Enhancing Fault Tolerance in Cloud Computing using Modified Deep Q-Network (M-DQN) for Optimal Load Balancing
DOI:
https://doi.org/10.22399/ijcesen.601Keywords:
Cloud computing, Load balancing, Fault tolerance, DQNAbstract
Due to popularity of cloud computing approach, excessive cloud user can send their request to cloud server for accessing their requirements. Servers are handling these incoming requests and allocate required resources to fulfill user demands. But in real scenario the numbers of servers are limited. Therefore, some servers are heavily loaded and some servers are in idle mode. This can result in a major fault tolerance issue that reduces system performance. To overcome this issue, this study presented an effective scheduling mechanism known as Modified Deep Q-Network (M-DQN). In this process the data centre controller performs appropriate actions on the environment in order to select a suitable virtual machine (VM) capable of optimizing different load balancing parameters. To get the desired outcome, a simulation is run using Google Colab with the TensorFlow environment, demonstrating the usefulness of the proposed scheduling technique. The experiment revealed that our suggested approach has a higher reward rate, reduces makespan but increases resource utilization and throughput when compared to the existing DQN algorithm. Simulation findings demonstrate that the M-DQN method works better in decreasing around 16% execution time and 10% makespan time, while it increases 8% resource utilization and 4% throughput value. Overall, it increases 18% reward value as compare with I-DQN and DQN algorithm.
References
Pradhan, A., Bisoy, S. K., and Mallick, P. K. (2020). Load balancing in cloud computing: survey. In book: Innovation in Electrical Power Engineering, Communication, and Computing Technology, Lecture Notes in Electrical Engineering, springer, pp 99-111.
Rehman, A. U., Aguiar, R. L., Barraca, J. P. (2022). Fault-Tolerance in the Scope of Cloud Computing. IEEE Access, 10;63422-63441.
Pradhan, A., Bisoy, S. K., Das, A. (2022). A survey on PSO based meta-heuristic scheduling mechanism in cloud computing environment. Journal of King Saud University –Computer and Information Sciences, 34(8);4888-4901 https://doi.org/10.1016/j.jksuci.2021.01.003
Pattnaik, B. C., Sahoo, B. K., Pradhan, A., Mishra, S. R., Tripathy, H. S., Agasti, P. (2024). Fault Tolerance Enhancement Through Load Balancing Optimization in Cloud Computing. International Journal of Intelligent Systems and Applications in Engineering, 12(4), 172–180. https://doi.org/10.1016/j.jksuci.2018.01.003
Pradhan, A., Bisoy, S. K., Kautish, S., Jasser, M. B., Mohamed, A. W. (2022). Intelligent Decision-Making of Load Balancing Using Deep Reinforcement Learning and Parallel PSO in Cloud Environment. IEEE Access, 10;76939-76952.
Pradhan, A., Bisoy, S. K., and Sain, M. (2022). Action-Based Load Balancing Technique in Cloud Network Using Actor-Critic-Swarm Optimization, Wireless Communications and Mobile Computing, Wiley, Hindawi, 2022;6456242, pp 1-17.
Hatem, M. E., Rabie, A. R. (2019). Resource Scheduling for Offline Cloud Computing Using Deep Reinforcement Learning. International Journal of Computer Science and Network Security (IJCSNS), 19(4);54-60.
Tennakoon, D., Chowdhury, M., Luan, T. H. (2018). Cloud-based load balancing using double Q-learning for improved Quality of Service. Wireless Networks, https://doi.org/10.1007/s11276-018-1888-8.
Li, M., Zhang, J., Wan, J., Ren, Y., Zhou, L., Wu, B., Yang, R., Wang, j. (2019). Distributed machine learning load balancing strategy in cloud computing services. Wireless Networks. https://doi.org/10.1007/s11276-019-02042-2.
Noel, R. R., Mehra, R., Lama, P. (2019). Towards Self-Managing Cloud Storage with Reinforcement Learning. IEEE International Conference on Cloud Engineering (IC2E), pp 34-44.
Tassel, P.,Gebser, M.,Schekotihin, K. (2021). A Reinforcement Learning Environment for Job-Shop Scheduling.arXiv:2104.03760[cs. LG].
Lin, J., Cui, D., Peng, Z., Li, Q., He, J. (2020). A Two-Stage Framework for the Multi-User Multi-Data Center Job Scheduling and Resource Allocation. IEEE Access, 8;197863-74.
Che, H., Bai, Z., Zuo, R., Li, H. (2020). A Deep Reinforcement Learning Approach to the Optimization of Data Center Task Scheduling. Hindawi Complexity, Wiley, 2020;3046769, pp 1-12. https://doi.org/10.1155/2020/3046769
Dong, T., Xue, f., Xiao, C., Li, J. (2020). Task scheduling based on deep reinforcement learning in a cloud manufacturing environment. Concurrency and Computation: Practice and Experience. Wiley, pp 1-12.
Pradhan, A., and Bisoy, S. K. (2022). Intelligent Action Performed Load Balancing Decision Made in Cloud Data center Based on Improved DQN Algorithm. 2022 International Conference on Emerging Smart Computing and Informatics (ESCI), pp. 1-6.
Peng, Z., Lin, J., Cui, D., Li, Q., He, J. (2020). A multi-objective trade-off framework for cloud resource scheduling based on the Deep Q-network algorithm. Cluster Computing. https://doi.org/10.1007/s10586-019-03042-9.
Pradhan A., Bisoy, S. K. (2022). A novel load balancing technique for cloud computing platform based on PSO. Journal of King Saud University –Computer and Information Sciences, 34(7);3988-3995. https://doi.org/10.1016/j.jksuci.2020.10.016
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2024 International Journal of Computational and Experimental Science and Engineering
This work is licensed under a Creative Commons Attribution 4.0 International License.
