Cloud computing has become an essential technology for providing scalable, on-demand services. Cloud computing is a way to use computing resources (like servers, storage, databases, software, and networking) over the internet on demand, instead of buying and managing everything yourself. Cloud computing means you use computers (servers) that belong to a company and are located somewhere else (in a data center). However, appropriate resource allocation remains a significant difficulty. Traditional techniques frequently fail to handle the dynamic and complicated nature of multi-cloud settings, resulting in poor performance and higher costs. This paper presents a new technique based on reinforcement learning and using Q- learning to optimize resources allocation. To optimize resource allocation by achieving three primary goals: reduced makespan, reduced operating costs, and promising load balance among virtual machines. Evaluations were conducted using the Cloud SIM simulator and real-world traces from a dataset. The findings show that the method significantly improve resource usage, enhances load balancing by up to 12%, and increases make span stability as virtual machines grow. It is noteworthy that cost remains independent of virtual machine scalability, demonstrating the model's effectiveness in resource management without incurring extra costs.
Keywords
Cloud ComputingResource AllocationReinforcement Learning Q-learningMakespanLoad Balancing and Cost Optimization.
References
G. Zhou, W. Tian, R. Buyya, R. Xue, and L. Song, “Deep reinforcement learning-based methods for resource scheduling in cloud computing: A review and future directions,” arXiv preprint arXiv:2105.04086, 2021, doi: 10.48550/arXiv.2105.04086.
S. K. Pradhan, S. K. Bisoy, S. Kautish, M. B. Jasser, and A. W. Mohamed, “Intelligent decision-making of load balancing using deep reinforcement learning and parallel PSO in cloud environment,” IEEE Access, vol. 10, pp. 76939-76952, 2022.
D. R. Abdulrazzaq, N. M. Shati, and H. K. Hoomod, “Bi-objective task scheduling based on heuristic initialization of the jellyfish search algorithm in cloud computing,” in Proc. 3rd Int. Sci. Conf. Eng. Sci. (ISCES), 2023, pp. 25-30.
P. S. Prabha and A. Rengarajan, “Adaptive cloud resource allocation using attention-driven deep reinforcement learning,” Eng. Technol. Appl. Sci. Res., vol. 15, no. 2, 2025.
H. Hallawi, “Development a framework for validating multi-capacity cloud resource allocation based on SimGrid,” in AIP Conf. Proc., vol. 2144, no. 1, p. 050012, 2019.
S. A. Jabber, S. H. Hashem, and S. H. Jafer, “Task scheduling and resource allocation in cloud computing: A review and analysis,” in Proc. 3rd Int. Conf. Emerg. Smart Technol. Appl. (eSmarTA), 2023, pp. 1-8.
H. Mao, M. Alizadeh, S. Shakkottai, and R. Katz, “Resource management with deep reinforcement learning,” in Proc. 15th ACM Workshop, 2016, doi: 10.1145/3005745.3005750.
S. M. Rozehkhani, F. Mahan, and W. Pedrycz, “Efficient cloud data center: An adaptive framework for dynamic virtual machine consolidation,” J. Netw. Comput. Appl., vol. 226, p. 103885, 2024.
L. Abualigah, A. M. Hussein, M. H. Almomani, R. A. Zitar, H. Migdady, A. I. Alzahrani, and A. Alwadain, “Improved synergistic swarm optimization algorithm to optimize task scheduling problems in cloud computing,” Sustain. Comput. Inform. Syst., vol. 43, p. 101012, 2024.
R. Khan, “Dynamic load balancing in cloud computing: Optimized RL-based clustering with multi-objective optimized task scheduling,” Processes, vol. 12, no. 3, p. 519, 2024.
R. Buyya and A. V. Dastjerdi, Cloud Computing: Principles and Paradigms, John Wiley & Sons, 2024.
Z. Xu, Y. Wang, J. Tang, J. Wang, and M. C. Gursoy, “A deep reinforcement learning based framework for power-efficient resource allocation in cloud RANs,” in Proc. IEEE Int. Conf. Commun. (ICC), 2017, pp. 1-6.
X. Chen, F. Zhu, Z. Chen, G. Min, X. Zheng, and C. Rong, “Resource allocation for cloud-based software services using prediction-enabled feedback control with reinforcement learning,” IEEE Trans. Cloud Comput., vol. 10, no. 2, pp. 1117-1129, 2020.
Muthusamy and R. K. Dhanaraj, “Dynamic Q-learning-based optimized load balancing technique in cloud,” Mob. Inf. Syst., vol. 2023, p. 7250267, 2023.
S. Belgacem, S. Mahmoudi, and M. Kihl, “Intelligent multi-agent reinforcement learning model for resources allocation in cloud computing,” J. King Saud Univ. Comput. Inf. Sci., vol. 34, no. 6, pp. 2391-2404, 2022.
Kruekaew and W. Kimpan, “Multi-objective task scheduling optimization for load balancing in cloud computing environment using hybrid artificial bee colony algorithm with reinforcement learning,” IEEE Access, vol. 10, pp. 17803-17818, 2022.
R. Panwar and M. Supriya, “RLPRAF: Reinforcement learning-based proactive resource allocation framework for resource provisioning in cloud environment,” IEEE Access, vol. 12, pp. 95986-96007, 2024.
T. Thein, M. M. Myo, S. Parvin, and A. Gawanmeh, “Reinforcement learning based methodology for energy-efficient resource allocation in cloud data centers,” J. King Saud Univ. Comput. Inf. Sci., vol. 32, no. 10, pp. 1127-1139, 2020.
F. Varghese, Dynamic Resource Allocation in Multi-Cloud Environments Using Reinforcement Learning, Ph.D. dissertation, National College of Ireland, Dublin, Ireland, 2025.
M. Arvindhan and D. R. Kumar, “Adaptive resource allocation in cloud data centers using actor-critical deep reinforcement learning for optimized load balancing,” Int. J. Recent Innov. Trends Comput. Commun., vol. 11, no. 5s, pp. 310-318, 2023.
J. Xu, Z. Xu, and B. Shi, “Deep reinforcement learning based resource allocation strategy in cloud-edge computing system,” Front. Bioeng. Biotechnol., vol. 10, p. 908056, 2022.
