Multiobjective Task Scheduling in Cloud Environment Using Decision Tree Algorithm

In recent years, Cloud computing has been developed and become the foundation of a wide range applications. It allows users to access catalog standardized services respond their business needs flexibly adaptively, in event unforeseen demands, paying solely for consumption they have made. Task scheduling problem is considered one most critical cloud challenges. The refers how reasonably order allocate applications tasks provided by be executed on virtual machines. Furthermore, quality performance direct effect customer satisfaction. task must more accurately described improve performance. this paper, multi-objective algorithm proposed based decision tree heterogenous environment. We introduce new Scheduling-Decision Tree (TS-DT) allocating executing an application’s task. To evaluate TS-DT algorithm, comparative study was conducted among existing algorithms; Heterogeneous Earliest Finish Time (HEFT), Technique Order Preference Similarity Ideal Solution that incorporates Entropy Weight Method (TOPSIS-EWM), combining Q-Learning with (QL-HEFT). Our results show outperforms HEFT, TOPSIS-EWM, QL-HEFT algorithms reducing makespan 5.21%, 2.54%, 3.32%, respectively, improving resource utilization 4.69%, 6.81%, 8.27%, load balancing 33.36%, 19.69%, 59.06%, respectively average.