Multifractal and AI Approaches for Coherent and Resilient Energy Networks in Urban Territories (Fracnet-city )

Urban areas need to integrate renewable energy, use land efficiently and strengthen resilience to extreme weather. Fracnet-city combines multifractal analysis and AI to optimise urban networks. Case studies in France and Switzerland explore how this approach can support more efficient, renewable and resilient urban systems.

Key data

Description

Urban areas increasingly face the challenge of integrating renewable energy sources while simultaneously managing the demands of high population density, land spare and resilience to extreme climate events. Traditional urban planning methods often lack the capacity to fully address the intricate, multiscale interconnections within urban systems, such as those between built-up areas, district energy networks, and the impacts of extreme weather events on energy infrastructure.

This project Fracnet-city aims to introduce a novel, multiscale framework that leverages multifractal analysis and Artificial Intelligence (AI) to tackle these challenges. The primary objective is to develop a multifractal-inspired approach for urban planning of physical networks that utilizes AI-driven geospatial analysis and simulation.

By applying multifractal analyses, the project will examine and optimize urban layouts, energy distribution networks, in a way that promotes spare land use, renewable energy integration, and increases resilience to extreme weather events. The framework will also include adaptive tools capable of responses to urban dynamics, such as shifts in energy demand, population growth, and climatic changes.

By a collaborative effort between research teams in France and Switzerland, the project brings together expertise in multifractal networks, photovoltaic integration, urban planning, and AI. Through case studies in selected urban areas in France and Switzerland, the project aims to demonstrate the practical application of its framework, showing a more coherent and efficient use of urban space, increased renewable energy integration and improved resilience to extreme climate change.

The expected outcomes are an adaptive planning model of urban networks grounded in multifractal and AI principles, comprehensive AI-driven tools for urban planning, and actionable insights for urban territories facing similar challenges globally.