基于竞争神经网络的无线传感器网络非均匀分簇算法  

Uneven clustering algorithm for WSNs based on competitive neural networks

作　　者：吴子敬 WU Zi-jing(College of Computer and Control Engineering,Qiqihar University,Heilongjiang Qiqihar 161006,China)

机构地区：[1]齐齐哈尔大学计算机与控制工程学院,黑龙江齐齐哈尔161006

出　　处：《齐齐哈尔大学学报（自然科学版）》2023年第5期1-6,共6页Journal of Qiqihar University(Natural Science Edition)

摘　　要：为了解决现有无线传感器网络节点能耗不均问题,提出了一种基于竞争神经网络的无线传感器网络非均匀分簇算法。首先,在竞选簇头阶段,使用基于竞争神经网络模型从所有传感器节点中选取簇头,各节点将剩余能量、节点密度与基站的距离作为输入向量,竞选出使整个传感器网络负载均衡的簇头;然后,在节点成簇阶段,使用基于自组织映射神经网络模型划分簇群,完成网络的自组织节点入簇。仿真实验表明,该算法有效减少了节点能耗。In order to solve the problem of uneven node and energy consumption in existing wireless sensor networks,a uneven clustering algorithm based on competitive neural network was proposed.Firstly,in the stage of cluster head selection,cluster heads are selected from all sensor nodes based on the competitive neural network model.Each node takes the remaining energy,node density and distance from base station as input vector to elect cluster heads that can balance the load of the whole sensor network.Then,in the node clustering stage,the self-organizing mapping neural network model is used to divide the cluster and complete the self-organizing map clustering of the network.Simulation results show that this algorithm can effectively reduce the energy consumption of nodes.

关 键 词：无线传感器网络 竞争神经网络 非均匀分簇 

分 类 号：TP212.9[自动化与计算机技术—检测技术与自动化装置]