Machine Learning-Based Resource Allocation for Scalable Cloud REST Services
DOI:
https://doi.org/10.63345/wjftcse.v1.i3.101Keywords:
Machine Learning, Cloud Computing, Resource Allocation, REST Services, Predictive Scaling, Cloud Infrastructure Optimization, Reinforcement Learning, API Performance OptimizationAbstract
Cloud computing environments today have an extensive range of distributed applications, which are dependent on the use of RESTful web services. These services are required to accommodate millions of simultaneous calls, as well as be highly performance, availability, and scalable. Conventional resource distribution systems of a cloud system are usually based on fixed policies or threshold-based auto-scaling strategies. Although these approaches offer a minimum scaleability, they are usually not efficient at managing unpredictable workloads and dynamic workloads typical in modern cloud systems. Consequently, the resources can be either underutilized or over-provisioned resulting in higher operational costs and poor performance of the system.
Machine learning (ML) can be an effective solution to the problem of cloud resource allocation optimization in scalable REST services. ML models can predict resource utilization in the future by examining past workload data and determine intricate trends in traffic behavior to doom and refer moving computing resources like CPU, memory, and network bandwidth. This predictability enables cloud systems to make proactive resource allocation prior to the deterioration of performance.
This paper presents an intelligent resource allocation framework on scalable cloud resource REST architecture based on machine learning algorithms. The framework combines predictive modeling of workload, resource scheduling by reinforcements of learning and real-time performance monitor. The system predicts the patterns of demand of the API using regression models and neural networks, which are supervised learning techniques. An agent of reinforcement learning then identifies ideal policies of resource allocation to achieve balance between system performance, latency and cost-efficiency.
Experimental assessment shows that response time, system throughput and infrastructure usage is improved significantly as compared to the conventional rule based scaling mechanisms. The suggested system is more efficient in resources utilization and minimizes system failure and overhead. These findings reveal the possibility of machine learning based resource management in the next generation cloud based infrastructure as well as the high performance REST service ecologies.
Downloads
References
• Lorido-Botran, T., Miguel-Alonso, J., & Lozano, J. A. (2014).
A review of auto-scaling techniques for elastic applications in cloud environments.
Journal of Grid Computing, 12(4), 559–592.
https://doi.org/10.1007/s10723-014-9314-7
• Mao, M., Li, J., & Humphrey, M. (2016).
Cloud auto-scaling with deadline and budget constraints.
Proceedings of the 11th International Conference on Autonomic Computing (ICAC).
https://doi.org/10.1109/ICAC.2016.30
• Gandhi, A., Harchol-Balter, M., Das, R., & Lefurgy, C. (2012).
Optimal power allocation in server farms.
SIGMETRICS Performance Evaluation Review, 40(1), 157–168.
https://doi.org/10.1145/2318857.2254782
• Xu, J., & Fortes, J. A. B. (2010).
Multi-objective virtual machine placement in virtualized data center environments.
Proceedings of the IEEE/ACM International Conference on Green Computing.
https://doi.org/10.1109/GREENCOMP.2010.5598296
• Ghani, N., Ghani, N., & Rehman, A. (2020).
Machine learning approaches for resource management in cloud computing: A review.
IEEE Access, 8, 111574–111599 .
https://doi.org/10.1109/ACCESS.2020.3002369
• Chen, X., Zhang, Y., Chen, Y., & Li, Z. (2018).
Reinforcement learning-based resource management in cloud computing.
Future Generation Computer Systems, 79, 203–212.
https://doi.org/10.1016/j.future.2017.09.030
• Islam, S., Keung, J., Lee, K., & Liu, A. (2012).
Empirical prediction models for adaptive resource provisioning in the cloud.
Future Generation Computer Systems, 28(1), 155–162.
https://doi.org/10.1016/j.future.2011.05.027
• Roy, N., Dubey, A., & Gokhale, A. (2011).
Efficient autoscaling in the cloud using predictive models for workload forecasting.
Proceedings of IEEE International Conference on Cloud Computing.
https://doi.org/10.1109/CLOUD.2011.42
• Beloglazov, A., & Buyya, R. (2012).
Optimal online deterministic algorithms and adaptive heuristics for energy-efficient dynamic consolidation of virtual machines in cloud data centers.
Concurrency and Computation: Practice and Experience, 24(13), 1397–1420.
https://doi.org/10.1002/cpe.1867
• Calheiros, R. N., Ranjan, R., Beloglazov, A., De Rose, C. A., & Buyya, R. (2011).
CloudSim: A toolkit for modeling and simulation of cloud computing environments.
Software: Practice and Experience, 41(1), 23–50.
https://doi.org/10.1002/spe.995
• Zhang, Q., Chen, M., Li, L., & Wu, Z. (2018).
Deep reinforcement learning for cloud resource allocation.
IEEE Transactions on Network and Service Management, 15(4), 1270–1283.
https://doi.org/10.1109/TNSM.2018.2873868
• Xu, Q., Zhang, Q., & Li, M. (2019).
Dynamic resource allocation for cloud computing using machine learning techniques.
Future Generation Computer Systems, 95, 510–518.
https://doi.org/10.1016/j.future.2019.01.018
• Li, K., Xu, G., Zhao, G., Dong, Y., & Wang, D. (2011).
Cloud task scheduling based on load balancing ant colony optimization.
Proceedings of the IEEE Sixth Annual ChinaGrid Conference.
https://doi.org/10.1109/ChinaGrid.2011.34
• Zhang, Y., Chen, X., & Li, Z. (2019).
Intelligent resource allocation in cloud computing using deep learning techniques.
IEEE Access, 7, 107931–107941.
https://doi.org/10.1109/ACCESS.2019.2933422
• Gandhi, A., Gupta, V., Harchol-Balter, M., & Kozuch, M. (2012).
Optimality analysis of energy-performance trade-off for server farm management.
Performance Evaluation, 67(11), 1155–1171.
https://doi.org/10.1016/j.peva.2010.08.004
• Mao, H., Alizadeh, M., Menache, I., & Kandula, S. (2016).
Resource management with deep reinforcement learning.
Proceedings of the 15th ACM Workshop on Hot Topics in Networks (HotNets).
https://doi.org/10.1145/3005745.3005750
• Jennings, B., & Stadler, R. (2015).
Resource management in clouds: Survey and research challenges.
Journal of Network and Systems Management, 23(3), 567–619.
https://doi.org/10.1007/s10922-014-9307-7
• Klein, C., Maggio, M., Årzén, K., & Hernandez-Rodriguez, F. (2014).
Brownout: Building more robust cloud applications.
Proceedings of the 36th International Conference on Software Engineering (ICSE).
https://doi.org/10.1145/2568225.2568227
• Lorido-Botran, T., Miguel-Alonso, J., & Lozano, J. A. (2012).
A review of auto-scaling techniques for elastic applications in cloud environments.
Department of Computer Architecture and Technology, University of the Basque Country Technical Report.
• Google Cloud Architecture Center (2022).
Autoscaling and resource management best practices for cloud services.
Downloads
Additional Files
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.