AI-driven demand-side management with reliability and carbon pricing integration for sustainable power systems in Qatar

Urban energy and infrastructure systems are facing growing pressure due to climate variability, rapid urbanization, increasing energy demand, and the need for more sustainable city operations. Conventional monitoring and control approaches are often unable to respond effectively to rapidly changing environmental and operational conditions, particularly in complex urban settings. This paper presents an AI-enabled urban Digital Twin framework designed to improve the management and resilience of smart city infrastructure through real-time data integration and intelligent decision support. The proposed framework combines environmental sensing, air-quality monitoring, mobility information, and adaptive AI models to support dynamic system optimization and operational awareness. To evaluate the framework, simulation studies were conducted using datasets representative of arid urban environments. The results indicate noticeable improvements in energy performance, operational resilience, and system responsiveness during periods of high congestion and extreme climate conditions compared with conventional rule-based approaches. The study demonstrates the potential of AI-driven Digital Twins to support more resilient, efficient, and sustainable urban infrastructure systems.