一种结合K-means均匀分簇和数据回归的WSN能量均衡策略

发布时间：2018-05-05 02:03

  本文选题：K-means算法 + 均匀分簇　； 参考：《小型微型计算机系统》2017年08期

【摘要】：针对LEACH协议簇头节点分布不均导致无线传感网节点能量消耗不均衡等不足,提出一种结合K-means均匀分簇和数据回归的能量均衡策略.采用优化初始簇中心K-means算法构建均匀分簇的分级无线传感网,通过获取节点地理位置信息,采用K-means聚类算法形成k个均匀分簇,再选举簇内节点剩余能量最多者当选簇头.该成簇算法可以使网络负载均匀,延长网络生存周期.通过优化初始簇中心的选择,降低K-means算法的迭代次数,使其更快收敛,成簇时间开销更少,簇与簇之间的地理分布也更均匀.在稳定数据传输阶段,采用数据回归的方法来减少普通节点与簇首的通信量,以达到降低功耗的作用.实验结果表明,该策略能够有效降低节点的功耗,延长网络的生存时间.
[Abstract]:An energy equalization strategy combining K-means uniform clustering and data regression is proposed to solve the problem that the uneven distribution of cluster heads in LEACH protocol leads to unbalanced energy consumption of wireless sensor network nodes. A hierarchical wireless sensor network with uniform clustering was constructed by optimizing the initial cluster center K-means algorithm. By obtaining the geographic location information of the nodes, the K-means clustering algorithm was used to form k uniform clusters, and then the cluster heads were elected if the most residual energy of the nodes in the cluster was the most abundant. The clustering algorithm can make the network load uniform and prolong the lifetime of the network. By optimizing the selection of initial cluster centers, the number of iterations of K-means algorithm is reduced to make it converge faster, the time cost of clustering is less, and the geographical distribution between clusters is more uniform. In the stage of stable data transmission, the method of data regression is used to reduce the communication between common nodes and cluster heads, so as to reduce the power consumption. Experimental results show that the proposed strategy can effectively reduce the power consumption and prolong the lifetime of the network.
【作者单位】： 江西师范大学计算机信息工程学院;
【基金】：国家自然科学基金项目(61462042,61650105)资助 江西省自然科学基金项目(20151BAB2017007)资助 江西省教育厅科研项目(GJJ13229)资助
【分类号】：TN929.5;TP212.9
，

本文编号：1845676