A Dynamic Resource Allocation Strategy for Cloud-Native Applications Leveraging Markov Properties
Keywords:
Cloud-native systems, resource allocation, Markov property, dynamic resource management, event-driven scalingAbstract
This study examines resource usage characteristics in cloud-native systems and develops a model for dynamically aligning resource allocations with application demands. Through feature analysis based on operational and monitoring data from stateless applications, we validate that time-series CPU utilization data adheres to Markovian properties. Building on this foundation, we propose a Markov-based resource allocation strategy that segments resource requirements into discrete states, enabling pre-allocation of resources tailored to each state. Additionally, an application infrastructure framework is designed to accommodate this strategy, categorizing information system services and facilitating the transmission of business workload data to the model's core. Within this framework, resource pre-allocation is abstracted into event-driven messages that dynamically manage resource scaling across service types. Finally, we validate the proposed model with data from a production system, providing insights into its efficacy through verification and analysis.
References
Mohamed A, Hamdan M, Khan S, et al. Software-defined networks for resource allocation in cloud computing: A survey[J]. Computer Networks, 2021, 195: 108151.
Yan J, Huang Y, Gupta A, et al. Energy-aware systems for real-time job scheduling in cloud data centers: A deep reinforcement learning approach[J]. Computers and Electrical Engineering, 2022, 99: 107688.
Goiri Í, Julia F, Ejarque J, et al. Introducing virtual execution environments for application lifecycle management and SLA-driven resource distribution within service providers[C]//2009 Eighth IEEE International Symposium on Network Computing and Applications. IEEE, 2009: 211-218.
Gmach D, Rolia J, Cherkasova L, et al. An integrated approach to resource pool management: Policies, efficiency and quality metrics[C]//2008 IEEE International Conference on Dependable Systems and Networks With FTCS and DCC (DSN). IEEE, 2008: 326-335.
Liu X, Buyya R. Resource management and scheduling in distributed stream processing systems: a taxonomy, review, and future directions[J]. ACM Computing Surveys (CSUR), 2020, 53(3): 1-41.
Wu Z, Liu X, Ni Z, et al. A market-oriented hierarchical scheduling strategy in cloud workflow systems[J]. The Journal of Supercomputing, 2013, 63: 256-293.
Weingärtner R, Bräscher G B, Westphall C B. Cloud resource management: A survey on forecasting and profiling models[J]. Journal of Network and Computer Applications, 2015, 47: 99-106.
Yu S D. Research on cloud computing in the key technologies of railway intelligent operation and maintenance sharing platform[C]//Journal of Physics: Conference Series. IOP Publishing, 2021, 1800(1): 012010.
Aiftimiei C, Costantini A, Bucchi R, et al. Cloud Environment Automation: from infrastructure deployment to application monitoring[C]//Journal of Physics: Conference Series. IOP Publishing, 2017, 898(8): 082016.
Zhang Q, Cheng L, Boutaba R. Cloud computing: state-of-the-art and research challenges[J]. Journal of internet services and applications, 2010, 1: 7-18.
Grebler L, Burns L S. Construction cycles in the United States since world war II[J]. Real Estate Economics, 1982, 10(2): 123-151.
Castro J, Kolp M, Mylopoulos J. Towards requirements-driven information systems engineering: the Tropos project[J]. Information systems, 2002, 27(6): 365-389.
