Energy and Cost Aware Workflow Offloading Using Quantum Inspired Differential Evolution in the Cloud Environments

The cloud provides a valuable environment for users to run their applications, which are used in various fields such as bioinformatics, astronomy, biodiversity, and image analysis. Executing tasks across various virtual machines while considering multiple objectives simultaneously is highly challenging and is classified as a Non-Polynomial (NP)-Complete problem. Another significant challenge is offloading workflow applications (WAs) with valid execution sequences while ensuring compliance with dependency constraints among all tasks. This paper introduces a novel Energy-Cost Aware Workflow Offloading using a quantum-inspired differential evolution (EC-QIDE) algorithm EC-QIDE considers several conflicting factors, including Makespan, resource utilization, energy consumption, cost, and load balance. Quantum Vectors (QVs) are created using quantum bits and updated using a quantum angle. These QVs are then decoded using a novel hashing technique. The fitness function is designed to incorporate the diverse objectives mentioned. Extensive simulations were conducted and compared against state-of-the-art techniques. Both variance analysis and a Friedman test were performed to evaluate the results. Additionally, Taguchi’s parametric statistical technique was applied for further analysis. The simulation results indicate that EC-QIDE surpassed existing approaches in terms of Makespan by 6.44%, resource utilization by 4.43%, energy consumption by 1.03%, load balance by 42.28%, and cost by 0.30%.