EDGE AI PLATFORM FOR PREDICTIVE MAINTENANCE IN SMART CITIES INFRASTRUCTURE

Abstract

Smart cities rely on interconnected infrastructure systems—such as transportation networks, utilities, and public facilities—that require continuous maintenance to avoid failures and service disruption. Traditional maintenance approaches are reactive and inefficient, leading to high operational costs and downtime. This paper proposes an Edge AI–enabled predictive maintenance platform that processes sensor data in real time to forecast equipment degradation and detect anomalies at the edge. By leveraging lightweight AI models, edge–cloud collaboration, and multimodal sensor inputs, the system enhances responsiveness, reduces latency, and minimizes communication overhead. Experimental evaluation demonstrates high accuracy in fault prediction, improved equipment uptime, and substantial reduction in maintenance cost. The framework offers a scalable and intelligent solution for modern smart city infrastructure management.