Mission Statement
Enhance power grid operations through AI-driven agents that augment human operator capabilities.
Description
Results stem from the AI4REALNET European project (https://ai4realnet.eu/), which aims to advance the operation of critical infrastructures through AI-based decision-support systems built on reinforcement learning and supervised learning. The project is structured around three core building blocks:
- A human–AI interface based on hypervision (interactiveAI), designed to provide operators with intuitive, enriched situational awareness and seamless interaction with AI-generated recommendations.
- Reinforcement learning agents enhanced with domain knowledge, capable of learning optimal operational strategies and adapting to evolving grid conditions while ensuring alignment with established engineering principles.
- Advanced alarm and advisory functions that quantify uncertainty and deliver explainable insights, enabling human decision-makers to understand the rationale behind AI suggestions and trust their outputs.
Originally conceived to deliver rapid, real-time advice to system operators, the AI4REALNET framework also incorporates forecasting capabilities, allowing it to anticipate future system states and propose preventative remedial actions such as topology reconfiguration, redispatch, or renewable curtailment.
AINETUS.pdf
Is this a new project or an existing one?
New project
Current lead(s)
INESC TEC, IRT SystemX, Politecnico di Milano, Fraunhofer IEE, University of Amsterdam
Sponsoring organization(s), along with any other key contributing individuals and/or organizations
RTE and INESC TEC and Linux Foundation Energy members
Detail any existing community infrastructure, including:
- Github/GitLab, or other location where the code is hosted
- Website and/or docs
- Communication channels ( such as Mailing lists, Slack, IRC )
- Social Media Accounts
Website: https://ai4realnet.eu/
Github: https://github.com/AI4REALNET
Only the following repositories will be considered:
https://github.com/AI4REALNET/T2.3_explainability_dashboard
https://github.com/AI4REALNET/InteractiveAI
https://github.com/AI4REALNET/InteractiveAI-API
https://github.com/AI4REALNET/grid2evaluate
https://github.com/AI4REALNET/T2.1_deep_expert
https://github.com/AI4REALNET/T2.1_graph_neural_solver
https://github.com/AI4REALNET/failure_prediction
https://github.com/AI4REALNET/distributed_rl
Are there any specific infrastructure needs or requests outside of what is provided normally by LF Energy ? If so please detail them.
No.
Why would this be a good candidate for inclusion in LF Energy?
It provides modular, open, and interoperable AI components that address core challenges in real-time grid operation. Its human-AI interface, reinforcement learning agents, and uncertainty-aware alarm functions complement existing LF Energy projects by adding an intelligence and decision-support layer, in particular: (a) it uses Grid2Op (https://lfenergy.org/projects/grid2op/) as a training and validation environment, (b) it uses OperatorFabric (https://opfab.github.io/) for notification management, and (c) it can be integrated in modular platforms such as SOGNO (https://lfenergy.org/projects/sogno/) for grid management. The project’s focus on explainability, operator trust, and integration with forecasting aligns closely with LF Energy’s mission to modernize power system operations through transparent and collaborative digital technologies.
How would this benefit from inclusion in LF Energy?
Create an open-source governance framework, larger industry visibility, and a community of TSOs, DSOs, vendors, and developers who could adopt, validate, and extend its functions. It will also accelrate the standardization of its AI components and compliance with the EU AI Act (and similar regulatory frameworks in other geographical locations). Moreover, the cooperation with complementary LF Energy projects, such as Grid2Op, OperatorFabric and SOGNO can increase the impact and real-world deployment.
Provide a statement on alignment with the mission in the LF Energy charter.
Aligns directly with the LF Energy charter by advancing open, collaborative, and interoperable digital technologies that strengthen the reliability, resilience, and sustainability of the energy sector. Its AI-based decision-support components enhance grid operations in a operator-centric manner. It supports LF Energy’s mission to accelerate the global energy transition through shared innovation in digital solutions and open-source solutions.
What specific need does this project address?
This project addresses the growing need for advanced, trustworthy decision-support tools that help grid operators manage increasing system complexity, high renewable penetration, and real-time operational uncertainty. It provides AI-based agents, predictive capabilities, and explainable recommendations that enable faster, more informed actions in critical infrastructure operations.
Describe how this project impacts the energy industry.
This project brings advanced AI-driven decision-support capabilities to grid operations, enabling operators to manage complexity, uncertainty, and renewable variability more effectively. By introducing explainable AI agents, predictive alarms, and proactive remedial action guidance, it improves reliability, efficiency, and situational awareness across power grids. Its methods accelerate digitalization, support safer real-time operations, and help utilities transition toward more automated (but human-centric), resilient, and sustainable energy systems.
Describe how this project intersects with other LF Energy projects/working groups/special interest groups.
(a) it uses Grid2Op (https://lfenergy.org/projects/grid2op/) as a training and validation environment; (b) it uses OperatorFabric (https://opfab.github.io/) for notification management; (c) it can be integrated in modular platforms such as SOGNO (https://lfenergy.org/projects/sogno/) for grid management.
Who are the potential benefactors of this project?
Transmission and distribution system operators; EMS/ADMS vendors; operators of other infrastructures (the AI4REALNET project that originated this result also developed AI-based decision systems for railway and air traffic management).
What other organizations in the world should be interested in this project?
Systems operators like TenneT, Energinet, Elia, E-ON, Enel, Areti.
Tecnology venders like GE Vernova, Schneider Electric, Hitachi.
Plan for growing in maturity if accepted within LF Energy
If accepted into LF Energy, the project would follow a clear maturity growth plan by first consolidating its core AI components into modular, well-documented open-source packages. This work will be financially supported by the AI4REALNET project until March 2027.
Next, it would expand community participation through collaboration with TSOs, DSOs, vendors, and researchers to validate the tools in real operational contexts. This will be supported by additional Horizon Europe funding, and in-kind contributions from the open-source community.
Integration paths with existing LF Energy projects would be developed to enhance interoperability. Over time, the project would establish governance practices, testing frameworks, benchmarking datasets, and deployment guidelines, ensuring sustained evolution, industry adoption, and long-term technical robustness.
Project license
Mozilla Public License, version 2.0
Is the project's code available now? If so provide a link to the code location.
https://github.com/AI4REALNET/T2.3_explainability_dashboard
https://github.com/AI4REALNET/InteractiveAI
https://github.com/AI4REALNET/InteractiveAI-API
https://github.com/AI4REALNET/grid2evaluate
https://github.com/AI4REALNET/T2.1_deep_expert
https://github.com/AI4REALNET/T2.1_graph_neural_solver
https://github.com/AI4REALNET/failure_prediction
https://github.com/AI4REALNET/distributed_rl
Does this project have ongoing public (or private) technical meetings?
So far no, but the AI4REALNET project will run until March 2027 with public and private technical meetings.
Does this project's community venues have a code of conduct? If so, please provide a link to it?
This is the code of conduct from AI4REALNET repository and that we can adopt here: https://github.com/AI4REALNET/.github/blob/main/code-of-conduct.md
Describe the project's leadership team and decision-making process.
The governance structure is still being formalized. At this stage, the project is led by INESC TEC with active contributions from IRT SystemX, Politecnico di Milano, Fraunhofer IEE, and the University of Amsterdam.
Does this project have public governance (more than just one organization)?
While the governance model is still evolving, the project already benefits from a multi-institutional structure. It is led by INESC TEC with contributions from IRT SystemX, Politecnico di Milano, Fraunhofer IEE, and the University of Amsterdam, ensuring that decision-making and development are supported by multiple independent organizations.
Does this project have a development schedule and/or release schedule?
We have new releases foressen for March 2026, September 2026 and March 2027.
Does this project have dependencies on other open source projects? Which ones?
No. But the training and validation can be done using Grid2Op from LF Energy.
Describe the project's documentation.
The project’s documentation is currently in an early stage and primarily consists of technical reports, deliverables, and research publications produced within the AI4REALNET consortium. These documents describe the system architecture, AI methods, evaluation results, and demonstration scenarios. As the project matures and transitions toward an open-source environment, the documentation will be expanded to include developer guides, API references, installation instructions, and user-focused materials to support broader adoption.
Describe any trademarks associated with the project.
There are currently no known trademarks associated with this project. All components developed so far have been produced under the AI4REALNET consortium without any registered trademarks. If the project is onboarded into LF Energy, trademark considerations can be reviewed and formalized as needed.
Do you have a project roadmap? If so please attach or provide a link.
The only roadmap so far is the one from the AI4REALNET project: https://ai4realnet.eu/project/
Are this project's roadmap and meeting minutes public posted?
Yes, it is available in the AI4REALNET website.
Does this project have a legal entity and/or registered trademarks?
No.
Has this project been announced or promoted in any press?
The AI4REALNET project yes. Some examples:
https://ai4realnet.eu/media-corner/
https://ai4realnet.eu/news/
https://ai4realnet.eu/events/
Does this project compete with other open source projects or commercial products?
The project does not directly compete with existing open-source projects or commercial products. While some commercial tools offer forecasting or decision-support functions, this project is mainly focused on explainable reinforcement-learning agents and human-AI interfaces/cooperation.
Mission Statement
Enhance power grid operations through AI-driven agents that augment human operator capabilities.
Description
Results stem from the AI4REALNET European project (https://ai4realnet.eu/), which aims to advance the operation of critical infrastructures through AI-based decision-support systems built on reinforcement learning and supervised learning. The project is structured around three core building blocks:
Originally conceived to deliver rapid, real-time advice to system operators, the AI4REALNET framework also incorporates forecasting capabilities, allowing it to anticipate future system states and propose preventative remedial actions such as topology reconfiguration, redispatch, or renewable curtailment.
AINETUS.pdf
Is this a new project or an existing one?
New project
Current lead(s)
INESC TEC, IRT SystemX, Politecnico di Milano, Fraunhofer IEE, University of Amsterdam
Sponsoring organization(s), along with any other key contributing individuals and/or organizations
RTE and INESC TEC and Linux Foundation Energy members
Detail any existing community infrastructure, including:
Website: https://ai4realnet.eu/
Github: https://github.com/AI4REALNET
Only the following repositories will be considered:
https://github.com/AI4REALNET/T2.3_explainability_dashboard
https://github.com/AI4REALNET/InteractiveAI
https://github.com/AI4REALNET/InteractiveAI-API
https://github.com/AI4REALNET/grid2evaluate
https://github.com/AI4REALNET/T2.1_deep_expert
https://github.com/AI4REALNET/T2.1_graph_neural_solver
https://github.com/AI4REALNET/failure_prediction
https://github.com/AI4REALNET/distributed_rl
Are there any specific infrastructure needs or requests outside of what is provided normally by LF Energy ? If so please detail them.
No.
Why would this be a good candidate for inclusion in LF Energy?
It provides modular, open, and interoperable AI components that address core challenges in real-time grid operation. Its human-AI interface, reinforcement learning agents, and uncertainty-aware alarm functions complement existing LF Energy projects by adding an intelligence and decision-support layer, in particular: (a) it uses Grid2Op (https://lfenergy.org/projects/grid2op/) as a training and validation environment, (b) it uses OperatorFabric (https://opfab.github.io/) for notification management, and (c) it can be integrated in modular platforms such as SOGNO (https://lfenergy.org/projects/sogno/) for grid management. The project’s focus on explainability, operator trust, and integration with forecasting aligns closely with LF Energy’s mission to modernize power system operations through transparent and collaborative digital technologies.
How would this benefit from inclusion in LF Energy?
Create an open-source governance framework, larger industry visibility, and a community of TSOs, DSOs, vendors, and developers who could adopt, validate, and extend its functions. It will also accelrate the standardization of its AI components and compliance with the EU AI Act (and similar regulatory frameworks in other geographical locations). Moreover, the cooperation with complementary LF Energy projects, such as Grid2Op, OperatorFabric and SOGNO can increase the impact and real-world deployment.
Provide a statement on alignment with the mission in the LF Energy charter.
Aligns directly with the LF Energy charter by advancing open, collaborative, and interoperable digital technologies that strengthen the reliability, resilience, and sustainability of the energy sector. Its AI-based decision-support components enhance grid operations in a operator-centric manner. It supports LF Energy’s mission to accelerate the global energy transition through shared innovation in digital solutions and open-source solutions.
What specific need does this project address?
This project addresses the growing need for advanced, trustworthy decision-support tools that help grid operators manage increasing system complexity, high renewable penetration, and real-time operational uncertainty. It provides AI-based agents, predictive capabilities, and explainable recommendations that enable faster, more informed actions in critical infrastructure operations.
Describe how this project impacts the energy industry.
This project brings advanced AI-driven decision-support capabilities to grid operations, enabling operators to manage complexity, uncertainty, and renewable variability more effectively. By introducing explainable AI agents, predictive alarms, and proactive remedial action guidance, it improves reliability, efficiency, and situational awareness across power grids. Its methods accelerate digitalization, support safer real-time operations, and help utilities transition toward more automated (but human-centric), resilient, and sustainable energy systems.
Describe how this project intersects with other LF Energy projects/working groups/special interest groups.
(a) it uses Grid2Op (https://lfenergy.org/projects/grid2op/) as a training and validation environment; (b) it uses OperatorFabric (https://opfab.github.io/) for notification management; (c) it can be integrated in modular platforms such as SOGNO (https://lfenergy.org/projects/sogno/) for grid management.
Who are the potential benefactors of this project?
Transmission and distribution system operators; EMS/ADMS vendors; operators of other infrastructures (the AI4REALNET project that originated this result also developed AI-based decision systems for railway and air traffic management).
What other organizations in the world should be interested in this project?
Systems operators like TenneT, Energinet, Elia, E-ON, Enel, Areti.
Tecnology venders like GE Vernova, Schneider Electric, Hitachi.
Plan for growing in maturity if accepted within LF Energy
If accepted into LF Energy, the project would follow a clear maturity growth plan by first consolidating its core AI components into modular, well-documented open-source packages. This work will be financially supported by the AI4REALNET project until March 2027.
Next, it would expand community participation through collaboration with TSOs, DSOs, vendors, and researchers to validate the tools in real operational contexts. This will be supported by additional Horizon Europe funding, and in-kind contributions from the open-source community.
Integration paths with existing LF Energy projects would be developed to enhance interoperability. Over time, the project would establish governance practices, testing frameworks, benchmarking datasets, and deployment guidelines, ensuring sustained evolution, industry adoption, and long-term technical robustness.
Project license
Mozilla Public License, version 2.0
Is the project's code available now? If so provide a link to the code location.
https://github.com/AI4REALNET/T2.3_explainability_dashboard
https://github.com/AI4REALNET/InteractiveAI
https://github.com/AI4REALNET/InteractiveAI-API
https://github.com/AI4REALNET/grid2evaluate
https://github.com/AI4REALNET/T2.1_deep_expert
https://github.com/AI4REALNET/T2.1_graph_neural_solver
https://github.com/AI4REALNET/failure_prediction
https://github.com/AI4REALNET/distributed_rl
Does this project have ongoing public (or private) technical meetings?
So far no, but the AI4REALNET project will run until March 2027 with public and private technical meetings.
Does this project's community venues have a code of conduct? If so, please provide a link to it?
This is the code of conduct from AI4REALNET repository and that we can adopt here: https://github.com/AI4REALNET/.github/blob/main/code-of-conduct.md
Describe the project's leadership team and decision-making process.
The governance structure is still being formalized. At this stage, the project is led by INESC TEC with active contributions from IRT SystemX, Politecnico di Milano, Fraunhofer IEE, and the University of Amsterdam.
Does this project have public governance (more than just one organization)?
While the governance model is still evolving, the project already benefits from a multi-institutional structure. It is led by INESC TEC with contributions from IRT SystemX, Politecnico di Milano, Fraunhofer IEE, and the University of Amsterdam, ensuring that decision-making and development are supported by multiple independent organizations.
Does this project have a development schedule and/or release schedule?
We have new releases foressen for March 2026, September 2026 and March 2027.
Does this project have dependencies on other open source projects? Which ones?
No. But the training and validation can be done using Grid2Op from LF Energy.
Describe the project's documentation.
The project’s documentation is currently in an early stage and primarily consists of technical reports, deliverables, and research publications produced within the AI4REALNET consortium. These documents describe the system architecture, AI methods, evaluation results, and demonstration scenarios. As the project matures and transitions toward an open-source environment, the documentation will be expanded to include developer guides, API references, installation instructions, and user-focused materials to support broader adoption.
Describe any trademarks associated with the project.
There are currently no known trademarks associated with this project. All components developed so far have been produced under the AI4REALNET consortium without any registered trademarks. If the project is onboarded into LF Energy, trademark considerations can be reviewed and formalized as needed.
Do you have a project roadmap? If so please attach or provide a link.
The only roadmap so far is the one from the AI4REALNET project: https://ai4realnet.eu/project/
Are this project's roadmap and meeting minutes public posted?
Yes, it is available in the AI4REALNET website.
Does this project have a legal entity and/or registered trademarks?
No.
Has this project been announced or promoted in any press?
The AI4REALNET project yes. Some examples:
https://ai4realnet.eu/media-corner/
https://ai4realnet.eu/news/
https://ai4realnet.eu/events/
Does this project compete with other open source projects or commercial products?
The project does not directly compete with existing open-source projects or commercial products. While some commercial tools offer forecasting or decision-support functions, this project is mainly focused on explainable reinforcement-learning agents and human-AI interfaces/cooperation.