DCN-LB: A Deep Learning-Driven Cloud Load ‎BalancingFramework for Efficient Resource ‎Optimization

  • Authors

    • Damodhar M.‎ Research Scholar, Department of Computer Science and Engineering,‎ S V U College of Engineering, Tirupati, India
    • Ch. D V Subba Rao Professor, Department of Computer Science and Engineering,‎ S V U College of Engineering, Tirupati, India
    https://doi.org/10.14419/535sc283

    Received date: July 31, 2025

    Accepted date: September 18, 2025

    Published date: September 29, 2025

  • Cloud Computing; Load Balancing; Workload Prediction; Reinforcement Learning

  • Abstract

    Cloud computing is a technology that meets the needs of a vast number of users. Predicting ‎workload and scheduling are often the elements that determine cloud performance. This study ‎addresses the challenge of efficient load balancing in scalable cloud environments, where ‎traditional methods fail under dynamic workloads, leading to resource wastage and ‎performance degradation. To overcome this, an advanced framework integrating Deep ‎Learning (DL) and Reinforcement Learning (RL) is proposed. Simulation data on CPU usage, ‎memory, network traffic, and execution times are collected and preprocessed using mean ‎imputation and Min-Max normalization. A Sliding Window Approach with Multi-Scale ‎Convolutional Bidirectional LSTM (MS-Conv-BiLSTM) is used for time-series feature ‎extraction. An Attention-based LSTM forecasts workload levels, while a lightweight CNN ‎assists in task classification. Adaptive load balancing decisions are optimized using the Double Deep Q-Network (DDQN), aiming to reduce latency and response time while maximizing throughput and resource utilization. Experimental results confirm that the DL-RL framework ‎significantly enhances real-time load balancing performance in cloud environments‎.

  • References

    1. Asimiyu, “Revolutionizing enterprise application design: Integrating microservices with cloud computing for scalable solutions,” 2025.
    2. K. Kotteswari, R. K. Dhanaraj, B. Balusamy, A. Nayyar, and A. K. Sharma, “EELB: An energy-efficient load balancing model for cloud environ-ment using Markov decision process,” Computing, vol. 107, no. 3, pp. 1–41, 2025. https://doi.org/10.1007/s00607-025-01439-6.
    3. L. Krishnasamy, D. Vetriveeran, R. K. Sambandam, and J. Jenefa, “Efficient load balancing and resource allocation in networked sensing systems—An algorithmic study,” Networked Sensing Systems, pp. 145–171, 2025. https://doi.org/10.1002/9781394310890.ch6.
    4. N. Khaledian, S. Razzaghzadeh, Z. Haghbayan, and M. Völp, “Hybrid Markov chain-based dynamic scheduling to improve load balancing perfor-mance in fog-cloud environment,” Sustainable Computing: Informatics and Systems, vol. 45, pp. 101077, 2025. https://doi.org/10.1016/j.suscom.2024.101077.
    5. M. Ghorbani, N. Khaledian, and S. Moazzami, “ALBLA: An adaptive load balancing approach in edge-cloud networks utilizing learning automata,” Computing, vol. 107, no. 1, pp. 34, 2025. https://doi.org/10.1007/s00607-024-01380-0.
    6. M. Khatri, F. Ahmed, and M. Ahmed, “DAFLB: Dynamic adaptive fuzzy based load balancing with genetic optimization for enhanced cloud perfor-mance,” in Proc. 2025 17th Int. Conf. COMmunication Systems and NETworks (COMSNETS), pp. 381–388, Jan. 2025. https://doi.org/10.1109/COMSNETS63942.2025.10885645.
    7. S. R. Mokhtar Abouamasha, “Load balancing in mobile networks using deep reinforcement learning and traffic prediction,” 2025.
    8. Aditi, V. K. Prasad, V. C. Gerogiannis, A. Kanavos, D. Dansana, and B. Acharya, “Utilizing convolutional neural networks for resource allocation bottleneck analysis in cloud ecosystems,” Cluster Computing, vol. 28, no. 1, pp. 22, 2025. https://doi.org/10.1007/s10586-024-04720-z.
    9. S. O. Rasaq, “Resource optimization in hybrid cloud: Leveraging microservices for IoT workloads,” Int. J. Novel Res. Eng. Pharm. Sci., vol. 1, no. 1, 2025.
    10. A. K. Bayya, “Leveraging advanced cloud computing paradigms to revolutionize enterprise application infrastructure,” 2025. https://doi.org/10.56557/ajomcor/2025/v32i19067.
    11. M. El-Hajj, “Enhancing communication networks in the new era with artificial intelligence: Techniques, applications, and future directions,” Network, vol. 5, no. 1, pp. 1, 2025. https://doi.org/10.3390/network5010001.
    12. S. C. Pandey and V. K. P, “Adaptive AI-driven toll management: Enhancing traffic flow and sustainability through real-time prediction, allocation, and task optimization,” Future Transportation, vol. 5, no. 1, pp. 21, 2025. https://doi.org/10.3390/futuretransp5010021.
    13. D. Sahu, Nidhi, R. Chaturvedi, S. Prakash, T. Yang, R. S. Rathore, et al., “Revolutionizing load harmony in edge computing networks with probabil-istic cellular automata and Markov decision processes,” Scientific Reports, vol. 15, no. 1, pp. 3730, 2025. https://doi.org/10.1038/s41598-025-88197-9.
    14. D. Abbadi, “Cyber threats and risk mitigation strategies for cloud systems and the Internet of Things,” 2025. https://doi.org/10.20944/preprints202502.1366.v1.
    15. A. T. Xun, L. A. Z. En, L. T. Shen, A. N. Xin, W. H. Soon, W. Z. Jun, et al., “Building trust in cloud computing: Strategies for resilient security,” 2025. https://doi.org/10.20944/preprints202501.0716.v1.
    16. V. Hayyolalam and Ö. Özkasap, “CBWO: A novel multi-objective load balancing technique for cloud computing,” Future Generation Computer Sys-tems, vol. 164, pp. 107561, 2025. https://doi.org/10.1016/j.future.2024.107561
    17. M. Haris and S. Zubair, “Battle Royale deep reinforcement learning algorithm for effective load balancing in cloud computing,” Cluster Computing, vol. 28, no. 1, pp. 19, 2025. https://doi.org/10.1007/s10586-024-04718-7.
    18. S. K. Hegde, R. Hegde, C. N. Kumar, R. Meenakshi, R. Raman, and G. M. Jayaseelan, “Hybrid Adam_POA: Hybrid Adam_Pufferfish Optimization Algorithm based load balancing in cloud computing,” SN Computer Science, vol. 6, no. 2, pp. 178, 2025. https://doi.org/10.1007/s42979-024-03577-8.
    19. M. S. R. Krishna and D. K. Vali, “Meta-RHDC: Meta reinforcement learning driven hybrid Lyrebird Falcon optimization for dynamic load balancing in cloud computing,” IEEE Access, vol. 99, pp. 1–1, 2025. https://doi.org/10.1109/ACCESS.2025.3544775.
    20. J. Roselin and I. J. Insulata, “Decentralized dynamic load balancing for virtual machines in cloud computing: A blockchain-enabled system with state channel optimization,” J. Supercomput., vol. 81, no. 3, pp. 1–30, 2025. https://doi.org/10.1007/s11227-025-06922-7.
    21. S. T. Milan, N. J. Navimipour, H. L. Bavil, and S. Yalcin, “A QoS-based technique for load balancing in green cloud computing using an artificial bee colony algorithm,” J. Exp. Theor. Artif. Intell., vol. 37, no. 2, pp. 307–342, 2025. https://doi.org/10.1080/0952813X.2023.2188490.
    22. N. V. Kumar, S. Mohanty, and P. K. Pattnaik, “Hybrid algorithm for optimized clustering and load balancing using deep Q recurrent neural networks in cloud computing,” Bull. Electr. Eng. Inform., vol. 14, no. 2, pp. 1570–1578, 2025. https://doi.org/10.11591/eei.v14i2.9123.
    23. A. Alwhelat, O. A. Fadare, F. Al-Turjman, and L. Ibrahim, “Adaptive load balancing in cloud computing using deep deterministic policy gradient (DDPG): A reinforcement learning approach,” in Smart Infrastructures in the IoT Era, Cham: Springer Nature Switzerland, pp. 1067–1078, 2025. https://doi.org/10.1007/978-3-031-72509-8_87.
    24. M. S. Raja, “Dynamic load balancing mechanisms for scalable cloud computing architectures,” Int. J. Emerging Trends Comput. Sci. Inf. Technol., vol. 1, no. 1, pp. 44–51, 2025. https://doi.org/10.63282/3050-9246.IJETCSIT-V6I1P105.
    25. N. V. Naik and K. Madhavi, “AGOA: Adam gazelle optimisation algorithm for collaborative e-learning application in cloud computing with load bal-ancing,” Int. J. Wireless Mobile Comput., vol. 28, no. 1, pp. 20–33, 2025. https://doi.org/10.1504/IJWMC.2025.143036.
    26. R. C. Pereira, P. H. Abreu, P. P. Rodrigues, and M. A. Figueiredo, “Imputation of data missing not at random: Artificial generation and benchmark analysis,” Expert Syst. Appl., vol. 249, pp. 123654, 2024. https://doi.org/10.1016/j.eswa.2024.123654.
    27. M. Prasad and T. Srikanth, “Clustering accuracy improvement using modified min-max normalization,” 2024. https://doi.org/10.20944/preprints202411.0486.v1.
    28. Y. Luo, Y. He, Y. Li, H. Liu, J. Wang, and F. Gao, “A sliding window-based CNN-BiGRU approach for human skeletal pose estimation using mm wave radar,” Sensors, vol. 25, no. 4, pp. 1070, 2025. https://doi.org/10.3390/s25041070.
    29. X. Lu, P. Zhang, X. Zheng, R. Xiong, N. Zhang, and S. Li, “DQN-based automatic emergency collision avoidance control considering driver style,” Int. J. Automot. Technol., pp. 1–12, 2025. https://doi.org/10.1007/s12239-025-00224-w.
    30. R. Goyal, A. Nath, U. Niranjan, and R. Sharda, “Analyzing the performance of deep convolutional neural network models for weed identification in potato fields,” Crop Protection, vol. 188, pp. 107035, 2025. https://doi.org/10.1016/j.cropro.2024.107035.

  • Downloads

  • How to Cite

    M.‎ , D. ., & Rao, C. D. V. S. . (2025). DCN-LB: A Deep Learning-Driven Cloud Load ‎BalancingFramework for Efficient Resource ‎Optimization. International Journal of Basic and Applied Sciences, 14(5), 891-911. https://doi.org/10.14419/535sc283