云环境中改进模糊聚类的资源聚合.pdfVIP

2013 年4 月 第30 卷第4 期 计算机仿真 文章编号:1∞6 -9348(2013)04 -0365-04 云环境中改进模糊聚类的资源聚合 王溢琴，秦振吉 (晋中学院计算机科学与技术学院，山西晋中的∞) 摘要:研究云中高性价比的资源聚合问题c 针对云中硬件资源聚合时没有考虑到资源的地理位置和运行成本，特别是传统 FCM 算法聚类时无法比较资源之间位置的关系，体现不出性价比。为解决上述问题，提出了一种改进模糊算法的资源聚合 策略。该策略首先定义描述资源位置关系的加权因子并构建新的目标函数;然后在资源属性矩阵中标准化数据，重复迭代 改进目标函数优化数据集的划分;最后定义了聚类集群综合性能评价指标，能从若干个子类中选取高性价资源池的目的。 仿真结果表明，改进算法和性能评价指标得到的聚类结果较好，适合云环境中资源性价比高的整合。 关键词:资源属性;加仅因子;目标函数;评价函数;集群综合性能 中图分类号:TP301 文献标识码:B Resources Polymerization ßased on Improved Fuzzy Clustering in Cloud Environment WANG Yi - qin ,QIN Zhen - ji 2 ( College of Computer Science and Technology , Jinzhong Univer词句， Jinzhung Shanxi 03侃∞， China) ABSTRACT:币le paper studied of cost - effective resources polymerization problem , and put forw町d a new 陀­ sources polymerization strategy based on improved fuzzy algorithm. FirsÙY. the strategy constructs a new objective function based on proposed weighted factor. Secondly , it standardizes data in the resource attribute matrÌx. An objec- tive function is iterated to optimize Ùle data set. Finally. it defines cluster comprehensive performance evaluation in- dex , which can select the high cost - effective pool from several subclasses. The experimental results show Ùlat it has a better clustering results according to the improved algorithm and 由e perfo口nance evaluation indexes , and c四 be applied to 11衍。urces integration wi Ùl high performance. KEY飞~ORDS: Resource property; Weighted factor; 0均ective function; Evaluation function; Cluster comprehensive performance