(EERO) Energy-Efficient Fog Resource Optimization Model for Scientific Workflow Applications

Abstract

Network congestion and increased latency may result from the speedy development of intelligent services and Internet of Things devices contacting cloud data centers. Fog computing meets the latency and privacy needs of operations running at the network edge by focusing on widely linked heterogeneous devices. The intricate and stringent Quality of Service limitations makes allocating resources in this paradigm challenging. We investigate workflow scheduling in fog-cloud systems to give an energy-efficient task plan within tolerable application completion times. The Energy Efficient optimization mode is presented. This paper investigated the outcomes of algorithms created by the community to address issues with energy management. The objective is to provide energy-efficient algorithms for a particular problem that minimize service compromise while reducing energy usage. The algorithms must attain a provably good performance, a crucial requirement. The goal is to find an efficient Pareto front by employing a Bayesian method with a maximum likelihood procedure for processing the fog node tasks while improving task scheduling by integrating heuristic methodologies such as PEFT and the Multi-objective genetic algorithm.