Authors : K. Usha Rani; V. G. Kishore Kumar; R. Pravin; T. P. Yagna Narayanan

Volume/Issue : Volume 11 - 2026, Issue 3 - March

Google Scholar : https://tinyurl.com/mr2ewu9f

Scribd : https://tinyurl.com/3chmrh32

DOI : https://doi.org/10.38124/ijisrt/26mar972

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Abstract : Efficient CPU scheduling plays a crucial role in optimizing system performance and reducing energy consumption in modern computing environments. Conventional scheduling methods, such Round Robin (RR), Shortest Job First (SJF), and First Come First Serve (FCFS), are based on preset heuristics and are unable to dynamically adjust to changing workload patterns. This study suggests a CPU scheduling paradigm based on deep learning that maximises execution time and energy use. The suggested approach predicts the best scheduling choices by utilising past task execution data, such as arrival time, burst time, and priority metrics. To find effective task ordering techniques that reduce average waiting time, turnaround time, and total power consumption, a neural network model is developed. In terms of execution efficiency and energy savings, experimental evaluation shows notable gains over traditional scheduling strategies. The outcomes confirm how well deep learning works to enable intelligent, performance-aware, and adaptive CPU scheduling techniques for contemporary computer systems.

Keywords : Deep Learning, CPU Scheduling, Energy Optimization, Execution Time Reduction, Multilayer Perceptron (MLP), Adam Optimizer, Neural Networks, Intelligent Scheduling, Machine Learning, System Performance Optimization.

References :

1. Prashanth Choppara, S. Sudheer Mangalampalli, “Resource Adaptive Automated Task Scheduling Using Deep Deterministic Policy Gradient in Fog Computing,” Vol. 13, 2025.
2. H. Janjani, T. Agarwal, M. P. Gopinath, V. Sharma, S. P. Raja, “Designing Energy-Aware Scheduling and Task Allocation Algorithms for Online Reinforcement Learning Applications in Cloud Environments,” Vol. 12, 2024.
3. Ying Dar Lin, Yin Tao Ling, Yuan Cheng Lai, Didik Sudyana, “Reinforcement Learning for AI as a Service: CPU-GPU Task Scheduling for Preprocessing, Training, and Inference Tasks,” Vol. 22, No. 4, pp. 3433‑3448, 2025.
4. Velasco-Montero, Delia, Bart Goossens, Jorge Fernandez-Berni, Ángel Rodríguez-Vázquez, and Wilfried Philips. "A pipelining-based heterogeneous scheduling and energy-throughput optimization scheme for cnns leveraging apache tvm." IEEe Access 11 (2023): 35007-35021.
5. Guan, Zheng, Zengwen Wang, Yu Cai, and Xue Wang. "Deep reinforcement learning based efficient access scheduling algorithm with an adaptive number of devices for federated learning IoT systems." Internet of Things 24 (2023): 100980.
6. Jalali Khalil Abadi, Zahra, Najme Mansouri, and Mohammad Masoud Javidi. "Deep reinforcement learning-based scheduling in distributed systems: a critical review." Knowledge and Information Systems 66, no. 10 (2024): 5709-5782.
7. Li, Peisong, Ziren Xiao, Xinheng Wang, Kaizhu Huang, Yi Huang, and Honghao Gao. "EPtask: Deep reinforcement learning based energy-efficient and priority-aware task scheduling for dynamic vehicular edge computing." IEEE Transactions on Intelligent Vehicles 9, no. 1 (2023): 1830-1846.
8. Lin, Chengran, ZhengCai Cao, and MengChu Zhou. "Autoencoder-embedded iterated local search for energy-minimized task schedules of human–cyber–physical systems." IEEE Transactions on Automation Science and Engineering 22 (2023): 512-522.
9. Zhang, Lixiang, Yan Yan, and Yaoguang Hu. "Deep reinforcement learning for dynamic scheduling of energy-efficient automated guided vehicles." Journal of Intelligent Manufacturing 35, no. 8 (2024): 3875-3888.
10. Choppara, Prashanth, and Sudheer Mangalampalli. "An efficient deep reinforcement learning based task scheduler in cloud-fog environment." Cluster Computing 28, no. 1 (2025): 67.
11. Gong, Lin, Zijie Huang, Xi Xiang, and Xin Liu. "Real-time AGV scheduling optimisation method with deep reinforcement learning for energy-efficiency in the container terminal yard." International Journal of Production Research 62, no. 21 (2024): 7722-7742.
12. Chai, Sheng, and Jimmy Huang. "Dependent task scheduling using parallel deep neural networks in mobile edge computing." Journal of Grid Computing 22, no. 1 (2024): 27.
13. Hosseinzadeh, Mehdi, Elham Azhir, Jan Lansky, Stanislava Mildeova, Omed Hassan Ahmed, Mazhar Hussain Malik, and Faheem Khan. "Task scheduling mechanisms for fog computing: a systematic survey." IEEE Access 11 (2023): 50994-51017.
14. Pal, Souvik, N. Z. Jhanjhi, Azmi Shawkat Abdulbaqi, D. Akila, Faisal S. Alsubaei, and Abdulaleem Ali Almazroi. "An intelligent task scheduling model for hybrid internet of things and cloud environment for big data applications." Sustainability 15, no. 6 (2023): 5104.
15. Ye, Zhisheng, Wei Gao, Qinghao Hu, Peng Sun, Xiaolin Wang, Yingwei Luo, Tianwei Zhang, and Yonggang Wen. "Deep learning workload scheduling in gpu datacenters: A survey." ACM Computing Surveys 56, no. 6 (2024): 1-38.