Penyetelan Parameter Berbantuan Machine Learning untuk Penjadwalan Cloud Berbasis Metaheuristik

Ardi Pujiyanta; Faisal Fajri Rahani; Taufiq Ismail

doi:10.30736/jti.v11i02.1649

Authors

Ardi Pujiyanta Universitas Ahmad Dahlan Yogyakarta
Faisal Fajri Rahani Universitas Ahmad Dahlan Yogyakarta
Taufiq Ismail Universitas Ahmad Dahlan Yogyakarta

DOI:

https://doi.org/10.30736/jti.v11i02.1649

Keywords:

Penjadwalan Cloud, Machine Learning, Genetic Algorithm, Penyetelan Parameter, Metaheuristik

Abstract

Penjadwalan cloud berbasis metaheuristik sangat dipengaruhi oleh kualitas pemilihan parameter algoritma. Namun, pada banyak penelitian, parameter genetic algorithm masih ditetapkan secara tetap atau dituning secara konvensional, sehingga kurang adaptif terhadap perubahan karakteristik workload. Penelitian ini mengusulkan pendekatan penyetelan parameter berbantuan machine learning untuk penjadwalan cloud berbasis metaheuristik guna memprediksi parameter genetic algorithm berdasarkan karakteristik workload cloud. Dataset yang digunakan berasal dari GoCJ mentah yang ditransformasikan menjadi 45 skenario workload melalui tiga regime, yaitu tight, medium, dan loose. Tahapan penelitian meliputi pembentukan fitur workload, pelabelan parameter terbaik genetic algorithm, pembangunan model prediksi parameter, serta evaluasi dampaknya terhadap performa penjadwalan. Metode usulan, yaitu GA-ML, dibandingkan dengan FCFS, EDF, GA-Default, dan GA-Grid. Hasil eksperimen menunjukkan bahwa GA-ML memberikan performa lebih baik dibandingkan GA-Grid pada tiga dari empat metrik evaluasi. Secara khusus, GA-ML menurunkan total penalty sebesar 8,269%, weighted tardiness sebesar 8,804%, dan violation rate sebesar 1,366% dibandingkan GA-Grid. Namun, GA-ML menghasilkan makespan sedikit lebih tinggi sebesar 0,582%. Hasil uji Wilcoxon signed-rank menunjukkan bahwa perbedaan antara GA-ML dan GA-Grid signifikan pada seluruh metrik. Temuan ini menunjukkan bahwa penyetelan parameter berbantuan machine learning efektif untuk meningkatkan performa penjadwalan berbasis SLA, terutama dalam menekan penalti, keterlambatan berbobot, dan tingkat pelanggaran deadline, meskipun terdapat trade-off kecil pada makespan.

Downloads

Download data is not yet available.

References

[1] W. K. Awad, Khairul Akram Zainol Ariffin, M. Z. A. Nazri, and E. T. Yassen, “Resource allocation strategies and task scheduling algorithms in cloud computing: a systematic literature review,” J. Intell. Syst., vol. 34, no. 1, 2025, doi: 10.1515/jisys-2024-0441.

[2] N. Devi et al., “A systematic literature review for load balancing and task scheduling techniques in cloud computing,” Artif. Intell. Rev., vol. 57, no. 10, p. 276, 2024, doi: 10.1007/s10462-024-10925-w.

[3] S. H. H. Madni, M. Faheem, M. Younas, M. H. Masum, and S. Shah, “Critical review on resource scheduling in IaaS clouds: Taxonomy, issues, challenges, and future directions,” J. Eng., no. 8, p. e12420, 2024, doi: 10.1049/tje2.12420.

[4] W. Khallouli and J. Huang, “Cluster resource scheduling in cloud computing: literature review and research challenges,” J. Supercomput., vol. 78, no. 5, pp. 6898–6943, 2022, doi: 10.1007/s11227-021-04138-z.

[5] R. Aron and A. Abraham, “Resource scheduling methods for cloud computing environment: The role of meta-heuristics and artificial intelligence,” Eng. Appl. Artif. Intell., vol. 116, no. September, p. 105345, 2022, doi: 10.1016/j.engappai.2022.105345.

[6] D. Zhang, Xiaolan Xie, and Y. Song, “A Multi-Objective Optimization-Based Container Cloud Scheduling Method for Multi-Scenario Resource Management,” Futur. Internet, vol. 18, no. 1, p. 58, 2026, doi: 10.3390/fi18010058.

[7] J. Pan, Yi Wei, L. Meng, and X. Meng, “A dual scheduling framework for task and resource allocation in cloud computing,” J. King Saud Univ. Comput. Inf. Sci., vol. 37, no. 5, p. 81, 2025, doi: 10.1007/s44443-025-00092-5.

[8] L. Mao, R. Chen, H. Cheng, W. Lin, B. Liu, and J. Z. Wang, “A resource scheduling method for cloud data centers based on thermal management,” J. Cloud Comput., vol. 12, no. 84, 2023, doi: 10.1186/s13677-023-00462-2.

[9] S. S. Sefati et al., “Adaptive Resource Scheduling in Multi-Cloud Computing Using Recurrent Neural Forecasting and Memory-Based Metaheuristic Optimization,” J. Grid Comput., vol. 23, no. 4, p. 26, 2025, doi: 10.1007/s10723-025-09812-7.

[10] H.-M. Song et al., “Task scheduling of cloud computing system by frilled lizard optimization with time varying expansion mixed function oscillation and horned lizard camouflage strategy,” J. Netw. Comput. Appl., vol. 245, p. 104386, 2025, doi: 10.1016/j.jnca.2025.104386.

[11] Y.-F. Sun, Si-Wen Zhang, J.-S. Wang, S.-H. Zhang, Y.-C. Wang, and X.-F. Sui, “Task scheduling in cloud computing system by improved honey badger optimization algorithm with two dimensional and three dimensional fractals,” Sustain. Comput. Informatics Syst., vol. 48, p. 101201, 2025, doi: 10.1016/j.suscom.2025.101201.

[12] Y. Han, “Cloud computing task scheduling based on particle swarm optimization algorithm,” Procedia Comput. Sci., vol. 261, pp. 1349–1355, 2025, doi: 10.1016/j.procs.2025.05.012.

[13] K. J. S and G. M, “A Probabilistic Genetic Algorithm Approach to Efficient Task Scheduling in Cloud Environments,” CLEI Electron. J., vol. 28, no. 5, 2025, doi: 10.19153/cleiej.28.5.9.

[14] X. Zhang, “Optimizing scientific workflow scheduling in cloud computing: a multi-level approach using whale optimization algorithm,” J. Eng. Appl. Sci., vol. 71, no. 1, p. 175, 2024, doi: 10.1186/s44147-024-00512-9.

[15] I. Behera and S. Sobhanayak, “Task scheduling optimization in heterogeneous cloud computing environments: A hybrid GA-GWO approach,” J. Parallel Distrib. Comput., vol. 183, p. 104766, 2024, doi: 10.1016/j.jpdc.2023.104766.

[16] M. Otair, Areej Alhmoud, H. Jia, M. Altalhi, A. M. Hussein, and L. Abualigah, “Optimized task scheduling in cloud computing using improved multi-verse optimizer,” Cluster Comput., vol. 25, no. 6, pp. 4221–4232, 2022, doi: 10.1007/s10586-022-03650-y.

[17] S.-W. Zhang, J.-S. Wang, S.-H. Zhang, Y.-X. Xing, X.-F. Sui, and Y.-H. Zhang, “Task scheduling in cloud computing systems using multi-objective honey badger algorithm with two hybrid elite frameworks and circular segmentation screening,” Artif. Intell. Rev., vol. 58, no. 2, p. 48, 2025, doi: 10.1007/s10462-024-11032-6.

[18] F. S. Prity, M. H. Gazi, and K. M. A. Uddin, “A review of task scheduling in cloud computing based on nature-inspired optimization algorithm,” Cluster Comput., vol. 26, no. 5, pp. 3037–3067, 2023, doi: 10.1007/s10586-023-04090-y.

[19] M. Tanha, Mirsaeid Hosseini Shirvani, and A. M. Rahmani, “A hybrid meta-heuristic task scheduling algorithm based on genetic and thermodynamic simulated annealing algorithms in cloud computing environments,” Neural Comput. Appl., vol. 33, no. 24, pp. 16951–1698, 2021, doi: 10.1007/s00521-021-06289-9.

[20] F. Kaplan and Ahmet Babalik, “Performance analysis of cloud computing task scheduling using metaheuristic algorithms in DDoS and normal environments,” Electronics, vol. 14, no. 10, p. 1988, 2025, doi: 10.3390/electronics14101988.

[21] D. Bodra, S. Khairnar, and Sushil Khairnar, “Machine learning-based cloud resource allocation algorithms: a comprehensive comparative review,” Front. Comput. Sci., vol. 7, p. 1678976, 2025, doi: 10.3389/fcomp.2025.1678976.

[22] S. Kayalvili, R. Senthilkumar, S. Yasotha, and R. S. Kamalakannan, “An Optimized Resource Allocation in Cloud Using Prediction Enabled Reinforcement Learning,” Sci. Rep., vol. 15, p. 36088, 2025, doi: 10.1038/s41598-025-19927-2.

[23] Y. Sanjalawe, Salam Al-E’mari, S. Fraihat, and S. Makhadmeh, “AI-driven job scheduling in cloud computing: a comprehensive review,” Artif. Intell. Rev., vol. 58, no. 7, p. 197, 2025, doi: 10.1007/s10462-025-11208-8.

[24] S. I. Mohammed and Z. T. M. Al-Ta’i, “Evaluation of Resource Allocation in Cloud Using Machine Learning,” in Proceedings Proceedings of the 13th International Conference on Applied on Applied Innovations in IT in IT (ICAIIT), 2025, pp. 253–260. [Online]. Available: https://opendata.uni-halle.de/bitstream/1981185920/122400/1/1-26-ICAIIT_2025_13%282%29.pdf

[25] F. S. Alsubaei, A. Y. Hamed, M. R. Hassan, M. Mohery, and M. K. Elnahary, “Machine learning approach to optimal task scheduling in cloud communication,” Alexandria Eng. J., vol. 89, pp. 1–30, 2024, doi: 10.1016/j.aej.2024.01.040.

[26] A. Bin Naeem, Biswaranjan Senapati, J. Rasheed, J. Baili, and O. Osman, “An intelligent job scheduling and real-time resource optimization for edge-cloud continuum in next generation networks,” Sci. Rep., vol. 15, p. 41534, 2025, doi: 10.1038/s41598-025-25452-z.

[27] M. F. A. Heirati and Mohammad Khalily-Dermany, “Optimized Task Scheduling in Fog-Cloud Computing Using Hybrid Deep Learning and Metaheuristic Algorithms,” Neural Process. Lett., vol. 58, no. 1, 2025, doi: 10.1007/s11063-025-11819-w.

[28] D. Cui, Zhiping Peng, K. Li, Q. Li, J. He, and X. Deng, “An novel cloud task scheduling framework using hierarchical deep reinforcement learning for cloud computing,” PLoS One, vol. 20, no. 8, p. e0329669, 2025, doi: 10.1371/journal.pone.0329669.

[29] S. Gurusamy and R. Selvaraj, “Resource allocation with efficient task scheduling in cloud computing using hierarchical auto-associative polynomial convolutional neural network,” Expert Syst. Appl., vol. 249, p. 123554, 2024, doi: 10.1016/j.eswa.2024.123554.

[30] A. Bolufé-Röhler and Dania Tamayo-Vera, “Machine learning for enhancing metaheuristics in global optimization: A comprehensive review,” Mathematics, vol. 13, no. 18, p. 2909, 2025, doi: 10.3390/math13182909.

[31] S. Szénási and G. Légrádi, “Machine learning aided metaheuristics: A comprehensive review of hybrid local search methods,” Expert Syst. Appl., vol. 258, p. 125192, 2024, doi: 10.1016/j.eswa.2024.125192.

[32] M. Cui and Yipeng Wang, “An effective QoS-aware hybrid optimization approach for workflow scheduling in cloud computing,” Sensors, vol. 25, no. 15, p. 4705, 2025, doi: 10.3390/s25154705.

[33] S. Chowdhury, Ajay Katangur, and A. Sheta, “Optimization of datacenter selection through a genetic algorithm-driven service broker policy,” J. Cloud Comput., vol. 13, no. 1, p. 156, 2024, doi: 10.1186/s13677-024-00719-4.