Cost-Efficient Task Scheduling in Cloud-Fog Systems using Hybrid Algorithm

Workflow scheduling in cloud-fog environment aims to optimize task allocation, execution time, and resource management. The complexity and dynamic nature of tasks and resources make finding an optimal workflow scheduling algorithm challenging. To address these limitations, this study introduces a Hybrid Particle Swarm Optimization Algorithm-Whale Optimization Algorithm (HPWOA). While Particle Swarm Optimization (PSO) struggles with slow convergence and high-dimensional search spaces, Whale Optimization Algorithm (WOA) faces difficulties in irregular search spaces and inconsistent convergence rates. By integrating PSO and WOA, HPWOA mitigates local optimization issues and enhances optimisation efficiency. The primary objective of this work is to minimise Total Execution Cost (TEC). To validate HPWOA, a comparative analyses against PSO, WOA, and HPWOA across three scientific workflows with increasing test cases has been performed. The results demonstrate that the proposed algorithm is 1.92% better than PSO and 9.60% better than WOA in terms of TEC. The paper highlights HPWOA's effectiveness in improving workflow scheduling and identifying the optimal workflow configurations for cloud-fog environments.