en.Wedoany.com Reported - The AI4REALNET project, led by researcher Ricardo Bessa from INESC TEC in Portugal, has developed an AI component named AINETUS that enhances decision-making in power grid operations through an intuitive interface and visualization technologies, enabling operators to instantly assess system conditions and AI recommendations.

AINETUS is regarded as a new paradigm for AI-assisted operations in safety-critical infrastructure. The component can be integrated as an open-source solution into LF Energy, aiming to develop transparent and scalable AI technologies for power grid operational use cases, promoting the adoption of AI-based assistants in industry operations. The component will also ensure its accessibility and long-term maintenance after the official conclusion of the AI4REALNET project in March 2027. The AI4REALNET project is dedicated to developing AI-based solutions, primarily targeting three critical systems: power grids, railways, and air traffic management. These systems are modeled by simulatable networks, traditionally operated by humans, but AI systems can complement and enhance human capabilities. Core elements of the project include supervised learning and reinforcement learning algorithms, human-machine collaborative decision-making for AI and human co-learning, and autonomous AI systems that rely on human supervision.

The foundation of AINETUS is built on two power grid use cases: one that supervises transmission networks using SCADA data and energy management system tools to identify and manage congestion; and another that transfers AI assistants from simulation to actual operations through two pathways, responding to real-world conditions while alerting operators when data limitations hinder full autonomy. In collaboration with LF Energy, selected project outcomes will be embedded into the established open-source ecosystem and managed under the LF Energy framework, ensuring transparent development, community governance, and long-term maintenance. The open-source initiative will integrate key technology modules developed by AI4REALNET, including reinforcement learning-based operational decision support agents, high-performance power flow solvers for real-time analysis, uncertainty quantification modules for risk-aware operations, and human-machine interaction capabilities based on the hypervision concept. By hosting AINETUS within LF Energy, the platform moves away from single-organization ownership, embedding itself into an ecosystem that supports open development, collaborative innovation, and technology transfer among academia, industry, and infrastructure operators. In addition to funding from Horizon Europe, AI4REALNET has also received financial support from the Swiss government.

This article is compiled by Wedoany. All AI citations must indicate the source as "Wedoany". If there is any infringement or other issues, please notify us promptly, and we will modify or delete it accordingly. Email: news@wedoany.com