基于流动性感知机制的大数据资源稳定评估算法研究

Research on Big Data Resource Stability Evaluation Algorithm Based on Flow Awareness Mechanism

为了解决云计算条件下大数据资源评估效率低下、用户服务响应缓慢、稳定评估周期短等问题,提出一种基于流动性感知机制的大数据资源稳定评估算法。首先,考虑到大数据资源具有的高并发特性,设计了通过级别匹配的方式进行用户访问强度评估,过滤服务性能较低的用户访问请求,提升用户访问质量,缩短资源评估周期。然后,针对数据响应过程存在的服务资源受限问题,构建服务资源评估排序方案,划分用户服务级别,提高用户服务访问的适应性能。仿真实验结果显示:与当前大数据评估领域常用的遗传重构蜂群算法和大数据K-匿名微聚集算法相比,该算法能有效地缩短资源评估时间,提高评估过程中的计算收敛速度,单位用户服务能力卓越。

In order to solve the problems of low evaluation efficiency,slow response of user service and short period of stability evaluation in the big data resource evaluation scheme under the cloud computing condition,a big data resource stability evaluation algorithm based on mobile awareness mechanism is proposed.First of all,considering the high concurrency of big data resources,a level matching method is designed to evaluate user access intensity,filter user access requests with low service performance,improve user access quality and shorten resource evaluation cycle.Then,aiming at the problem of limited service resources in the process of data response,a service resource evaluation ranking scheme is constructed in this paper,to divide the service levels of users,and improve the adaptive performance of the algorithm for high-intensity user service access.The simulation results show that compared with the genetic artificial bee colony algorithm and the k-anonymous micro-aggregation in big data evaluation,the algorithm proposed in this paper can effectively shorten the time of resource evaluation,improve the convergence speed of calculation in the evaluation process,and provide excellent service capability for unit users.