Reducing Transmission Latency and Optimizing Power Consumption in Fog Computing to Improve Performance in Fog-Cloud Computing

Abstract

The important problems of latency and power inefficiency in fog-cloud computing systems are discussed in this work. Driven by growing demand for real-time processing in Internet of Things (IoT) applications, these difficulties compromise the performance of distributed systems. This work aims to minimize transmission latency and power consumption so that seamless integration between fog and cloud computing layers may be attained, hence improving system performance. Emphasizing important issues such as resource allocation algorithms, energy-efficient task scheduling, and latency reduction approaches in fog computing, a thorough evaluation of the body of current research was undertaken. Though many fall short in achieving the dual goals of lowering latency and concurrently optimizing energy use, existing studies emphasize the possibilities of fog computing in bridging the gap between IoT devices and centralized cloud servers. The study also shows that while many techniques and frameworks have been suggested for individual optimization, there is a dearth of coherent approaches addressing both elements in concert. The results of this work emphasize the need to use hybrid optimization techniques based on dynamic workload allocation and energy-aware scheduling. While preserving power economy, advanced techniques using machine learning-based predictive models were shown to dramatically lower latency. The results imply that further studies should concentrate on creating scalable, adaptive systems able to balance sustainable energy practices with real-time performance requirements. By offering practical insights on optimizing fog- cloud architectures, therefore allowing better QoS (Quality of Service) and promoting the spread of IoT-based applications, this work adds to the increasing corpus of knowledge.