The scope of AI4REALNET covers the perspective of AI-based solutions addressing critical systems (electricity, railway, and air traffic management) modelled by networks that can be simulated, and are traditionally operated by humans, and where AI systems complement and augment human abilities. It has two main strategic goals: 1) to develop the next generation of decision-making methods powered by supervised and reinforcement learning, which aim at trustworthiness in AI-assisted human control with augmented cognition, hybrid human-AI co-learning and autonomous AI, with the resilience, safety, and security of critical infrastructures as core requirements, and 2) to boost the development and validation of novel AI algorithms, by the consortium and AI community, through existing open-source digital environments capable of emulating realistic scenarios of physical systems operation and human decision-making. The core elements are: a) AI algorithms mainly composed by supervised and reinforcement learning, unifying the benefits of existing heuristics, physical modelling of these complex systems and learning methods, as well as, a set of complementary techniques to enhance transparency, safety, explainability and human acceptance; b) human-in-the-loop decision making for co-learning between AI and humans, considering integration of model uncertainty, human cognitive load and trust; c) autonomous AI systems relying on human supervision, embedded with human domain knowledge and safety rules. The AI4REALNET framework will be validated in 6 uses cases driven by industry requirements, across 3 network infrastructures with common properties. The use cases are focused on critical challenges and tasks of network operators, considering strategic long-term goals, such as decarbonisation, digitalisation, and resilience to disturbances, and are formulated in a unified sequential decision problem where many AI and non-AI algorithms can be applied and benchmarked.

Prompted by the need to comply with environmental and societal concerns, Electrical Power and Energy Systems are undergoing an unprecedented transformation, demanding urgent upgrades to make them more reliable, resilient and secure. Modernization of current grids will greatly reduce the frequency and duration of power blackouts, diminish the impact of disruptive events and restore service faster when outages occur, creating broad benefits to society and economy. eFORT approach will enable the further upgrading of the energy grid without affecting the security of supply and increasing their reliability and resiliency against extreme weather events, man-made hazards and equipment failures. eFORT addresses this complex challenge by gathering a consortium of 24 partners, from 10 EU countries, that provides the needed expertise. The project will put in place a set of solutions at the cyber and physical layers for detecting, preventing and mitigating vulnerabilities and threats. Among them, an interoperable Intelligent Platform will set a common foundation for grid characterization and vulnerability overseeing, as well as gather information from smart grid components and apply heavy-duty algorithms, whereas Asset Management developments will strengthen grid infrastructure robustness, which will be empowered by the addressed Digital Technologies. All these elements will be validated in relevant environments coming from 4 demo cases covering the whole grid value chain: (i) a transmission network (The Netherlands); (ii) a remote distribution grid (Italy); (iii) a digital substation in Ukraine; and (iv) a micro-grid in Spain. Moreover, eFORT relies on several horizontal actions aiming at empowering EPES players by establishing a common regulatory and standardisation framework, performing technical and cost-benefit analysis, and evaluating new related business models and replication potential, in the pathway towards a more sustainable energy system.

The current international situation makes the process of energy transition more critical for Europe than ever before. It is a key requirement to increase the penetration of renewables while aiming at making the infrastructure more resilient and cost-effective. In this context, digital twins (DT) build a key asset to facilitate all aspects of business and operational coordination for system operators and market parties. It is of fundamental importance to now start a process of agreement at European level so not to develop isolated instances but a federated ecosystem of DT solutions. Each operator should be able to make its own implementation decisions while preserving and supporting interoperability and exchange with the remaining ecosystem. Exactly this is the vision of the TwinEU consortium: enabling new technologies to foster an advanced concept of DT while determining the conditions for interoperability, data and model exchanges through standard interfaces and open APIs to external actors. The envisioned DT will build the kernel of European data exchange supported by interfaces to the Energy Data Space under development. Advanced modeling supported by AI tools and able to exploit High Performance Computing infrastructure will deliver an unprecedented capability to observe, test and activate a pan-European digital replica of the European energy infrastructure. In this process, reaching consensus is crucial: the consortium therefore gathers an unprecedented number of actors committed to achieving this common goal. The concepts developed by TwinEU span over 15 different European countries with a continuous coverage of the continental map. Demos will encompass key players at every level from transmission to distribution and market operators, while also testing the coordinated cross-area data exchange. The consortium also includes relevant industry players, research institutions and associations with a clear record in developing innovative solutions for Europe.