MACHINE LEARNING-BASED LOAD BALANCING MECHANISMS IN CLOUD COMPUTING: TAXONOMY, CHALLENGES, AND FUTURE DIRECTIONS
DOI:
https://doi.org/10.29121/shodhkosh.v7.i10s.2026.8169Keywords:
Cloud Computing, Load Balancing, Machine Learning, Resource Optimization, Explainable Ai, Edge–Fog ComputingAbstract [English]
Cloud computing has become the backbone of modern digital infrastructure, offering flexible and scalable access to computing resources. However, uneven workload distribution continues to hinder system efficiency. Conventional load balancing methods such as Round Robin, Min-Min, and various heuristic or metaheuristic techniques often fall short when dealing with large-scale, heterogeneous, and highly dynamic cloud environments.
Recent advances in machine learning (ML) have opened new avenues for adaptive and predictive load management. ML-based approaches can forecast workloads, adjust resource allocation, and optimize task scheduling with minimal human intervention. This review presents a structured taxonomy of ML-driven load balancing methods, organized into four main categories: supervised learning, unsupervised learning, deep learning, and reinforcement learning. Key models including artificial neural networks (ANN), convolutional neural networks (CNN), long short-term memory (LSTM) networks, and reinforcement learning agents are analyzed in terms of throughput, latency, energy efficiency, and fault tolerance. Despite significant progress, several issues persist, such as scalability, computational cost, limited data availability, and model interpretability. The paper also discusses emerging directions like explainable AI (XAI), hybrid heuristic-ML models, transfer learning, and integration with edge and fog computing layers. By consolidating recent research, this study aims to guide the development of intelligent, adaptive, and energy-aware load balancing strategies for future cloud ecosystems.
References
A. O. Ercan and I. F. Akyildiz, “Optimization techniques in cloud resource allocation: A survey,” Comput. Netw., vol. 150, pp. 136–151, 2018.
A. O. Ercan and I. F. Akyildiz, “Optimization techniques in cloud resource allocation: A survey,” Comput. Netw., vol. 150, pp. 136–151, 2018.
A. O. Ercan and I. F. Akyildiz, “Optimization techniques in cloud resource allocation: A survey,” Comput. Netw., vol. 150, pp. 136–151, 2018.
A. Rahmani, M. Nikravesh, and A. Yassine, “Scalable cloud resource scheduling with reinforcement learning,” IEEE Trans. Cloud Comput., vol. 9, no. 4, pp. 1243–1257, 2021.
A. Rahmani, M. Nikravesh, and A. Yassine, “Scalable cloud resource scheduling with reinforcement learning,” IEEE Trans. Cloud Comput., vol. 9, no. 4, pp. 1243–1257, 2021.
A. Rahmani, M. Nikravesh, and A. Yassine, “Scalable cloud resource scheduling with reinforcement learning,” IEEE Trans. Cloud Comput., vol. 9, no. 4, pp. 1243–1257, 2021.
B. Biggio and F. Roli, “Wild patterns: Ten years after the rise of adversarial machine learning,” Pattern Recognit., vol. 84, pp. 317–331, 2018.
B. Biggio and F. Roli, “Wild patterns: Ten years after the rise of adversarial machine learning,” Pattern Recognit., vol. 84, pp. 317–331, 2018.
B. Biggio and F. Roli, “Wild patterns: Ten years after the rise of adversarial machine learning,” Pattern Recognit., vol. 84, pp. 317–331, 2018.
B. Biggio and F. Roli, “Wild patterns: Ten years after the rise of adversarial machine learning,” Pattern Recognit., vol. 84, pp. 317–331, 2018.
B. P. Rimal, E. Choi, and I. Lumb, “Architectural requirements for cloud resource management: A vision for future computing paradigms,” IEEE Commun. Mag., vol. 57, no. 2, pp. 76–82, 2019.
B. P. Rimal, E. Choi, and I. Lumb, “Architectural requirements for cloud resource management: A vision for future computing paradigms,” IEEE Commun. Mag., vol. 57, no. 2, pp. 76–82, 2019.
B. P. Rimal, E. Choi, and I. Lumb, “Architectural requirements for cloud resource management: A vision for future computing paradigms,” IEEE Commun. Mag., vol. 57, no. 2, pp. 76–82, 2019.
Beimborn, D., Miletzki, T., & Wenzel, S. (2011). Platform as a service (PaaS). Wirtschaftsinformatik, 53(6), 371-375.
D. A. Shafiq, N. Z. Jhanjhi, and A. Abdullah, “Load balancing techniques in cloud computing environment: A review,” J. King Saud Univ.–Comput. Inf. Sci., vol. 34, no. 8, pp. 3910–3933, 2021.
Dubey, A. K., & Dubey, A. (2026). Digitalization in Teaching and Learning: Impact on Student Engagement and Academic Achievement. ShodhAI: Journal of Artificial Intelligence, 3(1), 37–42. https://doi.org/10.29121/shodhai.v3.i1.2026.73
E. Gures, I. Shayea, and M. Ergen, “Machine learning-based load balancing algorithms in future heterogeneous networks: A survey,” IEEE Access, vol. 10, pp. 37689–37712, 2022.
E. Gures, I. Shayea, and M. Ergen, “Machine learning-based load balancing algorithms in future heterogeneous networks: A survey,” IEEE Access, vol. 10, pp. 37689–37712, 2022.
E. Puiutta and E. Veith, “Explainable reinforcement learning: A survey,” in Proc. ICML Workshop Explainable Artif. Intell., pp. 1–10, 2020.
E. Puiutta and E. Veith, “Explainable reinforcement learning: A survey,” in Proc. ICML Workshop Explainable Artif. Intell., pp. 1–10, 2020.
E. Puiutta and E. Veith, “Explainable reinforcement learning: A survey,” in Proc. ICML Workshop Explainable Artif. Intell., pp. 1–10, 2020.
E. Puiutta and E. Veith, “Explainable reinforcement learning: A survey,” in Proc. ICML Workshop Explainable Artif. Intell., pp. 1–10, 2020.
E. Strubell, A. Ganesh, and A. McCallum, “Energy and policy considerations for deep learning,” in Proc. 58th Annu. Meeting Assoc. Comput. Linguist. (ACL), pp. 3645–3650, 2020.
E. Strubell, A. Ganesh, and A. McCallum, “Energy and policy considerations for deep learning,” in Proc. 58th Annu. Meeting Assoc. Comput. Linguist. (ACL), pp. 3645–3650, 2020.
E. Strubell, A. Ganesh, and A. McCallum, “Energy and policy considerations for deep learning,” in Proc. 58th Annu. Meeting Assoc. Comput. Linguist. (ACL), pp. 3645–3650, 2020.
E. Strubell, A. Ganesh, and A. McCallum, “Energy and policy considerations for deep learning,” in Proc. 58th Annu. Meeting Assoc. Comput. Linguist. (ACL), pp. 3645–3650, 2020.
G. I. Parisi, R. Kemker, J. L. Part, C. Kanan, and S. Wermter, “Continual lifelong learning with neural networks: A review,” Neural Netw., vol. 113, pp. 54–71, 2019.
G. I. Parisi, R. Kemker, J. L. Part, C. Kanan, and S. Wermter, “Continual lifelong learning with neural networks: A review,” Neural Netw., vol. 113, pp. 54–71, 2019.
G. I. Parisi, R. Kemker, J. L. Part, C. Kanan, and S. Wermter, “Continual lifelong learning with neural networks: A review,” Neural Netw., vol. 113, pp. 54–71, 2019.
J. Muchori and P. Mwangi, “Machine learning load balancing techniques in cloud computing: A review,” Int. J. Comput. Appl. Technol. Res., vol. 11, no. 6, pp. 179–186, 2022.
J. Wu, L. Wang, and Y. Zhou, “Lightweight deep learning for edge–cloud orchestration,” Future Gener. Comput. Syst., vol. 144, pp. 547–562, 2023.
J. Wu, L. Wang, and Y. Zhou, “Lightweight deep learning for edge–cloud orchestration,” Future Gener. Comput. Syst., vol. 144, pp. 547–562, 2023.
J. Wu, L. Wang, and Y. Zhou, “Lightweight deep learning for edge–cloud orchestration,” Future Gener. Comput. Syst., vol. 144, pp. 547–562, 2023.
L. Huang, A. Joseph, B. Nelson, B. Rubinstein, and J. Tygar, “Adversarial machine learning,” in Proc. ACM Workshop Secur. Artif. Intell. (AISec), pp. 43–58, 2011.
L. Huang, A. Joseph, B. Nelson, B. Rubinstein, and J. Tygar, “Adversarial machine learning,” in Proc. ACM Workshop Secur. Artif. Intell. (AISec), pp. 43–58, 2011.
L. Huang, A. Joseph, B. Nelson, B. Rubinstein, and J. Tygar, “Adversarial machine learning,” in Proc. ACM Workshop Secur. Artif. Intell. (AISec), pp. 43–58, 2011.
L. Qian and Y. Zhao, “Federated learning for secure cloud resource optimization,” IEEE Trans. Cloud Comput., vol. 12, no. 3, pp. 423–435, 2024.
L. Qian and Y. Zhao, “Federated learning for secure cloud resource optimization,” IEEE Trans. Cloud Comput., vol. 12, no. 3, pp. 423–435, 2024.
L. Qian and Y. Zhao, “Federated learning for secure cloud resource optimization,” IEEE Trans. Cloud Comput., vol. 12, no. 3, pp. 423–435, 2024.
L. Qian and Y. Zhao, “Federated learning for secure cloud resource optimization,” IEEE Trans. Cloud Comput., vol. 12, no. 3, pp. 423–435, 2024.
M. Alam, S. Shah, and R. Ahmed, “Reliable edge intelligence for IoT and cloud systems,” IEEE Trans. Ind. Informat., vol. 19, no. 7, pp. 7212–7225, 2023.
M. Alam, S. Shah, and R. Ahmed, “Reliable edge intelligence for IoT and cloud systems,” IEEE Trans. Ind. Informat., vol. 19, no. 7, pp. 7212–7225, 2023.
M. Alam, S. Shah, and R. Ahmed, “Reliable edge intelligence for IoT and cloud systems,” IEEE Trans. Ind. Informat., vol. 19, no. 7, pp. 7212–7225, 2023.
M. Hossain, S. Rahman, and M. Karim, “Online learning for adaptive cloud workload management,” ACM Trans. Auton. Adapt. Syst., vol. 18, no. 2, pp. 1–24, 2023.
M. Hossain, S. Rahman, and M. Karim, “Online learning for adaptive cloud workload management,” ACM Trans. Auton. Adapt. Syst., vol. 18, no. 2, pp. 1–24, 2023.
M. Hossain, S. Rahman, and M. Karim, “Online learning for adaptive cloud workload management,” ACM Trans. Auton. Adapt. Syst., vol. 18, no. 2, pp. 1–24, 2023.
M. Hossain, S. Rahman, and M. Karim, “Online learning for adaptive cloud workload management,” ACM Trans. Auton. Adapt. Syst., vol. 18, no. 2, pp. 1–24, 2023.
M. T. Ribeiro, S. Singh, and C. Guestrin, “Why should I trust you? Explaining the predictions of any classifier,” in Proc. 22nd ACM SIGKDD Int. Conf. Knowl. Discovery Data Mining (KDD), pp. 1135–1144, 2016.
M. T. Ribeiro, S. Singh, and C. Guestrin, “Why should I trust you? Explaining the predictions of any classifier,” in Proc. 22nd ACM SIGKDD Int. Conf. Knowl. Discovery Data Mining (KDD), pp. 1135–1144, 2016.
M. T. Ribeiro, S. Singh, and C. Guestrin, “Why should I trust you? Explaining the predictions of any classifier,” in Proc. 22nd ACM SIGKDD Int. Conf. Knowl. Discovery Data Mining (KDD), pp. 1135–1144, 2016.
N. Kumar and R. Goyal, “Unsupervised learning for cloud workload grouping: An efficient load balancing strategy,” Cluster Comput., vol. 23, no. 4, pp. 2463–2480, 2020.
N. Kumar and R. Goyal, “Unsupervised learning for cloud workload grouping: An efficient load balancing strategy,” Cluster Comput., vol. 23, no. 4, pp. 2463–2480, 2020.
Q. Zhang, L. Cheng, and R. Boutaba, “Cloud computing: State-of-the-art and research challenges,” J. Internet Serv. Appl., vol. 1, no. 1, pp. 7–18, 2010.
R. Buyya, J. Broberg, and A. Goscinski, Cloud Computing: Principles and Paradigms. Hoboken, NJ, USA: Wiley, 2019.
R. Buyya, J. Broberg, and A. Goscinski, Cloud Computing: Principles and Paradigms. Hoboken, NJ, USA: Wiley, 2019.
R. Buyya, R. N. Calheiros, and A. V. Dastjerdi, “Intelligent cloud management: Research challenges and opportunities,” IEEE Cloud Comput. Mag., vol. 10, no. 1, pp. 8–19, 2023.
R. Buyya, R. N. Calheiros, and A. V. Dastjerdi, “Intelligent cloud management: Research challenges and opportunities,” IEEE Cloud Comput. Mag., vol. 10, no. 1, pp. 8–19, 2023.
R. Buyya, R. N. Calheiros, and A. V. Dastjerdi, “Intelligent cloud management: Research challenges and opportunities,” IEEE Cloud Comput. Mag., vol. 10, no. 1, pp. 8–19, 2023.
R. Mahmud, S. Srirama, and R. Buyya, “A benchmark framework for AI-driven cloud resource management,” IEEE Access, vol. 9, pp. 78467–78479, 2021.
R. Mahmud, S. Srirama, and R. Buyya, “A benchmark framework for AI-driven cloud resource management,” IEEE Access, vol. 9, pp. 78467–78479, 2021.
R. Mahmud, S. Srirama, and R. Buyya, “A benchmark framework for AI-driven cloud resource management,” IEEE Access, vol. 9, pp. 78467–78479, 2021.
R. Mahmud, S. Srirama, and R. Buyya, “A benchmark framework for AI-driven cloud resource management,” IEEE Access, vol. 9, pp. 78467–78479, 2021.
R. Mahmud, S. Srirama, and R. Buyya, “Cloud–fog–edge orchestration using artificial intelligence: Taxonomy and research challenges,” Future Gener. Comput. Syst., vol. 111, pp. 300–320, 2020.
R. Mahmud, S. Srirama, and R. Buyya, “Cloud–fog–edge orchestration using artificial intelligence: Taxonomy and research challenges,” Future Gener. Comput. Syst., vol. 111, pp. 300–320, 2020.
R. Mahmud, S. Srirama, and R. Buyya, “Cloud–fog–edge orchestration using artificial intelligence,” Future Gener. Comput. Syst., vol. 111, pp. 300–320, 2020.
R. S. Sutton and A. G. Barto, Reinforcement Learning: An Introduction, 2nd ed. Cambridge, MA, USA: MIT Press, 2018.
R. S. Sutton and A. G. Barto, Reinforcement Learning: An Introduction, 2nd ed. Cambridge, MA, USA: MIT Press, 2018.
S. M. Lundberg and S. I. Lee, “A unified approach to interpreting model predictions,” in Proc. Adv. Neural Inf. Process. Syst. (NeurIPS), pp. 4765–4774, 2017.
S. M. Lundberg and S. I. Lee, “A unified approach to interpreting model predictions,” in Proc. Adv. Neural Inf. Process. Syst. (NeurIPS), pp. 4765–4774, 2017.
S. M. Lundberg and S. I. Lee, “A unified approach to interpreting model predictions,” in Proc. Adv. Neural Inf. Process. Syst. (NeurIPS), pp. 4765–4774, 2017.
S. M. Lundberg and S. I. Lee, “A unified approach to interpreting model predictions,” in Proc. Adv. Neural Inf. Process. Syst. (NeurIPS), pp. 4765–4774, 2017.
S. Singh and I. Chana, “A survey on resource scheduling in cloud computing: Issues and challenges,” J. Grid Comput., vol. 14, no. 2, pp. 217–264, 2016.
S. Singh and I. Chana, “A survey on resource scheduling in cloud computing: Issues and challenges,” J. Grid Comput., vol. 14, no. 2, pp. 217–264, 2016.
S. Wachter, B. Mittelstadt, and C. Russell, “Counterfactual explanations without opening the black box: Automated decisions and the GDPR,” Harvard J. Law Technol., vol. 31, no. 2, pp. 841–887, 2018.
S. Wachter, B. Mittelstadt, and C. Russell, “Counterfactual explanations without opening the black box: Automated decisions and the GDPR,” Harvard J. Law Technol., vol. 31, no. 2, pp. 841–887, 2018.
S. Wachter, B. Mittelstadt, and C. Russell, “Counterfactual explanations without opening the black box: Automated decisions and the GDPR,” Harvard J. Law Technol., vol. 31, no. 2, pp. 841–887, 2018.
T. Alharbi, M. I. Khan, and A. Hussain, “Scalable machine learning-driven resource allocation in multi-cloud environments,” J. Cloud Comput., vol. 12, no. 4, pp. 331–352, 2023.
T. Alharbi, M. I. Khan, and A. Hussain, “Scalable machine learning-driven resource allocation in multi-cloud environments,” J. Cloud Comput., vol. 12, no. 4, pp. 331–352, 2023.
T. Alharbi, M. I. Khan, and A. Hussain, “Scalable machine learning-driven resource allocation in multi-cloud environments,” J. Cloud Comput., vol. 12, no. 4, pp. 331–352, 2023.
T. Alharbi, M. I. Khan, and A. Hussain, “Scalable machine learning-driven resource allocation in multi-cloud environments,” J. Cloud Comput., vol. 12, no. 4, pp. 331–352, 2023.
T. Miller, “Explanation in artificial intelligence: Insights from the social sciences,” Artif. Intell., vol. 267, pp. 1–38, 2019.
T. Miller, “Explanation in artificial intelligence: Insights from the social sciences,” Artif. Intell., vol. 267, pp. 1–38, 2019.
T. Miller, “Explanation in artificial intelligence: Insights from the social sciences,” Artif. Intell., vol. 267, pp. 1–38, 2019.
T. P. Lillicrap, J. J. Hunt, A. Pritzel, and N. Heess, “Continuous control with deep reinforcement learning,” in Proc. Int. Conf. Learn. Represent. (ICLR), 2016.
T. P. Lillicrap, J. J. Hunt, A. Pritzel, and N. Heess, “Continuous control with deep reinforcement learning,” in Proc. Int. Conf. Learn. Represent. (ICLR), 2016.
Y. Han, C. Park, and H. Kim, “Resource-aware deep learning for cloud scheduling and performance optimization,” IEEE Trans. Netw. Serv. Manage., vol. 19, no. 2, pp. 817–829, 2022.
Y. Han, C. Park, and H. Kim, “Resource-aware deep learning for cloud scheduling and performance optimization,” IEEE Trans. Netw. Serv. Manage., vol. 19, no. 2, pp. 817–829, 2022.
Y. Zhang, X. Li, and H. Chen, “Federated reinforcement learning for distributed cloud management,” IEEE Internet Things J., vol. 9, no. 16, pp. 14421–14434, 2022.
Y. Zhang, X. Li, and H. Chen, “Federated reinforcement learning for distributed cloud management,” IEEE Internet Things J., vol. 9, no. 16, pp. 14421–14434, 2022.
Z. Chen and S. Wu, “Benchmarking machine learning models for cloud scheduling: A systematic evaluation,” Future Gener. Comput. Syst., vol. 108, pp. 720–733, 2020.
Z. Chen and S. Wu, “Benchmarking machine learning models for cloud scheduling: A systematic evaluation,” Future Gener. Comput. Syst., vol. 108, pp. 720–733, 2020.
Z. Li, L. Chen, and H. Liu, “Deep learning-based resource prediction for cloud applications,” IEEE Access, vol. 9, pp. 145632–145649, 2021.
Z. Li, L. Chen, and H. Liu, “Deep learning-based resource prediction for cloud applications,” IEEE Access, vol. 9, pp. 145632–145649, 2021.
Z. Li, L. Chen, and H. Liu, “Deep learning-based resource prediction for cloud applications,” IEEE Access, vol. 9, pp. 145632–145649, 2021.
Z. Li, L. Chen, and H. Liu, “Deep learning-based resource prediction for cloud applications,” IEEE Access, vol. 9, pp. 145632–145649, 2021.
Z. Xiong, Y. Li, and F. Xu, “Blockchain for secure federated learning in cloud environments,” IEEE Trans. Services Comput., vol. 15, no. 5, pp. 2949–2961, 2022.
Z. Xiong, Y. Li, and F. Xu, “Blockchain for secure federated learning in cloud environments,” IEEE Trans. Services Comput., vol. 15, no. 5, pp. 2949–2961, 2022.
Z. Xiong, Y. Li, and F. Xu, “Blockchain for secure federated learning in cloud environments,” IEEE Trans. Services Comput., vol. 15, no. 5, pp. 2949–2961, 2022.
Z. Xiong, Y. Li, and F. Xu, “Blockchain for secure federated learning in cloud environments,” IEEE Trans. Services Comput., vol. 15, no. 5, pp. 2949–2961, 2022.
Zhou, Z., Abawajy, J., Chowdhury, M., Hu, Z., Li, K., Cheng, H., ... & Li, F. (2018). Minimizing SLA violation and power consumption in Cloud data centers using adaptive energy-aware algorithms. Future Generation Computer Systems, 86, 836-850.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Utkarsh Dubey, Wajahat GH Mohd, Sanjay Kumar Tuddu
This work is licensed under a Creative Commons Attribution 4.0 International License.
With the licence CC-BY, authors retain the copyright, allowing anyone to download, reuse, re-print, modify, distribute, and/or copy their contribution. The work must be properly attributed to its author.
It is not necessary to ask for further permission from the author or journal board.
This journal provides immediate open access to its content on the principle that making research freely available to the public supports a greater global exchange of knowledge.
