复杂水系无线监测网络的智能分簇算法研究  

Research on Intelligent Clustering Algorithm for Complex Water Wireless Network Surveillance

作　　者：华翔[1,3] 梁洪涛 董兆鑫 王昭 姚红娟 李宝华 姜冰清 Hua Xiang;Liang Hongtao;Dong Zhaoxin;Wang Zhao;Yao Hongjuan;Li Baohua;Jiang Bingqing(College of Electronic Information Engineering,Xi‘an Technological University,Xi‘an 710021,China;College of Physics and Information Technology,Shaanxi Normal University,Xi‘an 710119,China;Northwest Institutes of Advanced Technology,Xi‘an Technological University,Xi‘an 710021,China)

机构地区：[1]西安工业大学电子信息工程学院,陕西西安710021 [2]陕西师范大学物理学与信息技术学院,陕西西安710119 [3]西安工业大学西北兵器工业研究院,陕西西安710021

出　　处：《系统仿真学报》2019年第11期2255-2263,共9页Journal of System Simulation

基　　金：陕西省2017年重点研发计划(2017GY-085);中央高校基本科研业务费项目(GK20193016)

摘　　要：非规则网络的分簇划分会产生负载不均,导致出现"能量热区"现象。在复杂水系无线网络监测背景下,针对非规则网络分簇划分的拓扑结构不均匀问题,提出一种基于遗传机理的智能分簇算法。建立了拓扑模型和能耗模型,设计了基于能耗最小原则的遗传聚类策略。给出了P矩阵编码方式,避免了数据计算的平方递增;构造了自适应遗传算子和模糊修正算子,提高了搜索的有向性。实验结果表明,该算法在网络分簇、能耗负载、生存时间等方面具有较好的性能。The clustering of irregular networks will cause load imbalance, which results in the phenomenon of "energy hot zone". Aiming at the unreasonable topology of irregular network clustering, an intelligent clustering algorithm based on genetic strategy is proposed for the wireless network surveillance of complex water system. An irregular complex water topology model and an energy consumption model are built, and a genetic clustering strategy is designed via the principle of minimum energy consumption. The P matrix coding method is given, which avoids the squared increment of data calculation. Simultaneously, an adaptive genetic operator and a fuzzy modified operator are established to improve the directionality of search. The experimental results show that the proposed algorithm has good performance in the network clustering, the energy consumption load and the lifetime.

关 键 词：非规则网络 智能分簇 复杂水系 遗传算法 拓扑控制 

分 类 号：TP393.1[自动化与计算机技术—计算机应用技术]