OPTIMIZING REAL TIME IOT PROCESSING WITH HYBRID EDGE CLOUD ARCHITECTURE FOR ENHANCED LATENCY AND ENERGY EFFICIENCY

The proposed hybrid edge-cloud architecture system aims to maximize efficiency in dynamically processing real-time data for Internet of Things (IoT) powered applications. By strategically placing a fog layer, the system seeks to balance the load, ensuring efficient data processing while minimizing latency, optimizing energy consumption, and enhancing scalability. This is achieved through a Dynamic Task Offloading (DTA) algorithm that intelligently assigns tasks to either the edge or cloud layer. Experiments using a synthetic smart city traffic dataset demonstrate that the hybrid model can reduce latency by 70% and save 55% in energy consumption compared to a cloud-only model, while achieving a task offloading efficiency of 92%. The architecture supports high scalability, resource utilization, and timely decision-making, significantly reducing processing latencies and energy usage for IoT applications. The study highlights the limitations of cloud-only systems, including high latency and scalability issues, and addresses these by proposing a hybrid solution that enhances real-time IoT data processing capabilities in dynamic environments.