IRO Journals
Journal of Trends in Computer Science and Smart Technology

Comparing Elitist Genetic Refinement and Reference-Point-Based Multi-Objective Optimization for Deep Q-Network Cloud Task Scheduling

Open Access
Published: 24 October, 2026
Pages: 993-1017
  • Sara Adnan Mahmood , Sara Adnan Mahmood
    Department of Computer Science, College of Education for Pure Science, University of Wasit, Wasit, Iraq
    Department of Computer Science, College of Education for Pure Science, University of Wasit, Wasit, Iraq
  • Hussein Najm Abd Ali Hussein Najm Abd Ali
    Department of Computer Science, College of Education for Pure Science, University of Wasit, Wasit, Iraq
    Department of Computer Science, College of Education for Pure Science, University of Wasit, Wasit, Iraq
view PDF
view PDF

How to Cite

Mahmood, Sara Adnan, and Hussein Najm Abd Ali. 2026. “Comparing Elitist Genetic Refinement and Reference-Point-Based Multi-Objective Optimization for Deep Q-Network Cloud Task Scheduling”. Journal of Trends in Computer Science and Smart Technology 8 (4): 993-1017. https://doi.org/10.36548/jtcsst.2026.4.005.
ACM ACS APA ABNT Chicago Harvard IEEE MLA Turabian Vancouver AMA

Download Citation

Endnote/Zotero/Mendeley (RIS) BibTeX

Keywords

Cloud Resource Scheduling
Deep Q-Network
Genetic Algorithm
NSGA-III
Multi-Objective Optimization
Statistical Significance Testing

Abstract

Cloud task scheduling must balance conflicting objectives: deadline compliance, energy consumption, makespan, and resource utilization. A common design pairs a forecasting module and a reinforcement-learning placement agent with a periodic evolutionary refinement stage, usually a single-objective genetic algorithm that merges the four objectives into one weighted score. This paper studies whether replacing that stage with the reference-point-based multi-objective Non-dominated Sorting Genetic Algorithm III (NSGA-III) changes the scheduling results when forecasting and placement remain unchanged. Both strategies were evaluated on simulated five-machine clusters with workload-prediction signals from real monitoring traces over ten random seeds at 50,000 tasks (NSGA-III also at 100,000). The elitist genetic algorithm produced a mean of 0.495 percent of tasks violating their service-level agreement (SLA), against 0.178 percent for NSGA-III; a paired Wilcoxon signed-rank test confirmed the difference (p = 0.0039, r = 0.854). Doubling the workload left NSGA-III’s violation rate stable (paired p = 0.426). NSGA-III needed far more time per run (48.56 versus 9.05 minutes) and slightly more energy (30,582,411 versus 30,034,047 simulation units; p = 0.0020, r = 0.886). Sensitivity analyses on a 10,000-task protocol showed that the result depends on configuration: ten tasks per batch lay in a narrow working range, the number of reference points mattered little, and the final-selection weights mattered most. The two procedures also differ in search budget, but a genetic algorithm given NSGA-III’s budget and operators had a higher mean violation rate than either of them, so extra search does not explain the advantage. With task attributes derived from the Bitbrains traces, the ranking held, but the SLA advantage of NSGA-III shrank from 65 to 24 percent, and its energy penalty disappeared.

References

  1. Arunarani, A. R., Dhanabalachandran Manjula, and Vijayan Sugumaran. “Task Scheduling Techniques in Cloud Computing: A Literature Survey.” Future Generation Computer Systems 91 (2019): 407-415.
  2. Bodra, Deep, and Sushil Khairnar. “Machine Learning-Based Cloud Resource Allocation Algorithms: A Comprehensive Comparative Review.” Frontiers in computer science 7 (2025): 1678976.
  3. Mao, Hongzi, Mohammad Alizadeh, Ishai Menache, and Srikanth Kandula. “Resource Management with Deep Reinforcement Learning.” In Proceedings of the 15th ACM workshop on hot topics in networks, 2016, 50-56.
  4. Osama, Muhammad, Syed Shah Sultan Mohiuddin Qadri, Rauf Ahmed Shams Malick, Muhammad Farrukh Shahid, and Kamran Dawood. “Enhanced Task Scheduling in IAAS Cloud Environments Using Elitism-Based Genetic Algorithms.” In 2024 8th International Conference on Electrical, Telecommunication and Computer Engineering (ELTICOM), IEEE, 2024, 62-67.
  5. Osama, Muhammad, Syed Shah Sultan Mohiuddin Qadri, Muhammad Farrukh Shahid, and Ahmet Kabarcık. “Enhancing Cloud Architecture’s Efficiency with an Adaptive Elitism-Based Genetic Algorithm for Task Scheduling.” In 2nd GCC International Conference on Industrial Engineering and Operations Management. IEOM Society, 2024.
  6. Deb, Kalyanmoy, and Himanshu Jain. “An Evolutionary Many-Objective Optimization Algorithm Using Reference-Point-Based Nondominated Sorting Approach, Part I: Solving Problems with Box Constraints.” IEEE transactions on evolutionary computation (2014). 18, no. 4 577–601.
  7. Wietheger, Simon, and Benjamin Doerr. “A Mathematical Runtime Analysis of the Non-Dominated Sorting Genetic Algorithm III (NSGA-III).” In Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence (IJCAI 2023), 5657–5665. 2023.
  8. Imene, Latreche, Slatnia Sihem, Kazar Okba, and Batouche Mohamed. “A Third Generation Genetic Algorithm NSGAIII for Task Scheduling in Cloud Computing.” Journal of King Saud University Computer and Information Sciences 34, no. 9 (2022): 7515-7529.
  9. Tang, Hongtao, Yu Xiao, Wei Zhang, Deming Lei, Jing Wang, and Tao Xu. “A DQL-NSGA-III Algorithm for Solving the Flexible Job Shop Dynamic Scheduling Problem.” Expert Systems with Applications 237 (2024): 121723.
  10. Derrac, Joaquín, Salvador García, Daniel Molina, and Francisco Herrera. “A Practical Tutorial on the Use of Nonparametric Statistical Tests as a Methodology for Comparing Evolutionary and Swarm Intelligence Algorithms.” Swarm and evolutionary computation 1, no. 1 (2011): 3-18.
  11. Carrasco, Jacinto, Salvador García, M. Mar Rueda, Swagatam Das, and Francisco Herrera. “Recent Trends in the Use of Statistical Tests for Comparing Swarm and Evolutionary Computing Algorithms: Practical Guidelines and a Critical Review.” Swarm and Evolutionary Computation 54 (2020): 100665.
  12. Xing, Yanli. “Work Scheduling in Cloud Network Based on Deep Q-LSTM Models for Efficient Resource Utilization.” Journal of Grid Computing 22, no. 1 (2024): 36.
  13. Naaz, Farheen, Ayes Chinmay, and Anmol Pattanaik. “QoS Aware Deep Reinforcement Learning Technique for Task Scheduling in Cloud Computing.” Discover Computing 29, no. 1 (2026): 185.
  14. Zeng, Lei, Qi Liu, Shigen Shen, and Xiaodong Liu. “Improved Double Deep Q Network-Based Task Scheduling Algorithm in Edge Computing for Makespan Optimization.” Tsinghua Science and Technology 29, no. 3 (2024): 806-817.
  15. Zhang, Ziyang, Guodong Fan, Jing Li, Ming Zhu, and Yujie Tian. “MA-DDQN: A Maintenance-Aware Adaptive Double Deep Q-Network for Multi-objective Scheduling in Cloud Manufacturing.” In International Conference on Intelligent Computing, Singapore: Springer Nature Singapore, 2025, 123-133.
  16. Yu, Xiaomo, Jie Mi, Ling Tang, Long Long, and Xiao Qin. “Dynamic Multi Objective Task Scheduling in Cloud Computing Using Reinforcement Learning for Energy and Cost Optimization.” Scientific Reports 15, no. 1 (2025): 45387.
  17. Guo, Wenxia, Wenhong Tian, Yufei Ye, Lingxiao Xu, and Kui Wu. “Cloud resource scheduling with deep reinforcement learning and imitation learning.” IEEE Internet of Things Journal 8, no. 5 (2021): 3576-3586.
  18. Ghaban, Wad, and Hind Salem Alatawi. “Federated Multi-Cloud Task Scheduling with Load Balancing Using Multi-Objective NSGA-II and Reinforcement Learning.” Scientific Reports (2026). 23729.
  19. Guna, G., S. Sarvan, Prashant Johri, Umidbek Abdalov, Sabokhon Erjanova, and Vaibhav C. Gandhi. “Multi-Objective Genetic Algorithms for Dynamic Resource Optimization in Cloud Computing.” In 2025 International Conference on Networks and Cryptology (NETCRYPT), IEEE, 2025, 876-881.
  20. Chen, Jing, Tiantian Du, and Gongyi Xiao. “A Multi-Objective Optimization for Resource Allocation of Emergent Demands in Cloud Computing.” Journal of Cloud Computing 10, no. 1 (2021): 20.
  21. Felsy, C., and R. Isaac Sajan. “Actor-Critic Optimization Based Adaptive Task Scheduling Using Deep Double Dueling Q Network for Heterogeneous Cloud Environments.” Transactions on Emerging Telecommunications Technologies 36, no. 7 (2025): e70185.
  22. Arbat, Shivani, Vinodh Kumaran Jayakumar, Jaewoo Lee, Wei Wang, and In Kee Kim. “Wasserstein Adversarial Transformer for Cloud Workload Prediction.” In Proceedings of the AAAI Conference on Artificial Intelligence, vol. 36, no. 11, 2022, 12433-12439.
  23. Chen, Yang, Jia Hao, Yu Peng, and Hongyan Xia. “Transformer-based Performance Prediction and Proactive Resource Allocation for Cloud-Native Microservices.” Cluster Computing 28, no. 9 (2025): 568.
  24. Zhang, Biying, Zhimin Qiu, Yanping Chen, and Yuling Huang. “Cloud Workload Prediction by the De-Based Nonstationary Transformer Model.” In Fourth International Conference on Network Communication and Information Security (ICNCIS 2024), vol. 13516, SPIE, 2025, 173-178.
  25. Zhang, Biying, Guanghao Yang, Feng Yu, and Qinghe Pan. “SWT-CLSTM: A Hybrid Model for Cloud Workload Prediction Combining Smooth Wavelet Transform and Contrastive Learning.” Journal of King Saud University Computer and Information Sciences 37, no. 10 (2025): 320.
  26. Ding, Zeyuan, Binbin Feng, and Wangyang Yu. “FELT: Large-Scale Cloud Workload Prediction Through Adaptive Feature-Enhanced and Similarity-Aware Transformer.” Tsinghua Science and Technology (2025).
  27. Verma, Abhishek, Luis Pedrosa, Madhukar Korupolu, David Oppenheimer, Eric Tune, and John Wilkes. “Large-scale Cluster Management at Google with Borg.” In Proceedings of the tenth european conference on computer systems, 2015, 1-17.
  28. Shen, Siqi, Vincent Van Beek, and Alexandru Iosup. “Statistical Characterization of Business-Critical Workloads Hosted in Cloud Datacenters.” In 2015 15th IEEE/ACM international symposium on cluster, cloud and grid computing, IEEE, 2015, 465-474.