Efficient workflow scheduling in fog-cloud collaboration using a hybrid IPSO-GWO algorithm.

Area of Science:

• Computer Science
• Distributed Systems
• Artificial Intelligence

Background:

• Fog-cloud computing is crucial for system performance and cost efficiency.
• Task offloading and workflow scheduling are complex in heterogeneous fog-cloud environments.

Purpose of the Study:

• To introduce a novel hybrid optimization strategy for fog-cloud task offloading.
• To improve system performance and cost efficiency in fog-cloud environments.

Main Methods:

• A hybrid Improved Particle Swarm Optimization (IPSO) and Grey Wolf Optimization (GWO) algorithm was developed.
• The IPSO-GWO algorithm features a dynamically adapting inertia weight for balanced exploration and exploitation.
• Simulations were conducted using the FogWorkflowSim framework with real-world scientific workflows.

Main Results:

• The IPSO-GWO approach outperformed standard PSO, GWO, IPSO, and GSA in simulations.
• Significant average reductions were observed: 26.14% in makespan, 37.73% in energy consumption, and 12.52% in total cost.
• Analysis of Variance (ANOVA) confirmed the statistical significance of the results.

Conclusions:

• The proposed IPSO-GWO algorithm offers superior performance for task offloading and workflow scheduling in fog-cloud systems.
• This research contributes to understanding workflow optimization dynamics in distributed computing.
• The findings pave the way for more intelligent and adaptive task scheduling in future computing paradigms.