<![CDATA[The rapid proliferation of Internet of Things (IoT) devices and real-time monitoring applications has intensified the demand for low-latency, reliable, and scalable data processing in distributed systems. Conventional cloud-centric architectures, although flexible and scalable, often suffer from high end-to-end latency, bandwidth congestion, and dependency on continuous network connectivity, making them less suitable for latency-sensitive monitoring applications. This study aims to evaluate the effectiveness of an edge computing–based architecture in reducing latency and improving overall system performance in real-time distributed monitoring systems. A multi-layer architecture consisting of edge, fog, and cloud layers is proposed, where data processing tasks are partially offloaded to edge nodes located closer to IoT sensors. The proposed system integrates load balancing using the least connection algorithm and data caching mechanisms to optimize request handling and minimize network overhead. The architecture is implemented and evaluated in a real-world monitoring scenario involving 100 IoT sensors distributed across multiple locations. Experimental results demonstrate that the proposed edge-based approach significantly outperforms a conventional cloud-only architecture. The average end-to-end latency is reduced by 73.4%, from 245 ms to 65 ms, while system throughput increases by 58.3%. In addition, packet loss is reduced from 3.2% to 0.4%, and bandwidth usage to the cloud is decreased by approximately 68% due to local processing and data aggregation at the edge layer. These findings indicate that integrating edge computing with load balancing and caching mechanisms can effectively enhance the performance, reliability, and scalability of real-time distributed monitoring systems. The study concludes that edge computing provides a practical and efficient solution for meeting strict latency requirements in modern IoT-based monitoring applications.]]>
Copyrights © 2026
