基于聚合度热点收敛映射机制的云计算人工智能数据筛选算法

Cloud Computing Artificial Intelligence Data Filtering Algorithm Based on Aggregation Degree Hotspot Convergence Mapping Mechanism

考虑到当前云计算智能数据筛选算法具有资源处理效率不高、用户满足度低、数据收敛效果不理想等问题,设计了一种基于聚合度热点收敛映射机制的云计算人工智能数据筛选算法。首先,基于供给侧—需求侧匹配模型,提出了一种基于资源匹配最大化的数据处理方案,显著提高云处理中心在并行计算上存在的效率。随后,通过设计聚焦成本、时间片及用户可靠度等三个调度参数,并结合拉格朗日优化方法,实现对聚焦成本、时间片、用户可靠度等最优调度,改善数据筛选性能。仿真实验表明,与当前常用的超欧里几何数据筛选算法(Ultra-Eulerian Geometric Data Screening Algorithms,UEG算法)、时间片累积调度筛选算法(Time Slice Cumulative Scheduling Filtering Algorithm,TSC-SF算法)相比,本文算法具有并发调度业务数多、数据筛选带宽高等特点,具有很强的实际部署价值。

Considering that the current cloud computing intelligent data screening algorithm has the problems of low resource processing efficiency,low user satisfaction and unsatisfactory data convergence effect,a cloud computing artificial intelligent data screening algorithm based on aggregation degree hotspot convergence mapping mechanism is designed.Firstly,based on the supply-side and demand-side matching model,a data processing scheme based on resource matching maximization is proposed,which significantly improves the efficiency of cloud processing center in parallel computing.Then,by designing three scheduling parameters,namely,focusing cost,time slice,and user reliability,and combining Lagrange optimization method,the optimal scheduling of focusing cost,time slice,and user reliability is realized,and the data screening performance is improved.Simulation results show that,compared with the currently commonly used ultra-Eulerian Geometric Data Screening Algorithms(UEG algorithm)and Time Slice Cumulative Scheduling Filtering Algorithms(TSC-SF algorithm),the algorithm in this paper has the characteristics of more concurrent scheduling services,higher data screening bandwidth,and is of great practical deployment value.