Adaptive Cloud Resource Allocation Using Attention-Driven Deep Reinforcement Learning

Pandi S. Prabha; A. Rengarajan

doi:10.48084/etasr.13443

Authors

Pandi S. Prabha Department of Computer Science and Information Technology (CSIT), Jain (Deemed to be University), Bengaluru, India
A. Rengarajan Department of Computer Science and Information Technology (CSIT), Jain (Deemed to be University), Bengaluru, India

Volume: 15 | Issue: 6 | Pages: 29334-29340 | December 2025 | https://doi.org/10.48084/etasr.13443

Received: 16 July 2025 | Revised: 28 August 2025 and 6 September 2025 | Accepted: 9 September 2025 | Online: 8 December 2025

Corresponding author: Pandi S. Prabha

Abstract

Efficient resource allocation remains a critical challenge in dynamic Cloud Computing (CC) environments, where maintaining Quality of Service (QoS), minimizing latency, and ensuring fairness are paramount. This study proposes a novel Deep Reinforcement Learning (DRL)-based framework that models resource allocation as a multi-agent Markov Decision Process (MDP), with each Virtual Machine (VM) link treated as an autonomous agent. Leveraging a Deep Q-Network (DQN) architecture enhanced by an attention mechanism, the framework enables agents to refine state observations and coordinate decisions adaptively. A custom reward function balancing throughput, latency, and resource cost guides the learning process, whereas experience replay and temporal annealing strategies promote optimal policy convergence. Experimental results demonstrate significant improvements in energy efficiency, execution time, waiting time, fairness, and throughput when benchmarked against existing Reinforcement Learning (RL)-based, Resource Management Framework–Deep Neural Network (RMF-DNN), and Federated Reinforcement Learning (F-RL) models. The proposed system introduces architectural innovations, including decentralized agent-based learning, attention-guided state refinement, and fairness-aware scheduling, establishing a scalable and intelligent solution for cloud resource management.

Keywords:

Cloud Computing (CC), resource allocation, Deep Reinforcement Learning (DRL), Deep Q-Network (DQN), multi-agent model

Downloads

Download data is not yet available.

References

M. V. Fard, A. Sahafi, A. M. Rahmani, and P. S. Mashhadi, "Resource allocation mechanisms in cloud computing: a systematic literature review," IET Software, vol. 14, no. 6, pp. 638–653, Dec. 2020. DOI: https://doi.org/10.1049/iet-sen.2019.0338

S. Malhotra, F. Yashu, M. Saqib, D. Mehta, J. Jangid, and S. Dixit, "Deep Reinforcement Learning for Dynamic Resource Allocation in Wireless Networks." arXiv, Mar. 13, 2025.

A. Mani, "Resource Allocation and Scheduling Techniques in Cloud Computing: A Comprehensive Review," International Journal For Multidisciplinary Research, vol. 7, no. 1, Feb. 2025, Art. no. IJFMR250138013. DOI: https://doi.org/10.36948/ijfmr.2025.v07i01.38013

M. C. Ho and S. Cho, "Deep Reinforcement Learning-Assisted Resource Allocation for Fluid Antenna System: Overview, Research Challenges and Future Trends," in 2025 International Conference on Artificial Intelligence in Information and Communication, Fukuoka, Japan, 2025, pp. 148–150.

T. Ma, Y. Chu, L. Zhao, and O. Ankhbayar, "Resource Allocation and Scheduling in Cloud Computing: Policy and Algorithm," IETE Technical Review, vol. 31, no. 1, pp. 4–16, Jan. 2014. DOI: https://doi.org/10.1080/02564602.2014.890837

A. Mahida, "A Comprehensive Review on Ethical Considerations in Cloud Computing-Privacy, Data Sovereignty and Compliance," Journal of Artificial Intelligence & Cloud Computing, vol. 1, no. 4, Dec. 2022, Art. no. SRC/JAICC-248. DOI: https://doi.org/10.47363/JAICC/2022(1)231

A. Kumar and W. Yeoh, "DECAF: Learning to be Fair in Multi-agent Resource Allocation," in Proceedings of the 24th International Conference on Autonomous Agents and Multiagent Systems, Detroit, MI, USA, 2025, pp. 2591–2593.

K. H. Ang et al., "Classification of Wafer Defects with Optimized Deep Learning Model," Proceedings of International Conference on Artificial Life and Robotics, vol. 28, pp. 609–614, Feb. 2023. DOI: https://doi.org/10.5954/ICAROB.2023.OS25-4

D. Lim and I. Joe, "MAARS: Multiagent Actor–Critic Approach for Resource Allocation and Network Slicing in Multiaccess Edge Computing," Sensors, vol. 24, no. 23, Dec. 2024, Art. no. 7760. DOI: https://doi.org/10.3390/s24237760

X. Wang, A. Li, and G. Han, "A Deep-Learning-Based Fault Diagnosis Method of Industrial Bearings Using Multi-Source Information," Applied Sciences, vol. 13, no. 2, Jan. 2023, Art. no. 933. DOI: https://doi.org/10.3390/app13020933

N. Khan, A. Abdallah, A. Celik, A. M. Eltawil, and S. Coleri, "Explainable AI-Aided Feature Selection and Model Reduction for DRL-Based V2X Resource Allocation," IEEE Transactions on Communications, vol. 73, no. 9, pp. 7633–7649, Sep. 2025. DOI: https://doi.org/10.1109/TCOMM.2025.3554655

G. K. Shyam and S. S. Manvi, "Resource allocation in cloud computing using agents," in 2015 IEEE International Advance Computing Conference, Banglore, India, 2015, pp. 458–463. DOI: https://doi.org/10.1109/IADCC.2015.7154750

J. J. Aloor, S. N. Nayak, S. Dolan, and H. Balakrishnan, "Cooperation and Fairness in Multi-Agent Reinforcement Learning," Journal on Autonomous Transportation Systems, vol. 2, no. 2, Dec. 2024, Art. no. 8. DOI: https://doi.org/10.1145/3702012

T. Thein, M. M. Myo, S. Parvin, and A. Gawanmeh, "Reinforcement learning based methodology for energy-efficient resource allocation in cloud data centers," Journal of King Saud University - Computer and Information Sciences, vol. 32, no. 10, pp. 1127–1139, Dec. 2020. DOI: https://doi.org/10.1016/j.jksuci.2018.11.005

X. Xiong, K. Zheng, L. Lei, and L. Hou, "Resource Allocation Based on Deep Reinforcement Learning in IoT Edge Computing," IEEE Journal on Selected Areas in Communications, vol. 38, no. 6, pp. 1133–1146, Jun. 2020. DOI: https://doi.org/10.1109/JSAC.2020.2986615

J. Bi, S. Li, H. Yuan, and M. Zhou, "Integrated deep learning method for workload and resource prediction in cloud systems," Neurocomputing, vol. 424, pp. 35–48, Feb. 2021. DOI: https://doi.org/10.1016/j.neucom.2020.11.011

S. B. Sangeetha, R. Sabitha, B. Dhiyanesh, G. Kiruthiga, N. Yuvaraj, and R. A. Raja, "Resource Management Framework Using Deep Neural Networks in Multi-Cloud Environment," in Operationalizing Multi-Cloud Environments: Technologies, Tools and Use Cases, R. Nagarajan, P. Raj, and R. Thirunavukarasu, Eds. Cham: Springer International Publishing, 2022, pp. 89–104. DOI: https://doi.org/10.1007/978-3-030-74402-1_5

B. Jeong, S. Baek, S. Park, J. Jeon, and Y.-S. Jeong, "Stable and efficient resource management using deep neural network on cloud computing," Neurocomputing, vol. 521, pp. 99–112, Feb. 2023. DOI: https://doi.org/10.1016/j.neucom.2022.11.089

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," Artificial Intelligence Review, vol. 57, no. 5, Apr. 2024, Art. no. 124. DOI: https://doi.org/10.1007/s10462-024-10756-9

P. K. Mishra and A. K. Chaturvedi, "An Improved Laxity based Cost Efficient Task Scheduling Approach for Cloud-Fog Environment," Engineering, Technology & Applied Science Research, vol. 15, no. 1, pp. 19037–19044, Feb. 2025. DOI: https://doi.org/10.48084/etasr.8595

E. Suganthi and F. K. M. Selvi, "Virtual Machine Load Balancing Model Framework for Cloud Computing," Engineering, Technology & Applied Science Research, vol. 15, no. 3, pp. 22553–22558, Jun. 2025. DOI: https://doi.org/10.48084/etasr.10556

K. G. S and M. Devi, "Optimized Resource Management and Security Enhancement in Fog Computing using Advanced Q-Learning Approaches," Engineering, Technology & Applied Science Research, vol. 15, no. 3, pp. 23965–23971, Jun. 2025. DOI: https://doi.org/10.48084/etasr.10995