Develop a CPU Scheduler that Predicts the Next CPU Burst Time Using Machine Learning.

Develop a CPU Scheduler that Predicts the Next CPU Burst Time Using Machine Learning and Schedules Processes Efficiently” is an advanced operating systems project that enhances traditional CPU scheduling techniques through data-driven intelligence. The system integrates classical algorithms like First-Come-First-Serve (FCFS) and Shortest Job First (SJF) with a Machine Learning-based SJF (ML-SJF) model to improve scheduling accuracy and efficiency. A core feature of the project is its ability to predict the next CPU burst time using a Scikit-learn model trained on historical process data. This predictive capability enables smarter scheduling decisions, reducing average waiting time and turnaround time compared to conventional methods. The platform includes an interactive frontend built with React 19, Vite, Recharts, and Tailwind CSS, offering dynamic visualizations such as Gantt charts for execution timelines and performance comparison charts for key metrics. Detailed analytics provide insights into prediction accuracy using MAE and MSE, along with comparisons between predicted and actual burst times. The backend, powered by FastAPI and Uvicorn, ensures efficient data handling and model integration. Additionally, users can export simulation results in JSON format for further analysis. This project demonstrates the practical application of machine learning in optimizing core system-level operations.