AI-Driven VM Load Balancing Using Fuzzy Logic and Support Vector Machine
DOI:
https://doi.org/10.22399/ijcesen.5290Keywords:
Cloud Computing, Load Balancing, Fuzzy Logic, Support Vector Machine SVM, Virtual Machine, Resource OptimizationAbstract
Cloud computing has become an important solution for providing flexible and on-demand computing resources. As the number of users and requests increases, load balancing becomes a key challenge because tasks must be assigned to virtual machines in a way that reduces response time and improves resource use. This study proposes an intelligent Active VM Load Balancing algorithm based on Fuzzy Logic and Support Vector Machine, SVM. Fuzzy Logic is used to evaluate virtual machines according to their main characteristics, including memory size, processor speed, and number of processors. Then, SVM is applied to classify the most suitable virtual machine for each incoming task. The proposed approach aims to improve task allocation, avoid overloaded and underloaded virtual machines, and enhance overall cloud performance. The method is evaluated using CloudAnalyst and compared with common load balancing algorithms such as Round Robin, Throttled and Equally Spread Current Execution Load. The results show that the proposed Fuzzy-SVM approach improves response time, data center processing time, and resource utilization, making it a promising solution for smarter cloud load balancing.
References
[1] M. Hamdani, Y. Aklouf, and H. Chaalal, “A Comparative Study on Load Balancing Algorithms in Cloud Environment,” in Proceedings of the 10th International Conference on Information Systems and Technologies, in ICIST ’20. New York, NY, USA: Association for Computing Machinery, 2021. doi: 10.1145/3447568.3448466. DOI: https://doi.org/10.1145/3447568.3448466
[2] J. Li et al., “An End-to-End Load Balancer Based on Deep Learning for Vehicular Network Traffic Control,” IEEE Internet Things J., vol. 6, no. 1, pp. 953–966, 2019, doi: 10.1109/JIOT.2018.2866435. DOI: https://doi.org/10.1109/JIOT.2018.2866435
[3] L. A. Zadeh, “Knowledge representation in fuzzy logic,” in An introduction to fuzzy logic applications in intelligent systems, Springer, 1992, pp. 1–25. DOI: https://doi.org/10.1007/978-1-4615-3640-6_1
[4] M. Hamdani, Y. Aklouf, and H. A. Bouarara, “A Parallel Fuzzy Load Balancing Algorithm for Distributed Nodes Over a Cloud System,” Int. J. Grid High Perform. Comput. IJGHPC, vol. 14, no. 1, pp. 1–22, 2022. DOI: https://doi.org/10.4018/IJGHPC.301576
[5] H. Chaalal, M. Hamdani, and H. Belbachir, “Finding the best between the column store and row store Databases,” in Proceedings of the 10th International Conference on Information Systems and Technologies, in ICIST ’20. New York, NY, USA: Association for Computing Machinery, 2021. doi: 10.1145/3447568.3448548. DOI: https://doi.org/10.1145/3447568.3448548
[6] A. M. Alakeel and S. Arabia, “A Guide to Dynamic Load Balancing in Distributed Computer Systems,” 2010. [Online]. Available: https://api.semanticscholar.org/CorpusID:14313112
[7] A. A. AlKhatib, T. Sawalha, and S. AlZu’bi, “Load Balancing Techniques in Software-Defined Cloud Computing: an overview,” in 2020 Seventh International Conference on Software Defined Systems (SDS), 2020, pp. 240–244. doi: 10.1109/SDS49854.2020.9143874. DOI: https://doi.org/10.1109/SDS49854.2020.9143874
[8] A. Katangur, S. Akkaladevi, and S. Vivekanandhan, “Priority Weighted Round Robin Algorithm for Load Balancing in the Cloud,” in 2022 IEEE 7th International Conference on Smart Cloud (SmartCloud), 2022, pp. 230–235. doi: 10.1109/SmartCloud55982.2022.00044. DOI: https://doi.org/10.1109/SmartCloud55982.2022.00044
[9] S.-L. Chen, Y.-Y. Chen, and S.-H. Kuo, “CLB: A novel load balancing architecture and algorithm for cloud services,” Comput. Electr. Eng., vol. 58, pp. 154–160, 2017, doi: https://doi.org/10.1016/j.compeleceng.2016.01.029. DOI: https://doi.org/10.1016/j.compeleceng.2016.01.029
[10] S. Razzaghzadeh, A. H. Navin, A. M. Rahmani, and M. Hosseinzadeh, “Probabilistic modeling to achieve load balancing in Expert Clouds,” Ad Hoc Netw., vol. 59, pp. 12–23, 2017, doi: https://doi.org/10.1016/j.adhoc.2017.01.001. DOI: https://doi.org/10.1016/j.adhoc.2017.01.001
[11] L. Kang and X. Ting, “Application of adaptive load balancing algorithm based on minimum traffic in cloud computing architecture,” in 2015 International Conference on Logistics, Informatics and Service Sciences (LISS), 2015, pp. 1–5. doi: 10.1109/LISS.2015.7369792. DOI: https://doi.org/10.1109/LISS.2015.7369792
[12] P. A. Pattanaik, S. Roy, and P. K. Pattnaik, “Performance study of some dynamic load balancing algorithms in cloud computing environment,” in 2015 2nd International Conference on Signal Processing and Integrated Networks (SPIN), IEEE, 2015, pp. 619–624. DOI: https://doi.org/10.1109/SPIN.2015.7095363
[13] P. V. Lahande, “Quantum Equally Spread Current Execution Load Algorithm for Edge-Cloud Environment,” presented at the 2026 International Conference on Intelligent and Innovative Technologies in Computing, Electrical and Electronics (IITCEE), IEEE, 2026, pp. 1–6. DOI: https://doi.org/10.1109/IITCEE67948.2026.11394130
[14] K. Patel, A. Patel, and B. Patel, “A Comparative Analytics for Dynamic Load Balancing Mechanisms Intended to Improve Task Scheduling in Cloud Computing With Security Challenges,” Converg. Strateg. Green Comput. Sustain. Dev., pp. 182–201, 2024. DOI: https://doi.org/10.4018/979-8-3693-0338-2.ch011
[15] M. A. Khan, “Optimized hybrid service brokering for multi-cloud architectures,” J. Supercomput., vol. 76, no. 1, pp. 666–687, Jan. 2020, doi: 10.1007/s11227-019-03048-5. DOI: https://doi.org/10.1007/s11227-019-03048-5
[16] Z. Wang, F. Qin, Q. Miao, and X. Yuan, “Dynamic Load Balancing of Virtual Machine Servers Using Genetic Algorithm in a Cloud Computing Environmen,” presented at the 2025 4th International Conference on Artificial Intelligence, Internet of Things and Cloud Computing Technology (AIoTC), IEEE, 2025, pp. 776–780. DOI: https://doi.org/10.1109/AIoTC66747.2025.11198820
[17] S.-J. Yang and Y.-R. Chen, “Design adaptive task allocation scheduler to improve MapReduce performance in heterogeneous clouds,” J. Netw. Comput. Appl., vol. 57, pp. 61–70, 2015, doi: https://doi.org/10.1016/j.jnca.2015.07.012. DOI: https://doi.org/10.1016/j.jnca.2015.07.012
[18] M. Kalra and S. Singh, “A review of metaheuristic scheduling techniques in cloud computing,” Egypt. Inform. J., vol. 16, no. 3, pp. 275–295, 2015, doi: https://doi.org/10.1016/j.eij.2015.07.001. DOI: https://doi.org/10.1016/j.eij.2015.07.001
[19] I. A. T. Hashem et al., “MapReduce scheduling algorithms: a review,” J. Supercomput., vol. 76, no. 7, pp. 4915–4945, Jul. 2020, doi: 10.1007/s11227-018-2719-5. DOI: https://doi.org/10.1007/s11227-018-2719-5
[20] F. Ebadifard and S. M. Babamir, “Autonomic task scheduling algorithm for dynamic workloads through a load balancing technique for the cloud-computing environment,” Clust. Comput., vol. 24, no. 2, pp. 1075–1101, Jun. 2021, doi: 10.1007/s10586-020-03177-0. DOI: https://doi.org/10.1007/s10586-020-03177-0
[21] K. Madanmohan and T. Hirwarkar, “Analysis Of Alba Efficiency For Distributed Cloud Computing,” Turk. J. Comput. Math. Educ., vol. 12, no. 2, pp. 1405–1410, 2021. DOI: https://doi.org/10.17762/turcomat.v12i2.1352
[22] P. Wu, L. Zhou, H. Chen, and H. Zhou, “An improved fuzzy risk analysis by using a new similarity measure with center of gravity and area of trapezoidal fuzzy numbers,” Soft Comput., vol. 24, no. 6, pp. 3923–3936, Mar. 2020, doi: 10.1007/s00500-019-04160-7. DOI: https://doi.org/10.1007/s00500-019-04160-7
[23] P. Ram and R. Sibal, “A Novel Hybrid Approach to Enhance Software Quality by Using the Honey Badger Algorithm (HBA) and Support Vector Machine (SVM),” in 2025 International Conference on Electronics, Computing, Communication and Control Technology (ICECCC), 2025, pp. 1–6. doi: 10.1109/ICECCC65144.2025.11064181. DOI: https://doi.org/10.1109/ICECCC65144.2025.11064181
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 International Journal of Computational and Experimental Science and Engineering
This work is licensed under a Creative Commons Attribution 4.0 International License.
