Hybrid Teaching–Learning-Based Optimization for Workflow Scheduling in Cloud Environment

At present, workflow scheduling in cloud computing environment is still a challenging optimization topic due to its NP-complete characteristics. In order obtain better results, researchers are constantly coming up with new methods. this study, we offer hybrid metaheuristic for solving minimize the makespan of considering heterogeneity virtual resources. This approach combines excellent properties Heterogeneous Earliest Finish Time (HEFT), Teaching–Learning-Based Optimization (TLBO), Opposition-Based Learning (OBL), and genetic manipulations, which named Hybrid TLBO (HTLBO). Firstly, HEFT-based method proposed produce high-quality diverse initial population. Secondly, Mixed OBL (MOBL) model designed, boundary search information population historical systematically taken into account. Finally, an enhanced learner stage using operations added effectively help algorithm jump out local optima. Rigorous experiments over various scientific workflows conducted validate HTLBO’s performance. The obtained results compared HEFT some state-of-the-art metaheuristics terms average makespan, running time non-parametric statistics. A significant improvement schedule quality demonstrates that HTLBO can increase diversity achieve good balance between effectiveness efficiency.