本文選題：K-means算法 + 均勻分簇　； 參考：《小型微型計算機系統(tǒng)》2017年08期

【摘要】：針對LEACH協(xié)議簇頭節(jié)點分布不均導致無線傳感網節(jié)點能量消耗不均衡等不足,提出一種結合K-means均勻分簇和數(shù)據回歸的能量均衡策略.采用優(yōu)化初始簇中心K-means算法構建均勻分簇的分級無線傳感網,通過獲取節(jié)點地理位置信息,采用K-means聚類算法形成k個均勻分簇,再選舉簇內節(jié)點剩余能量最多者當選簇頭.該成簇算法可以使網絡負載均勻,延長網絡生存周期.通過優(yōu)化初始簇中心的選擇,降低K-means算法的迭代次數(shù),使其更快收斂,成簇時間開銷更少,簇與簇之間的地理分布也更均勻.在穩(wěn)定數(shù)據傳輸階段,采用數(shù)據回歸的方法來減少普通節(jié)點與簇首的通信量,以達到降低功耗的作用.實驗結果表明,該策略能夠有效降低節(jié)點的功耗,延長網絡的生存時間.
[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.
【作者單位】： 江西師范大學計算機信息工程學院;
【基金】：國家自然科學基金項目(61462042,61650105)資助 江西省自然科學基金項目(20151BAB2017007)資助 江西省教育廳科研項目(GJJ13229)資助
【分類號】：TN929.5;TP212.9
，

本文編號：1845676