Development of Dynamic Task Scheduling in Multi-Core Systems Using Teaching–Learning-Based Optimization
DOI:
https://doi.org/10.63561/jca.v3i1.1236Keywords:
Multi-core systems, Task scheduling, Teaching-Learning-Based Optimization (TLBO), Multi-objective optimization, Makespan, Load balancingAbstract
Efficient task scheduling in multi-core systems remains a critical challenge due to the increasing complexity of applications, dynamic workloads, and the need to optimize multiple conflicting objectives such as execution time, energy consumption, and load balancing. Traditional scheduling algorithms often struggle to adapt to dynamic environments and fail to achieve optimal performance across diverse system conditions. This paper proposes a dynamic task scheduling approach based on the Teaching-Learning-Based Optimization (TLBO) algorithm to address these limitations. The proposed method models task scheduling as a multi-objective optimization problem, where tasks are dynamically allocated to multiple processing cores while considering task dependencies and system constraints. The TLBO algorithm, inspired by the teaching–learning process in a classroom, is adapted to efficiently explore and exploit the solution space without requiring algorithm-specific parameters. The methodology incorporates both teacher and learner phases to iteratively improve scheduling decisions and enhance system performance. To evaluate the effectiveness of the proposed approach, extensive simulations were conducted using standard benchmarking scenarios and compared against conventional optimization techniques such as Genetic Algorithm (GA) and Particle Swarm Optimization (PSO). Performance metrics, including makespan, throughput, resource utilization, and energy efficiency, were analyzed. The results demonstrate that the TLBO-based scheduler significantly improves overall system performance, achieving reduced execution time and better load distribution across cores. The findings suggest that TLBO provides a robust and scalable solution for dynamic task scheduling in multi-core environments. This research contributes to the advancement of intelligent scheduling techniques and offers a foundation for future work in adaptive and energy-aware computing systems.
References
Abdullahi, M., Ngadi, M. A., & Abdulhamid, S. M. (2020). A survey of metaheuristic algorithms for task scheduling in cloud computing. Journal of Network and Computer Applications, 150, 102-118.
Aminu, A., Sani, M. L., & Musa, A. (2025). A systematic review of metaheuristic-based scheduling approaches in edge computing environments. Future Generation Computer Systems, 152, 45-63.
Chen, H., Li, X., & Zhang, Y. (2021). Clustering-based scheduling for large task graphs in multi-core systems. IEEE Transactions on Parallel and Distributed Systems, 32(4), 891-905.
Chen, W., Wang, J., & Liu, Z. (2022). Ant Colony Optimization for dynamic task scheduling in distributed computing systems. Swarm and Evolutionary Computation, 68, 101-115.
Clark, R., & Xu, L. (2024). Genetic programming-based scheduler with advanced crossover semantics for dependency-intensive workloads. Genetic Programming and Evolvable Machines, 25(2), 215-234.
Gupta, A., & Reddy, K. S. (2022). Energy-aware hybrid scheduler integrating TLBO with dynamic voltage scaling for IoT edge gateways. Sustainable Computing: Informatics and Systems, 34, 100-112.
Hegde, S., Patil, R., & Kulkarni, P. (2024). TLBO-based scheduler with constraint-handling for multi-objective task scheduling in grid computing. Journal of Grid Computing, 22(1), 45-62.
Huang, J., & Wang, S. (2021). Dependency-aware scheduling in heterogeneous multi-core systems. Journal of Systems Architecture, 118, 102-115.
Kim, S., & Lee, J. (2021). Adaptive list scheduling for heterogeneous multi-core systems under fluctuating workloads. IEEE Transactions on Computers, 70(8), 1250-1263.
Kumar, R., & Singh, P. (2021). Multi-core architectures for high-performance computing: Challenges and opportunities. ACM Computing Surveys, 54(3), 1-36. DOI: https://doi.org/10.1145/3456628
Lee, M., Park, H., & Kim, D. (2024). Enhanced Particle Swarm Optimization with adaptive inertia weighting for throughput improvement in heterogeneous clusters. Applied Soft Computing, 158, 111-129.
Li, Q., & Zhao, F. (2023). Enhanced PSO-driven dynamic scheduler for unpredictable task arrivals in real-time systems. Real-Time Systems, 59(2), 178-201.
Liu, Y., Zhang, W., & Chen, G. (2025). TLBO-based energy-aware scheduler with load balancing for heterogeneous multi-core processors. IEEE Transactions on Sustainable Computing, 10(1), 88-102.
Nguyen, T., Tran, H., & Hoang, K. (2022). Real-time adaptive scheduler with dynamic priority weighting for cloud-driven multi-core servers. Journal of Cloud Computing, 11(1), 23-38.
Patel, D., & Mehta, N. (2023). Multi-objective Genetic Algorithm for optimizing makespan and energy consumption in heterogeneous computing clusters. Cluster Computing, 26(4), 2345-2362.
Rahman, A., & Caldwell, B. (2023). Reinforcement learning-based dynamic scheduler for cloud burst scenarios. IEEE Transactions on Cloud Computing, 11(3), 2789-2802.
Rahman, M., Islam, R., & Hossain, S. (2022). Task scheduling challenges in edge computing: A comprehensive review. Journal of Parallel and Distributed Computing, 168, 45-62.
Rao, R. V. (2020). Teaching-Learning-Based Optimization algorithm: Principles and applications. Springer.
Rao, R. V., Savsani, V. J., & Vakharia, D. P. (2020). Teaching-Learning-Based Optimization for combinatorial optimization problems. Computers & Industrial Engineering, 148, 106-118.
Singh, A., & Verma, P. (2024). Modified NSGA-II with problem-specific heuristics for multi-objective task scheduling in multi-core systems. Swarm and Evolutionary Computation, 82, 101-120.
Tran, H., & Hoang, K. (2022). Dependency-aware Ant Colony Optimization scheduler for directed acyclic graph task sets. Future Generation Computer Systems, 129, 345-358.
Wang, L., Liu, B., & Chen, Y. (2021). NP-hard problems in multi-core task scheduling: A survey. ACM Computing Surveys, 54(5), 1-35.
Zhang, X., Li, M., & Wang, Y. (2022). From single-core to multi-core: Evolution and challenges. Computer, 55(6), 42-51.
Zhang, Y., Liu, J., & Zhao, H. (2023). Ant Colony Optimization with dynamically adjusted pheromone mechanisms for load balancing in real-time heterogeneous systems. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 53(7), 4321-4334.
.
