Automated Scheduler of Teaching Load: A Genetic

Algorithm Approach
Author Name 1 Author Name 2 Author Name 3 Author Name 4
Department, Institution Department, Institution Department, Institution Department, Institution
Location Location Location Location
Email: [email protected] Email: [email protected] Email: [email protected] Email: [email protected]

Abstract—Managing academic schedules, subjects, and class- emphasizing its suitability for large and parameter-rich search
rooms poses complex challenges for educational institutions. spaces.
Manual generation of timetables involves time-consuming tasks
with numerous constraints. This research introduces an Au- IV. P ROPOSED W ORK
tomated Scheduler of Teaching Load, a web application that
automates the creation of load sheets and timetables. The system, The proposed Automated Scheduler of Teaching Load is
based on a constraint satisfaction problem, employs various a web application designed to automate timetable generation.
approaches to handle both hard and soft constraints. Using
It aims to streamline the scheduling process, reduce manual
frameworks like Django, MySql, and Python, the system provides
a user-friendly interface for efficient timetable creation, address- effort, and provide a user-friendly interface. The system allows
ing issues related to faculty workload, classroom allocation, and administrators and faculty to log in, manage timetables, edit
subject assignments. existing schedules, and update personnel and subject details.
Index Terms—Timetable, Django, MySql, Python, Web Appli- Genetic Algorithm is employed to enhance the efficiency of
cation, Load sheet, Excel sheet, Genetic Algorithm. timetable generation, reducing time requirements and mini-
mizing human errors.
I. I NTRODUCTION
Timetabling in educational institutions involves the intri- V. R ESULT A NALYSIS
cate process of scheduling lectures, allocating resources, and The system successfully generates load sheets in Excel
avoiding conflicts. Manual scheduling is a time-consuming format, providing detailed faculty and subject information. The
and complex task, considering factors like available faculty, use of Django framework facilitates easy data retrieval and
courses, rooms, and labs. This paper formulates the scheduling systematic data entry. The Genetic Algorithm implementation
problem as a constraint satisfaction problem and explores effectively produces timetables without clashes, ensuring op-
various approaches, including Genetic Algorithm, to address timal scheduling for multiple semesters and divisions. The
both hard and soft constraints. The proposed system offers an described steps involve initializing populations, performing
automatic timetable generation solution with a graphical user- crossovers, mutations, and fitness evaluations to achieve satis-
friendly interface, providing flexibility and avoiding clashes. factory solutions.
II. T YPES OF C ONSTRAINTS
VI. C ONCLUSIONS
The timetabling problem involves hard constraints such
as avoiding lecture clashes, room and lecturer utilization, The research presents a comprehensive solution to the
and meeting faculty working hour limits. Soft constraints timetable scheduler problem, utilizing Genetic Algorithm and
include minimizing empty slots, adhering to teaching loads, web application technologies. The proposed system success-
and accommodating specific room requirements. The paper fully addresses hard and soft constraints, making it a valu-
categorizes and addresses these constraints to achieve an able tool for educational institutions. The implementation
optimal and feasible timetable. using Django ensures user-friendly access, and the Genetic
Algorithm significantly improves the efficiency of timetable
III. L ITERATURE S URVEY generation.
The paper discusses various timetabling issues and dif-
VII. R EFERENCES
ferent methodologies, such as Group technique, Sequential
strategy, Meta-Heuristics, and Constraint-Based strategy. It R EFERENCES
explores meta-heuristic methods like Simulated Annealing, [1] Adithya R Pai, Ashwitha S, Raksha Shetty, and Prof. Geethalaxmi. ”Au-
Tabu Search, and Genetic Algorithm. The focus on Genetic tomated school schedule generator.” International Journal of Scientific
Algorithm involves creating a solution inspired by natural and Engineering Research, April 2018.
[2] Akshay Puttaswamy, H M Arshad Ali Khan, Chandan S.V, and Parka.A.
selection, making it suitable for optimization problems. The ”An investigation on programmed plan generator.” Global Journal of
advantages and limitations of Genetic Algorithm are outlined, Innovative Research and Growth, May 2018.
[3] Sundresan Perumal, Mujahid Tabassum, Norita MD, Ganthan Samy,
Sivananthan Perumal. ”Advancement of an efficient Timetable System.”
International Conference on Control System, Computing, and Engineer-
ing, 23-25 November 2018, Malaysia.
[4] Ping Guo, Jing-Xin Chen, Lin Zhu. ”The Design and Implementation
of schedule framework dependent on hereditary calculations.” Interna-
tional Conference on Mechatronic Science, Electric Engineering and
Computer, August 19-22, 2011, Jilin.
[5] Saritha M, Pranav Kiran Vaze, Pradeep, Mahesh N R. ”Programmed plan
generator.” International Journal of Advanced Research in Computer
Science and Software Engineering, May 2017.
[6] D. G. Maere. ”How Working Group Automated Timetabling was es-
tablished.” Retrieved from http://www.asap.ac.nott.ac.uk/, 2010, Last
accessed on 9th December 2011.