Deep Learning-Enhanced Scheduling and Load Balancing in Multi-Tenant Computational Architectures
DOI:
https://doi.org/10.63282/3117-5481/AIJCST-V5I5P101Keywords:
Deep Learning, Scheduling, Load Balancing, Multi-Tenant Cloud, Reinforcement Learning, Resource Management, Edge Computing, Artificial IntelligenceAbstract
Multi-tenant computer architectures are the staple of the contemporary cloud computing, they provide the information of usage of multiple users and applications at the Deep Learning, Scheduling, Load Balancing, Multi-Tenant Cloud, Reinforcement Learning, Resource Management, Edge Computing, Artificial Intelligence. same time and can share resource optimally. Yet, with a much more heterogeneous workload, traditional, fixed-point scheduling and load balancing methods do not have the dynamism to support fairness, reduce latency, and maximize resource utilization. In this paper, a new Deep Learning-Improved Scheduling and Load Balancing Framework (DL-SLBF) is presented to address the multi-tenant and dynamic cloud infrastructure. The presented framework is based on deep reinforcement learning (DRL) combined with distributed load prediction and adaptive task migration approaches to find optimal task allocation in the network of computation nodes. This is in contrast to conventional heuristic-based approaches whereby, as opposed to the latter, DL-SLBF continuously applies workload properties, resource requirements, and tenant quality-of-service (QoS)-constrained policies. The model utilizes both a hybrid CNN-LSTM architecture to predict the workload requirements and a Dueling Deep Q-Network D-DQN to make the best decisions regarding scheduling decisions. Significant performance gains (27.4% throughput and 31.6% latency reduction and 22.3% fairness) are achieved through simulation experiments on a multi-tenant, Kubernetes-based, testbed utilizing classical load balancing (Round Robin (RR), Least Connection (LC), and Weighted Least Response (WLR)) load balancing algorithms. Moreover, the model has adaptive robustness in a scenario of sudden workload burst and equipment heterogeneity
References
[1] Shafiq, D. A., Jhanjhi, N. Z., Abdullah, A., & Alzain, M. A. (2022). Load balancing techniques in cloud computing environment. Journal of King Saud University – Computer and Information Sciences.
[2] Afzal, S. (2019). Load balancing in cloud computing – A hierarchical view. Journal of Cloud Computing.
[3] Kalra, M. (2015). A review of metaheuristic scheduling techniques in cloud and grid. Journal of Supercomputing.
[4] Houssein, E. H. (2021). Task Scheduling in Cloud Computing based on Meta-heuristic: A systematic review. Applied Soft Computing.
[5] Goodarzy, S., Nazari, M. (2020). Resource management in cloud computing using machine learning: A survey. IEEE/ICMLA 2020.
[6] Zhou, G., Tian, W., Buyya, R., Xue, R., & Song, L. (2021). Deep Reinforcement Learning – based Methods for Resource Scheduling in Cloud Computing: A Review and Future Directions. arXiv.
[7] Performance modeling of load balancing algorithms using neural networks – I. Ahmad, A. Ghafoor, K. Mehrotra, C. K. Mohan & S. Ranka, 1994.
[8] Ji Xiang Yang, Guo Zhen Tan, Fan Wang & Mei Na Zhou, “A Load Balancing Strategy for Large Scale Distributed Computing”, Acta Electronica Sinica, 2012, Vol 40(11), pp 2226 2231.
[9] T. M. Willems & J. E. Rooda, “Neural networks for job shop scheduling”, Control Engineering Practice, Vol 2, Issue 1, pp 31 39 (1994).
[10] DL2: A Deep Learning driven Scheduler for Deep Learning Clusters — Peng, Y., Bao, Y., Chen, Y., Wu, C., Meng, C., & Lin, W. (2019). ArXiv preprint, Sept 13 2019.
[11] Enabling Mission-Critical Communication via VoLTE for Public Safety Networks - Varinder Kumar Sharma - IJAIDR Volume 10, Issue 1, January-June 2019. DOI 10.71097/IJAIDR.v10.i1.1539
[12] Load Balancing Optimization Based on Deep Learning Approach in Cloud Environment — Kaur, A., Kaur, B., Singh, P., Devgan, M. S., & Toor, H. K. (2020). International Journal of Information Technology & Computer Science (IJITCS), Vol 12, No 3, June 8, 2020.
[13] Zhou, G., Tian, W., Buyya, R., Xue, R., & Song, L. (2021). Deep Reinforcement Learning based Methods for Resource Scheduling in Cloud Computing: A Review and Future Directions.
[14] Thallam, N. S. T. (2020). Comparative Analysis of Data Warehousing Solutions: AWS Redshift vs. Snowflake vs. Google BigQuery. European Journal of Advances in Engineering and Technology, 7(12), 133-141.
[15] The Role of Zero-Emission Telecom Infrastructure in Sustainable Network Modernization - Varinder Kumar Sharma - IJFMR Volume 2, Issue 5, September-October 2020. https://doi.org/10.36948/ijfmr.2020.v02i05.54991
[16] Thallam, N. S. T. (2021). Performance Optimization in Big Data Pipelines: Tuning EMR, Redshift, and Glue for Maximum Efficiency.
[17] Reinforcement Learning Applications in Self Organizing Networks - Varinder Kumar Sharma - IJIRCT Volume 7 Issue 1, January-2021. DOI: https://doi.org/10.5281/zenodo.17062920
[18] Kulasekhara Reddy Kotte. 2022. ACCOUNTS PAYABLE AND SUPPLIER RELATIONSHIPS: OPTIMIZING PAYMENT CYCLES TO ENHANCE VENDOR PARTNERSHIPS. International Journal of Advances in Engineering Research , 24(6), PP – 14-24, https://www.ijaer.com/admin/upload/02%20Kulasekhara%20Reddy%20Kotte%2001468.pdf
[19] Krishna Chaitanaya Chittoor, “ANOMALY DETECTION IN MEDICAL BILLING USING MACHINE LEARNING ON BIG DATA PIPELINES”, INTERNATIONAL JOURNAL OF CURRENT SCIENCE, 12(3), PP-788-796,2022, https://rjpn.org/ijcspub/papers/IJCSP22C1314.pdf
[20] Garg, A. (2022). Unified Framework of Blockchain and AI for Business Intelligence in Modern Banking . International Journal of Emerging Research in Engineering and Technology, 3(4), 32-42. https://doi.org/10.63282/3050-922X.IJERET-V3I4P105
[21] Thallam, N. S. T. (2022). Sustainable Cloud Computing: Reducing Carbon Footprint in Large-Scale Cloud Infrastructures. Journal of Scientific and Engineering Research, 9(1), 217-224.
[22] Kanji, R. K. (2022). Generative Query Optimization in Data Warehousing: A Foundation Model-Based Approach for Autonomous SQL Generation and Execution Optimization in Hybrid Architectures. Available at SSRN 5401216.
[23] Varinder Kumar Sharma - AI-Based Anomaly Detection for 5G Core and RAN Components - International Journal of Scientific Research in Engineering and Management (IJSREM) Volume: 06 Issue: 01 | Jan-2022 .DOI: 10.55041/IJSREM11453
[24] Gopi Chand Vegineni. 2022. Intelligent UI Designs for State Government Applications: Fostering Inclusion without AI and ML, Journal of Advances in Developmental Research, 13(1), PP – 1-13, https://www.ijaidr.com/research-paper.php?id=1454
