多维度视角下离散事件自动聚合方法研究

Research on automatic aggregation of discrete events from multi-dimensional perspective

为了提高多维度视角下离散事件的聚合调度质量,需要进行多维度视角离散事件的优化聚合调度处理,提出一种基于自适应均衡控制的多维度视角下离散事件大数据聚合算法。构建多维度视角下离散事件的大数据相空间分布结构模型,采用分段自适应融合分析方法对多维度视角下离散事件输出大数据进行均衡配置,构建模板特征匹配模型进行离散事件集成大数据的统计特征提取,对提取的多维度视角下离散事件特征分量采用模糊C均值聚合方法进行分类处理,构建自适应学习参数对聚合后的大数据进行线性规划和融合调度,实现多维度视角下离散事件的均衡聚合调度。仿真结果表明,采用该方法进行多维度视角下离散事件自动聚合的准确性较高,聚合数据输出的误差较低,提高了多维度视角下离散事件自动聚合质量。

In order to improve the aggregate scheduling quality of discrete events in multi-dimensional view,it is necessary to optimize aggregation scheduling of multi-dimensional discrete events.A multi-dimensional big data aggregation algorithm for discrete events from a multi-dimensional perspective based on adaptive equilibrium control is proposed.The big data phase space distribution structure model of discrete events in multi-dimensional view is constructed,and a piecewise adaptive fusion analysis method is used to allocate the discrete event output in a multi-dimensional perspective evenly.The template feature matching model is constructed to extract the statistical features of discrete event integration big data,and the feature components of discrete events are classified by fuzzy C-means aggregation method.Adaptive learning parameters are constructed to carry out linear programming and fusion scheduling for big data after aggregation to achieve balanced aggregation scheduling of discrete events in multi-dimensional perspective.The simulation results show that the accuracy of the method is higher and the error of aggregate data output is lower under multi-dimensional view angle,which improves the quality of automatic aggregation of discrete events in multi-dimensional view.