Loading...
Ms. B. Akilandeswari is an Assistant Professor in the PG and Research Department of Computer Science at Shrimati Indira Gandhi College, Tiruchirappalli, Tamil Nadu, India. Her areas of interest include software engineering, data analytics, AI applications, and academic automation systems.
The automated creation of timetables constitutes a multifaceted scheduling challenge that encompasses several constraints, including course prerequisites, teacher availability, classroom assignments, and student preferences. Conventional manual scheduling is labour-intensive and frequently leads to disagreements and inefficiencies. This chapter examines the application of optimisation algorithms and machine learning approaches to automate timetable generation in educational institutions. It analyses traditional optimisation techniques including GA, Simulated Annealing (SA), Constraint Satisfaction Problems (CSP), and Integer Linear Programming (ILP), in conjunction with machine learning methodologies for predictive scheduling and adaptive optimisation. The chapter introduces a hybrid architecture that combines optimisation algorithms with machine learning models to provide conflict-free, efficient, and adaptable timetables. It addresses system architecture, constraint modelling, and objective functions for workload balancing, conflict minimisation, and resource utilisation maximisation. Applications in educational institutions, universities, and digital learning platforms are emphasised. Furthermore, difficulties including scalability, dynamic alterations, and data integrity are rigorously examined. Emerging developments such as reinforcement learning-driven scheduling, real-time timetable modification, and cloud-based scheduling systems are also examined. This chapter illustrates how intelligent scheduling systems can markedly enhance administrative efficiency and improve the overall educational experience.