Optimizing workload distribution in Fog-Cloud ecosystem: A JAYA based meta-heuristic for energy-efficient applications

Fog-integrated Cloud has emerged as a novel computing paradigm that brings Cloud computing services to the network's edge in real -time, though with limited capabilities. Despite its advantages, there are several challenges including workload distribution, energy consumption, computational time, and network latency, that require attention. The workload of IoT applications can be distributed over the Fog or Cloud devices based on their priority, deadline, and latency restrictions. In this work, we introduce a novel population-based metaheuristic called MAYA, a modified variant of the JAYA algorithm, to address the Energy-Efficient Workload Distribution of Sensors (EEWDS) in the Fog-Cloud ecosystem. The workload distribution of IoT applications depends on several factors such as request deadlines, the energy consumed during transmission, and needed computation. The performance of the proposed model for the energy consumption, computation time, CO2 emission, fairness index, and the convergence rate, is evaluated through simulation experiments. The results are compared in two scenarios: one concerning to methodology, where the performance is compared with JAYA, Genetic Algorithm (GA), Particle Swarm Optimization (PSO), and Ant Colony Optimization (ACO) techniques. The other scenario is based on the environment, where we examine Cloud-only, Fog-only, and Fog-Cloud integrated environments. Compared to JAYA, GA, PSO and ACO, the proposed MAYA technique demonstrates significant improvements, including reduction in energy consumption by 34.76%, 88.92%, 85.36% and 93.84%; decrease in computation time by 37.64%, 85.07%, 87.22%, and 91.08%; decrease in CO2 emissions by 23.46%, 76.24%, 97.17%, and 99.02%; and increase in fairness index by 9.62%, 3.72%, 16.90%, and 15.26% respectively.