THE ROLE OF EDGE COMPUTING IN ENABLING REAL-TIME DATA PROCESSING IN AUTONOMOUS SYSTEMS FOR SMART CITIES

Abstract

The rapid growth of smart cities and autonomous systems has intensified the demand for low-latency, reliable, and scalable computing infrastructures capable of processing large volumes of real-time data. This study investigates the effectiveness of edge computing in supporting autonomous operations within smart city environments through an experimental, mixed-method evaluation framework. A distributed edge-based architecture was implemented to process sensor and vehicular data locally, while centralized cloud resources were reserved for non-time-critical analytics. Quantitative results reveal significant performance improvements, including reduced end-to-end latency, higher throughput efficiency, lower packet loss rates, and decreased energy consumption compared to cloud-centric approaches. Qualitative analysis further demonstrates enhanced system resilience, improved fault tolerance, and stronger privacy preservation due to localized data processing. The integration of edge-based artificial intelligence enabled faster and more accurate decision-making for autonomous vehicles and intelligent traffic management systems, even under high network load and dynamic conditions. Overall, the results confirm that edge computing substantially enhances the operational efficiency, responsiveness, and scalability of autonomous smart city systems. The findings provide strong empirical evidence supporting the adoption of edge-enabled architectures as a core component of future smart city infrastructures.