GNN acceleration, robustification and improvement,
- Application of EnerGNN to new use cases,
- Extension of EnerGNN to other industrial domains.

Speakers

Balthazar Donon

Research Officer, RTE (Réseau de Transport d'Électricité)

Balthazar is a research officer at RTE (Réseau de Transport d’Électricité) Research & Development. He mainly works on designing an AI algorithm to help power grid operators.
He graduated from the École polytechnique and Stanford University. He obtained a PhD in Computer Science at Université Paris-Saclay and RTE R&D under the supervision of Isabelle Guyon, Marc Schoenauer, and Rémy Clément. He then worked as a postdoctoral researcher at the Unive... Read More →

Tuesday September 15, 2026 16:30 - 17:00 CEST
Waldbühne

Data + AI, Session Presentation

10:30 CEST

OpenSynth: Open Experiments in Low-carbon Technology Detection & Disaggregation - Gus Chadney & Ian Goddard, Centre for Net Zero; Jacco Heres, Alliander

Wednesday September 16, 2026 10:30 - 12:10 CEST

Back Stage

Detecting low-carbon technologies (LCTs) from smart meter data, and disaggregating their individual consumption profiles, is becoming increasingly important as electrification reshapes electricity systems. This interactive workshop will explore emerging approaches for technologies such as EVs, heat pumps, solar PV, and batteries from Advanced Metering Infrastructure (AMI), or smart meter, data using open and reproducible methods.

Hosted by researchers from the Centre for Net Zero, the session will combine presentations with collaborative, hands-on experimentation using open datasets and starter notebooks. Participants will explore machine learning and demand disaggregation techniques, discuss benchmarking and evaluation challenges, and consider the operational value of LCT detection for forecasting, flexibility, and network planning.

The workshop is designed to foster collaboration between researchers, industry practitioners, and open-source contributors working at the intersection of energy systems and data science. Whilst content is evolving, the focus will remain on practical experimentation, transparent methodologies, and community learning using open tools and datasets.

Speakers

Gus Chadney

Data Lead, Centre for Net Zero

A data professional with experience leading multi-disciplinary data teams in the finance, technology and energy industries. Gus started his career in finance tech consulting before pivoting to data science in several fast moving startup companies. After his own entrepreneurial journey... Read More →

Ian Goddard

Senior Data Scientist, Centre for Net Zero

Data scientist focussed on modeling electricity demand under the adoption of LCTs, and the potential for flexibility to accelerate the transition to a clean energy system

Jacco Heres

Lead Data Scientist, Alliander

Data Scientist Lead at Alliander, specialised into estimating the load on the grid using measurements, grid topology and smart meter data. Also I have been working and am still interested in performing long and medium term forecasts for the power grid on all voltage levels. Industry... Read More →

Wednesday September 16, 2026 10:30 - 12:10 CEST
Back Stage

Data + AI, Tutorial Sessions

13:10 CEST

P-SWAMP (power -Stability Wide Area Monitoring Protection) Open R&D for WAMS - Geir Harald Borse, Unicus+auticon & Hallvar Haugdal, SINTEF

Wednesday September 16, 2026 13:10 - 13:40 CEST

Crossover

Synchronous generation retires and renewable, converter-interfaced resources increase, modern power systems face new operational challenges. High penetration of HVDC connections, large volumes of solar and wind generation are reshaping the grid. System operators need to modernize their control rooms. p-SWAMP (Power Stability Wide Area Monitoring Protection) provides an open extensible Research & Development for future Wide Area Monitor System (WAMS). A cloud-native, open-source platform where new concepts can be integrated and demonstrated to users in a setting mimicking actual control rooms. Statnett, the Transmission System Operator (TSO) in Norway uses an open -source collaboration platform called Statnett RnDP, serves as an integration platform for p-SWAMP, RnDP contains a timeseries database to hold Phase Measurement Unit Data, for analysis and simulate Kafka streams needed. RnDP offers Jupyter, Grafana and more user interfaces, the user can control their own pods. All run on Kubernetes cluster with Kyverno for policy control, Rook/Ceph for storage and Linkerd for network observability (MtM). Harbour for hosting images allows to use Trivy for vulnerability scanning.

Speakers

Geir Harald Borse

CTO, Unicus+auticon

Geir has 30 years' experience in analysing, developing and managing IT Systems. For Unicus he works as an architect and project manager, delivering advanced analytics to customers worldwide. At Unicus we believe in the power of neurodiversity; all of our consultants are on the autism... Read More →

Hallvar Haugdal

Researcher, SINTEF

Hallvar Haugdal received the M.Sc. and Ph.D. degrees in electrical power engineering from the Norwegian University of Science and Technology, Trondheim, Norway, in 2016 and 2022, and is currently working as a researcher at SINTEF. His research interests include power system dynamics... Read More →

Wednesday September 16, 2026 13:10 - 13:40 CEST
Crossover

Data + AI, Session Presentation

13:10 CEST

Build With OpenGridFM: Synthetic Grid Data and Graph Neural Solvers in Practice - Alban Puech, IBM Research - Zurich

Wednesday September 16, 2026 13:10 - 14:50 CEST

Back Stage

This hands-on tutorial introduces our end-to-end framework released through the OpenGridFM project, enabling the development and deployment of GridFM models for steady-state grid analysis.
Participants will work with notebooks to generate synthetic but realistic power-flow and optimal-power-flow datasets using gridfm-datakit, including load variation, generator-dispatch variation, topology perturbations, and configurable grid cases. They will then use gridfm-graphkit to train and evaluate GENCO, a unified graph neural solver, in a low-code environment and compare its performance against classical solvers. For advanced participants, the tutorial will also explain how to implement, integrate, and benchmark custom model architectures using the framework and the provided benchmarking datasets.
The tutorial is designed for power-system practitioners, researchers, and developers who want to contribute to OpenGridFM or apply its tools in their own workflows. No prior experience with the project is required; familiarity with Python and basic power-system concepts is helpful.

Speakers

Alban Puech

PhD Researcher, IBM Research

Wednesday September 16, 2026 13:10 - 14:50 CEST
Back Stage

Data + AI, Tutorial Sessions

13:45 CEST

OpenEnergyTwin: Building Open, Interoperable Digital Twin Infrastructure for DSO Grid Operations - Jürgen Meister, OFFIS – Institute for Information Technology

Wednesday September 16, 2026 13:45 - 14:15 CEST

Crossover

Distribution system operators (DSOs) must manage increasingly complex grids with renewable generation, electrification, sector coupling, and active assets, especially at the low voltage level. Today’s grid control systems, however, are often monolithic, proprietary, and hard to extend, limiting interoperability and innovation. OpenEnergyTwin addresses this issue as an open source reference implementation for modular grid control systems. It provides a modular, event-driven digital twin infrastructure, capable of integrating all grid levels of a DSO, thereby creating a runtime environment for next-generation grid control services, including AI-based assistance and automation. The platform connects operational technology to a CIM-based digital twin core through flexible protocol adapters for topology, measurements, and state assessment, and exposes standardized interfaces for HMIs, alerting, forecasting, and control applications. Using publish-subscribe communication and CIM/JSON-LD, OpenEnergyTwin enables event-driven, standardized data exchange across all services. This talk presents key results of the research project, in which the OpenEnergyTwin platform has been developed.

Speakers

Jürgen Meister

Director R+D Division Energy, OFFIS – Institute for Information Technology

Dr. Jürgen Meister earned his doctorate in software product lines and has worked in the energy sector since 2006. He started out as a software architect and team lead, developing software products for offshore wind farms and virtual power plants at BTC AG. He now manages the Energy... Read More →

Wednesday September 16, 2026 13:45 - 14:15 CEST
Crossover

Data + AI, Session Presentation

14:05 CEST

Mastering the Grid: How MCP & AI Make Power System Simulations Effortless - Jérôme Picault, RTE (Réseau de Transport d'Electricité)

Wednesday September 16, 2026 14:05 - 14:50 CEST

Elektro Stage

Executing grid modelling and simulations like load flows, N-1 analyses, or sensitivity studies typically demands deep tooling expertise or custom scripting. What if grid engineers could drive these workflows directly in natural language - without sacrificing rigor or control?

pypowsybl-mcp demonstrates an open-source Model Context Protocol (MCP) server that exposes PowSyBl as AI-callable tools, callable by any conversational UI or AI agent to perform grid modelling simulations.

Our demo showcases a comprehensive TSO workflow driven entirely by natural-language prompts. Attendees will watch our AI agent dynamically orchestrate complex tool calls to execute:
1. Stress assessment: "Run an AC load flow; show voltage violations"
2. N-1 security: "Run N-1 on 400 kV lines; identify insecure contingencies"
3. Sensitivity: "Rank generators by impact on overload mitigation"
4. Remedial action: "Re-dispatch and re-run N-1"
5. Reproducibility: "Generate a Python script to reproduce this session"
Results come from pypowsybl (accurate, reproducible, hallucination-free results), while the LLM handles orchestration only and adaptation of results to the expertise of the user.

Speakers

Jérôme Picault

Senior AI Engineer, RTE (Réseau de Transport d'Electricité)

Jérôme Picault is a Senior AI R&D Engineer at the French TSO RTE, where he works on NLP and generative AI for power systems. He previously led technical work on grid simulation tools. Before RTE, he held senior AI research roles at Alcatel-Lucent Bell Labs and Motorola Labs, contributing... Read More →

Wednesday September 16, 2026 14:05 - 14:50 CEST
Elektro Stage

Data + AI, Demo Sessions

14:20 CEST

DT4Energy: Open AI-Driven Digital Twins for Energy Systems - DT4EC Use Case - Ferdinando Bosco, Engineering Ingegneria Informatica Spa & Vincenzo Croce, Engineering

Wednesday September 16, 2026 14:20 - 14:50 CEST

Crossover

The increasing complexity of energy systems calls for new approaches to design, develop, and operate secure and interoperable Digital Twins across heterogeneous environments.
Within the IPCEI-CIS AVANT project, DT4ENERGY is developed as an open platform enabling the creation of Digital Twins for energy systems, supporting real-time monitoring, simulation, and data-driven services. It provides a modular and extensible foundation for integrating distributed data, models, and applications, while ensuring interoperability and enabling the scalable deployment of AI capabilities.
In this session we present DT4EC, a real-world implementation for Energy Communities, demonstrating how DT4ENERGY supports operational use cases. DT4EC integrates Machine Learning models for day-ahead production and consumption prediction, as well as self-consumption optimization, combined with Generative AI services for KPI analysis, explainability and decision support.
By sharing implementation insights, this session shows how open Digital Twin platforms can move from architecture to operation, enabling secure, interoperable, and AI-driven energy applications, with DT4EC as a concrete and validated example.

Speakers

Ferdinando Bosco

R&I Project Manager, Engineering Ingegneria Informatica

Ferdinando Bosco is a Project Manager at Engineering Group’s R&I Department, with over 10 years of experience in advanced IT solutions for the energy sector. He holds a degree in Computer Engineering from the University of Palermo and has contributed to several European projects... Read More →

Vincenzo croce

Mr, Engineering

Is an Engineer in Computer Science. Since February 2001, he worked as senior researcher in Engineering’s R&D laboratory.
Main focus of his research activities is in energy efficiency in district and local communities.
Since 2007 his main research interest includes efficiency... Read More →

Wednesday September 16, 2026 14:20 - 14:50 CEST
Crossover

Data + AI, Session Presentation

15:20 CEST

VAREN: Open Source LiDAR Analytics for Overhead Distribution Networks - Guillaume Houle, Hydro-Québec

Wednesday September 16, 2026 15:20 - 15:50 CEST

Seebühne

VAREN (Vegetation and Asset Recognition for Electrical Network) is an open source library from Hydro-Québec's research centre. It reads mobile LiDAR point clouds from overhead distribution networks and extracts information utilities can act on. The library includes four algorithms: a point cloud classifier for power network assets, an overhead span extractor, a mathematical reconstruction method for heavily obstructed power lines, and a vegetation encroachment detector. These address a common problem, namely that mobile LiDAR data is often incomplete or blocked by vegetation. VAREN aims to give utilities reusable foundation for LiDAR-based grid analytics to help map their assets and assess vegetation risk.

Speakers

Guillaume Houle

Researcher, Hydro-Québec

Guillaume Houle is a researcher at Hydro-Québec's research centre in Varennes, Québec, where he works on asset analytics and applied AI for power distribution networks. His work focuses on computer vision and LiDAR-based detection, mapping, and risk assessment of grid infrastructure... Read More →

Wednesday September 16, 2026 15:20 - 15:50 CEST
Seebühne

Data + AI

15:20 CEST

OpenSTEF 4 Tutorial: Build Forecasting Pipelines That Fit Your Use Case - Daan van Es & Lars Schilders, Alliander

Wednesday September 16, 2026 15:20 - 17:00 CEST

Back Stage

OpenSTEF 4 introduces a redesigned, modular architecture that makes it easier to build and adapt energy forecasting solutions to your specific context. Rather than prescribing a single way of to integrate OpenSTEF in your setup, version 4 gives users the flexibility to create forecasting pipelines that fit their data, workflows, and IT environment.

In this hands-on tutorial, participants will explore the new architecture and learn how to assemble forecasting workflows using OpenSTEF's modular building blocks. You'll discover how to customize data preparation and feature engineering, integrate your preferred tools, experiment with different modeling approaches, and adapt forecasting setups to your own use case.

The tutorial provides a practical introduction to the newly developed capabilities of OpenSTEF 4, including support for ensemble forecasting, benchmarking and backtesting through STEF BEAM, and integration of deep learning and foundation models. Participants will work through real examples and gain insight into how

OpenSTEF can support everything from experimentation to production-scale forecasting.

Who should attend?
Whether you are a researcher exploring new forecasting methods, a data scientist building operational models, an organization looking to scale forecasting capabilities, or whether you are already experienced with forecasting (potentially through using OpenSTEF 3), this session is for you.

Speakers

Lars Schilders

Data Science Software Engineer, Alliander

Hi, I am a data science software engineer at Alliander, where we are using OpenSTEF for energy load forecasting on the Dutch electricity grid. I am one of the top contributors to OpenSTEF and co-developed the newly released version 4.

Daan van Es

Chair, OpenSTEF Technical Steering Committee | Alliander, Alliander

Wednesday September 16, 2026 15:20 - 17:00 CEST
Back Stage

Data + AI, Tutorial Sessions

10:30 CEST

11:05 CEST

13:10 CEST

13:45 CEST

14:20 CEST

14:30 CEST

14:40 CEST

15:20 CEST

15:20 CEST

15:55 CEST

16:30 CEST

10:30 CEST

13:10 CEST

13:10 CEST

13:45 CEST

14:05 CEST

14:20 CEST

15:20 CEST

15:20 CEST

Get help with the event