Enhanced Multitask Scheduling in Cloud Computing through Advanced Techniques

The delivery of computing services over the internet is referred to as cloud computing. One of the most significant challenges in the cloud computing environment is task scheduling, which directly impacts the overall performance of the platform. Tasks are assigned to specific resources at designated times based on user requests, primarily aiming to maximize resource utilization and minimize makespan. Despite various methods to enhance task scheduling, it remains a challenge in cloud computing. Efficiently scheduling tasks is a crucial step in fully leveraging the potential of cloud computing. This work presents a machine learning technique aimed at improving multitask scheduling in cloud environments. We propose an ML feature-based heuristic task scheduling (MLF-H) for efficient task management. Rather than randomly applying a scheduling algorithm, ML techniques are utilized to evaluate incoming task requests and determine the most suitable algorithm for each task. Simulation results indicate that the MLF-H task scheduling approach achieves the shortest makespan and demonstrates rapid generalization capabilities compared to traditional methods. This validates the effectiveness and efficiency of the MLF-H scheduling algorithm.