Exploration of dynamic task scheduling using machine learning approaches

Abstract

Allocating shared resources gradually allows tasks to be completed efficiently within the allocated time. This is the process of scheduling. The terms "task" and "resource" are used separately in task scheduling and resource allocation, respectively. In computer science and operational management, scheduling is a hot topic. Efficient schedules guarantee system effectiveness, facilitate sound decision-making, reduce resource waste and expenses, and augment total productivity. Selecting the most appropriate resources to complete work items and schedules for computing and business process execution is typically a laborious task. Particularly in dynamic real-world systems, where scheduling different dynamic tasks involves multiple tasks, is a difficult problem. Emerging technology known as "Machine Learning Algorithms" has the ability to dynamically resolve the issue of scheduling tasks and resources optimally. This review paper discusses a study that looked at Machine Learning algorithms used them to schedule tasks dynamically. The Machine Learning Algorithms utilized in dynamic task scheduling and a comparative analysis of those methods are used in this paper to address the study's findings.