Balance Model of Resource Management and Customer Service Availability in Cloud Computing Platform
DOI:
https://doi.org/10.71222/xbgm8616Keywords:
cloud computing, resource management, service availabilityAbstract
In response to the real-time requirements of resource allocation and service availability dynamic balance in cloud service scheduling, this paper constructs an integrated Markov Decision Process (MDP) scheduling optimization model, comprehensively analyzes the impact of scheduling delay, load balancing efficiency, and virtual machine migration cost on service quality (SLA completion rate and average response time). At the same time, the XGBoost algorithm is used to further mine previous business data and improve the accuracy of business service availability prediction. The model was tested on scheduling and monitoring data for the fourth quarter of operation on a large public cloud platform. The results showed that within a 95% confidence interval, the prediction accuracy reached 93.7% and the resource utilization rate increased by 17.4%. The performance of this scheduling method was evaluated and validated in high concurrency scenarios, and it was found that it can effectively improve the system's availability and scheduling efficiency. This study provides theoretical and engineering practical basis for implementing an intelligent resource scheduling mechanism based on learning and modeling integration.
References
1. Z. Wang, J. Zhang, L. Li, H. Chen, M. Liu, X. Zhao, et al., “Computer vision system for multi-robot construction waste management: Integrating cloud and edge computing,” Build., vol. 14, no. 12, p. 3999, 2024, doi: 10.3390/buildings14123999.
2. V. Tabunshchik, A. Kerimov, I. Guliyev, F. Khalilov, R. Aliyev, M. Abdullayev, et al., “The dynamics of air pollution in the southwestern part of the Caspian Sea Basin (based on the analysis of Sentinel-5 satellite data utilizing the Google Earth En-gine cloud-computing platform),” Atmosphere, vol. 15, no. 11, p. 1371, 2024, doi: 10.3390/atmos15111371.
3. H. Jang and H. Koh, “A unified web cloud computing platform MiMedSurv for microbiome causal mediation analysis with survival responses,” Sci. Rep., vol. 14, no. 1, p. 20650, 2024, doi: 10.1038/s41598-024-71852-y.
4. Y. Jiang, X. Wang, Z. Liu, H. Li, J. Chen, M. Sun, et al., “Improvement of monitoring technology for corrosive pollution of marine environment under cloud computing platform,” Coatings, vol. 12, no. 7, p. 938, 2022, doi: 10.3390/coatings12070938.
5. A. Kumar and P. Sivakumar, “Cat-squirrel optimization algorithm for VM migration in a cloud computing platform,” Int. J. Semant. Web Inf. Syst., vol. 18, no. 1, pp. 1–23, 2022, doi: 10.4018/IJSWIS.297142.
