A Machine Learning Approach for Predicting Efficient CPU Scheduling Algorithm

CPU scheduling is a critical aspect of an operating system design as it dictates how processes are prioritized for execution. In a uniprocessor, only a single process at a time can be executed simultaneously. The CPU scheduler considers various factors to determine the most effective process order. Thus, it's vital to decide quickly on the CPU scheduling strategy. In this research, a number of different machine learning algorithms are compared in order to determine which one offers the most suitable CPU scheduling method that is very effective and has the quickest turnaround time to carry out the new process requests. Implementing machine learning techniques in operating systems research can improve critical aspects such as response time, throughput, turnaround time, and waiting time. By enhancing the overall performance of the system, users are delivered a faster and more efficient computing experience. This analysis showcases the significance of utilizing machine learning techniques as a solution to the issues arising due to the ever-increasing complexity and demands of modern computing. By optimizing resource utilization and improving overall performance, we can reduce energy consumption and environmental impact while meeting the demands of modern computing. This aligns with the objectives of sustainable technology and Industry 5.0 to integrate physical and digital systems for sustainable and efficient production.