An AI-Driven Situational Awareness Architecture for Citywide Energy Governance with Risk-Prioritized Multi-Drone Verification

Abstract

Increasing urban energy complexity requires governance architectures capable of integrating predictive intelligence, distributed sensing, physical verification, and accountable response at city scale. Conventional energy monitoring remains reactive and fragmented across buildings, electric vehicle charging hubs, public lighting, renewable assets, and distribution infrastructure. The study follows a Design Science Research method and evaluates the artifact through analytical scenario modelling for a representative 100 km2 urban area with approximately 4,500 monitored nodes. The validation indicates that selective drone activation avoids full-city inspection and requires only 3-12 drones across low, medium, and high disturbance scenarios. Drone-assisted verification reduces false anomaly confirmations from 16% to 6%, improves the Situational Awareness Index from 0.79 to 0.92, and reduces response latency from 50 to 19 minutes. The paper contributes a governance aligned architecture, a compact risk-verification model, and an accountable validation framing for AI-enhanced urban energy governance.