Research database

DIVERSE addresses critical challenges in modern power distribution networks as they transition to accommodate high shares of renewable energy sources (RES) and increasing electrification demands. The project develops an AI-powered framework to optimize power distribution networks, supporting robust RES integration while tackling key issues such as variability and grid reconfiguration. By combining advanced machine learning, deep learning, and adaptive grid technologies, DIVERSE introduces predictive analytics, near real-time optimization, and consumer-side flexibility to enhance grid efficiency and scalability. The project's objectives include: _Developing AI-driven forecasting and regulation strategies for RES integration _Enhancing operational flexibility and efficiency through adaptive control mechanisms _Ensuring grid resilience across different network configurations _Optimizing multi-energy system coordination DIVERSE's innovative approach incorporates resilience-focused design into distributed energy resource (DER) coordination, ensuring effective grid operation under dynamic scenarios. Through simulations on RTDS-based platforms, the project optimizes adaptive response strategies, enhancing long-term grid flexibility, reliability, and multi-energy integration. The consortium unites academic institutions, SMEs, and industry partners from six countries, fostering interdisciplinary collaboration among experts in AI, power systems, and energy management. This international, intersectoral, and interdisciplinary approach ensures that DIVERSE's outcomes are scalable and adaptable to diverse grid configurations across Europe and beyond. By addressing the urgent need for innovative solutions in power distribution networks, DIVERSE contributes significantly to the EU's energy transition goals, aligning with key agendas such as the European Green Deal and the Circular Economy Action Plan. The project's outcomes will enhance Europe's energy security, reduce reliance

• Andrea Mazza (Principal Investigator)
• Gianfranco Chicco (Component of the research team)
• Angela Russo (Component of the research team)