Fog Computing Integration for Real-Time Iot Data Processing

Abstract

The rapid expansion of the Internet of Things (IoT) has created massive streams of real-time data that require processing near their sources to ensure timely and efficient responses. Traditional cloud-centric architectures struggle to meet these demands, leading to significant latency, energy overhead, and security vulnerabilities. Fog computing, by extending computational and storage capabilities toward the network edge, offers a promising solution to these limitations. This study systematically analyses recent advancements in fog-enabled IoT data processing, consolidating performance results from diverse approaches into a unified comparative framework. The proposed model balances latency, energy consumption, and operational costs, demonstrating performance gains of up to 95% in latency reduction, 65% in energy savings, and notable improvements in system security. Through detailed comparative analysis and graphical evaluation, the findings reveal that multi-layer fog architectures, when combined with adaptive scheduling and energy-aware service placement, can significantly enhance quality of service (QoS) while optimising resource utilisation. These insights provide practical guidance for designing sustainable, secure, and high-performance IoT ecosystems.