<![CDATA[The rapid expansion of Internet of Things (IoT) ecosystems has intensified the need for efficient real-time data processing, exposing limitations of cloud-centric architectures in handling latency-sensitive applications. Increasing data volumes, network congestion, and delayed response times have highlighted the necessity of decentralized computing approaches. This study aims to examine the effectiveness of edge computing in optimizing latency and system efficiency within IoT environments. A mixed-methods experimental and simulation-based design was employed, comparing edge-based, cloud-based, and hybrid architectures across multiple application scenarios. Performance metrics including latency, throughput, energy consumption, and bandwidth utilization were analyzed using statistical and comparative techniques. Findings indicate that edge computing significantly reduces latency and energy consumption, while hybrid architectures achieve optimal throughput and scalability. Bandwidth utilization emerges as a key mediating factor influencing system performance, with decentralized processing improving responsiveness under high network load conditions. The study concludes that edge computing provides a robust and adaptive solution for enhancing real-time data processing in IoT ecosystems, particularly when integrated with cloud systems through optimized task allocation strategies. Effective deployment requires context-aware design, efficient resource management, and alignment with application-specific requirements.]]>
