云存储中大数据优化粒子群聚类算法

Large data optimization particle swarm clustering algorithm based on cloud storage

对云存储系统中的大数据进行优化聚类设计,降低存储开销,提高数据管理和调度能力,传统方法中对云存储大数据聚类方法采用量子进化方法,当量子群个体存在非线性偏移时,数据聚类存在局部收敛,导致聚类准确度降低。提出一种基于优化粒子群算法的云存储中大数据优化聚类算法,进行了云存储大数据聚类的原理分析,在传统的模糊C均值聚类的基础上,采用粒子群聚类算法进行大数据聚类算法改进设计,把数据的分割转化为对空间的分割,得到云存储系统中海量数据的模糊聚类中心矢量,采用粒子群聚类方法对聚类数据的离散样本进行动态分配,得到数据聚类的信息素浓度,结合粒子群优化聚类的约束条件,求得云存储中大数据聚类的中心最优解。仿真结果表明,采用该算法进行云存储中大数据优化粒子群聚类,数据聚类的聚类准确度高,收敛性能较好,能在较短的迭代步数下计算得到最优解,在模式识别等领域展示了较好的应用价值。

The large data of cloud storage system is optimized for clustering design, reducing storage overhead, improving data management and scheduling ability. The traditional method uses quantum evolutionary algorithm to cluster large data clustering method. When the quantum group has a nonlinear shift, data clustering has local convergence, which leads to the decrease of clustering accuracy. A large data clustering algorithm based on particle swarm optimization is proposed, which is based on the traditional fuzzy C means clustering. The clustering algorithm is used to improve the design. The data is transformed into the spatial segmentation. The clustering algorithm is used to obtain the data concentration. The optimal solution is obtained. The simulation results show that this algorithm is used to optimize the particle swarm optimization in cloud storage. The clustering accuracy is high, and the convergence performance is better, and the optimal solution can be obtained in the short iterative step.