2024 · 10 citations · 14 references
ComputingCloud ComputingComputer ScienceCloud ArchitectureCloud Performance OptimizationMachine LearningCloud Resource ManagementCompute Resource ManagementCost-performance TradeoffsResource ProvisioningResource SchedulingWorkload SchedulingCloud Resource Performance ModelingComparative Data AnalysisDynamic ScalingEnergy PerformanceEnergy-efficient Resource ManagementResource Utilization Optimization
The past decade has seen a marked increase in the utilization of cloud-based applications. As these applications become more integral to an organization's operations, optimizing their performance is becoming a critical issue. Recent advances in machine learning have made it possible to integrate this technology into dynamic scaling strategies for cloud-based applications. Machine learning algorithms can analyze data on system resources in real time, predicting resource demands and allowing the application to adjust its usage accordingly. Consequently, it is possible to improve energy performance and reduce costs. This paper investigates the role of machine learning in optimizing dynamic scaling strategies for cloud-based applications. A comparative analysis of different configurations is undertaken, in order to identify optimal settings for specific workloads. Evaluation methods and metrics are discussed, as well as practical considerations and open issues, such as the selection of the appropriate model and the evaluation of energy-aware strategies. Overall, this paper is expected to provide an essential review on the role of machine learning in optimizing dynamic scaling strategies for cloud-based applications, enhancing the efficiency, resilience and cost-effectiveness of such systems.
14
Cloud-Based Artificial Intelligence Framework for Battery Management System
Dapai Shi, Jingyuan Zhao, Chika Eze et al. · Energies · 2023 · 85 citations · Full text
Cloud-Based Deep Learning for Co-Estimation of Battery State of Charge and State of Health
Dapai Shi, Jingyuan Zhao, Zhenghong Wang et al. · Energies · 2023 · 58 citations · Full text