Ai-Driven Smart Street Lighting and Urban Sustainability: The Dortmund Case

Abstract

This study examines the contribution of AI-driven smart street lighting to sustainable urban development by focusing on its role in improving energy efficiency, reducing carbon emissions, minimizing unnecessary illumination, and strengthening data-driven urban management. The study evaluates the environmental, functional, and technological performance of Dortmund’s smart street-lighting system in Germany. It applies a Litmap-based literature review and an analytical case-study model structured around three indicators: carbon-emission reduction, urban-use efficiency, and intelligent data-processing capability. The findings show that replacing conventional street lighting with smart wireless LED technology reduced annual electricity consumption by approximately 47%, equivalent to nearly 9.15 million kWh, and prevented an estimated 3,700–4,200 tons of CO₂-equivalent emissions each year. The system also achieved advanced data-processing performance through centralized monitoring, individual luminaire control, energy-consumption analysis, adaptive lighting schedules, and automated fault detection. In contrast, the average congestion level increased from 31.9% in 2024 to 33.3% in 2025, suggesting that the project did not produce a measurable improvement in citywide urban-use efficiency. The analytical model generated an overall score of 56.25 out of 100, reflecting a moderate urban impact. The results confirm that AI enabled smart street lighting can contribute to sustainable urban development when supported by real-time monitoring, adaptive control, wireless communication, and predictive maintenance. Nevertheless, more direct project-level indicators are needed to assess its effects on pedestrian mobility, cycling activity, nighttime safety, and public-space use with greater accuracy.