AI-enhanced design strategies for energy efficiency are opening new options for urban adaptation across diverse environments. Paris, Dijon, and Nice illustrate distinct approaches shaped by climate, governance structures, and policy frameworks. Their experiences show how cities can tailor AI applications in energy management to local constraints and opportunities. This paper identifies the institutional, technical, and social mechanisms that enable successful integration of AI solutions into urban energy systems, and highlights key considerations for adapting them elsewhere.
A comparative case study methodology underpins the analysis, drawing on official French reports, municipal open data, and academic and technical literature. The three cities were selected to represent different climatic zones and governance models. The study focuses on AI deployment in energy management at building and district scales, and on the roles of policy and stakeholder engagement in enabling or constraining experimentation.
The results show that Paris uses AI platforms to manage building energy use, optimize infrastructure, and support smart grid operation in a metropolitan context. Dijon’s centralized operations system coordinates multiple infrastructures, achieving significant energy savings, particularly in public lighting, through real-time monitoring, cross-domain data integration, and predictive control. Nice deploys AI to manage neighborhood-scale smart grids and integrate renewable energy under Mediterranean conditions, with particular emphasis on peak-load management and resilience. These cases reveal how performance is shaped by data governance, institutional capacity, and degrees of citizen and stakeholder participation.
The analysis identifies opportunities for adapting AI-based urban energy applications, while underscoring persistent challenges: data standardization, algorithmic transparency, interoperability across sectors, policy alignment, social acceptance, and privacy and security concerns. Addressing these issues is crucial to align technical innovation with institutional and societal conditions. The paper offers guidance for cities seeking to design and govern AI-based energy solutions that are both effective and context-sensitive.
