Automation of Scheduling for Examination using Genetic Algorithm

Abstract

This study focused on developing a genetic algorithm-based scheduling system designed to address the complexities of examination scheduling in academic institutions. In scheduling examinations, several constraints exist, such as room allocation, faculty proctoring limits, and the need to avoid schedule conflicts for students. Traditionally, educational institutions utilize spreadsheet scheduling, which is time-consuming, prone to errors, and unable to keep pace with the growing number of students, sections, and examinations. Therefore, the developed system aims to automate the scheduling process following institutional policies and constraints. The system was developed to optimize the examination scheduling process, with constraints encoded into the fitness functions that helped guide the genetic algorithm's operations. Modules for data validation, schedule generation, and conflict resolution underwent rigorous testing during the coding and unit testing phases. Integration and testing ensured that all parts of the system interacted seamlessly to create a robust scheduling solution. Significant findings include a constraint satisfaction rate of 96.63%, with all subjects successfully scheduled without conflict across over ten test iterations. The system ensured synchronized scheduling of shared subjects, minimized room replication to just 96.04%, eliminated faculty-proctor conflicts, and 100% conflict-free subject schedule. Additionally, it achieved a maximum fitness value of 190, demonstrating the effectiveness of the algorithm in resolving complex resource allocation challenges. The output demonstrates the capacity of the system to manage complex scheduling requirements within a classroom setup while ensuring conformity to the institution. It offers an efficient and scalable means of automating exam scheduling with time and manpower savings compared to conventional scheduling methods. Future improvements can be in terms of real-time room utilization optimization for unexpected schedule updates. These developments would further increase the usability and flexibility of the system in accommodating different scheduling requirements.