The application of hybrid spider monkey optimization and fuzzy self-defense algorithms for multi-objective scientific workflow scheduling in cloud computing

Abstract

Scheduling workflows in this cloud computing era might as well be the way to go, given that resource allocation will be significantly improved, besides reduced execution time and costs. Most conventional scheduling algorithms lack the potential for optimal performance among conflicting objectives like performance, cost-efficiency, and resource utilization. The paper proposes a new multi-objective workflow scheduling framework, where the Spider Monkey Optimization algorithm will be combined with the Fuzzy Self-Defense Algorithm. SMO algorithm emulates the foraging behavior of spider monkeys for a compelling exploration of the complex solution space to find superior task-resource mappings. Besides this, a fuzzy self-defense strategy tackles the inherent uncertainties of dynamic cloud environments to make the framework more adaptable and resilient against failures and performance degradation. The proposed framework will be multi-objective, including the optimization of minimizing execution time, optimization of resource utilization, and energy consumption. Therefore, the model will significantly improve the balance of those competing goals, drawing strengths from SMO and fuzzy logic. The effectiveness is further validated through extensive experiments using synthetic and real-world workflow applications in a simulated cloud environment. Indeed, notable improvements have been observed along all the key performance indicators related to execution time, energy efficiency, and resource utilization. Besides, the hybrid framework is much more scalable and flexible in handling massive workflows, establishing its value as a practical resource management solution in cloud computing.