DEEP REINFORCEMENT LEARNING-BASED INTELLIGENT TASK SCHEDULING FRAMEWORK FOR CLOUD DISTRIBUTED SYSTEMS
DOI:
https://doi.org/10.65405/yj85x769Keywords:
Deep Reinforcement Learning, Task Scheduling, Cloud Computing, Resource Allocation, Deep Q-Networks, Proximal Policy Optimization, Energy Efficiency, Load Balancing, Intelligent Optimization, Distributed Systems, Quality of Service (QoS), Markov Decision Process.Abstract
Cloud computing environments face increasingly complex challenges in task scheduling due to dynamic workloads, heterogeneous resources, and multi-objective optimization requirements. This paper proposes an innovative Deep Reinforcement Learning (DRL)-based Intelligent Task Scheduling Framework (DRITS) designed to optimize task allocation and resource utilization in cloud distributed systems. The proposed framework leverages advanced Deep Q-Networks (DQN) and Proximal Policy Optimization (PPO) algorithms to enable dynamic, adaptive scheduling that continuously learns optimal policies through interaction with the cloud environment. Our comprehensive evaluation demonstrates that DRITS achieves significant performance improvements, including 32.4% reduction in makespan, 48.7% lower energy consumption, and 22.6% improvement in resource utilization compared to traditional heuristic algorithms [1]. Extensive simulations using real-world Google Cluster workloads and diverse benchmark datasets validate the robustness and scalability of the proposed approach across varying workload conditions. The framework demonstrates strong adaptability to dynamic environments, fault tolerance capabilities, and superior performance in multi-objective optimization scenarios. These results establish DRL-based intelligent scheduling as a promising solution for next-generation cloud computing infrastructure management.
Downloads
References
[1] Medishetti, S.K., et al. (2025). "Deep Reinforcement Learning for Intelligent Task Scheduling in Heterogeneous Cloud Environments." Proceedings of ICESC 2025.
[2] Sakib, S., et al. (2025). "Reinforcement Learning Based Adaptive Task Scheduling in Cloud Environments." IEEE ICCT.
[3] Waseem, M., Kavitha, G. (2025). "EdgeCloud-DRL: A Deep Reinforcement Learning-Based Task Scheduling Framework for Edge-Cloud Computing." International Journal of Applied Mathematics.
[4] Liao, X., et al. (2026). "Multi-Objective Deep Reinforcement Learning for Dynamic Task Scheduling Under Time-of-Use Electricity Price." Electronics, 15(1).
[5] Yu, X., et al. (2025). "Dynamic Multi-Objective Task Scheduling in Cloud Computing Using Reinforcement Learning." Scientific Reports.
[6] Choppara, P., Mangalampalli, S. (2024). "An Efficient Deep Reinforcement Learning Based Task Scheduler." Cluster Computing.
[7] Cui, D., et al. (2025). "Hierarchical Deep Reinforcement Learning for Cloud Task Scheduling." PLOS ONE.
[8] Kharche, S., et al. (2025). "Adaptive Deep Reinforcement Learning for Federated Cloud Computing." Journal of Information Systems and Engineering Management.
[9] Wang, Y., Yang, X. (2025). "Edge Computing and Cloud Collaborative Resource Scheduling Using DRL." ICAACE Proceedings.
[10] Li, T., et al. (2024). "Batch Jobs Load Balancing Using Distributional Reinforcement Learning." IEEE TPDS.
[11] Abushafa, M. (2026). Academic conferences as transitional learning infrastructures: Supporting AI engagement and professional learning in Libyan higher education. مجلة العلوم الشاملة, 10(39), 3338-3347.
[12] Al-Souri, L. M., Abuadla, A. M., Mubarak, J. R., Al-Qablawi, S. S. K., & Makari, I. M. (2026). Developing a Critical Inquiry-Based E-Educational Model (CIEM) to Enhance Critical Thinking Skills among High School Students: A Mixed-Methods Study in the Libyan Context. Al-Farooq Journal of Sciences, 2(4), 525-540.
[13] Ali, R. S. (2025). EFL Pre-Service Teachers’ Attitudes Towards Using AI Applications. Al-Farooq Journal of Sciences, 1(1), 93-109.
[14] Othman, E. A. (2026). A Contrastive Study of Relative Clauses between English and Libyan Arabic. مجلة العلوم الشاملة, 11(41), 1219-1225.
