【摘要】 针对传统大数据调度过程存在不稳定、耗时长、数据切换不流畅等问题,提出云平台安全监控大数据集群调度容错控制方法。构建阶梯式C/S云平台监控框架,采用3+1集成法中的CPU信号强度波动算法,对数据集群进行调度计算。对大数据集群中非线性切换系统稳定性分析,在闭环系统下实现数据切换,实现大数据集群调度容错控制。通过仿真证明,闭环系统环境下大数据之间可以进行稳定切换;大数据调度过程中波动幅值在一定范围之间,调度过程更稳定;较好实现更低耗时的大数据集群调度,实验结果说明研究方法具有更高的应用性能。更多还原

【Abstract】 In traditional big data scheduling process, instability, high time consumption and unsmooth data switching are main problems. Therefore, a fault tolerant control method for cloud platform security monitoring big data cluster scheduling is proposed. A stepped C/S cloud platform monitoring framework was built. The CPU signal intensity fluctuation algorithm in the 3+1 integration method was adopted to schedule and calculate the data cluster. The stability of nonlinear switching system in big data cluster was analyzed, and then the data switching under closed-loop system was achieved. Thus, the big data cluster scheduling fault tolerant control was completed. Simulation results show that the big data can be switched stably in the closed-loop system. In the process of big data scheduling, the fluctuation amplitude changes within a certain range, so the scheduling process is more stable. Thus, the big data cluster scheduling with lower consumption was realized well. Experimental results show that the proposed method has higher application performance.更多还原