面向农业观光服务的无线传感网节点布局优化  

Node layout optimization of wireless sensor network for agricultural sightseeing service

作　　者：杨义[1] 张静文 万雪芬 郑涛[4] 崔剑[5] Sardar Muhammad Sohail YANG Yi;ZHANG Jing-wen;WAN Xue-fen;ZHENG Tao;CUI Jian;Sardar Muhammad Sohail(College of Information Science and Technology,Donghua University,Shanghai 201620,China;College of Computer,North China Institute of Science and Technology,Langfang,Hebei 065201,China;Hebei IoT Monitoring Engineering Technology Research Center,North China Institute of Science and Technology,Langfang,Hebei 065201,China;School of Economics and Management,Yanshan University,Qinhuangdao,Hebei 066004,China;Engineering Training Center,Beijing University of Aeronautics and Astronautics,Beijing 100083,China)

机构地区：[1]东华大学信息科学与技术学院,上海201620 [2]华北科技学院计算机学院,河北廊坊065201 [3]华北科技学院河北省物联网监控工程技术研究中心,河北廊坊065201 [4]燕山大学经济管理学院,河北秦皇岛066004 [5]北京航空航天大学工程训练中心,北京100083

出　　处：《南方农业学报》2018年第8期1674-1682,共9页Journal of Southern Agriculture

基　　金：国家自然科学基金项目(71371046);廊坊市科学技术研究与发展计划项目(2016011034);河北省物联网监控工程技术研究中心项目(3142018055);河北省社会科学发展研究课题区域经济联合基金项目(201705020209)

摘　　要：【目的】探讨面向农业观光园区分布式服务的无线传感器网络节点布局优化方案,为提高农业观光园区服务质量及提升游客游园体验提供依据。【方法】利用社会力模型结合观光园区规划信息,采用Anylogic行人仿真平台获取游客在园中的空间分布数据,用传统K-means算法和改进K-means算法分别对游客空间分布数据进行聚类分析,并根据节点优化布局评价指标,计算节点最优位置。【结果】采用传统K-means算法和改进K-means算法对选取的12组游客空间分布数据进行单日游客聚类分析得到两组节点位置;改进K-means算法聚类得到的节点最终位置对节点被接入次数的均衡效果均优于传统K-means算法,其节点被接入次数均方差的均值降低约41.8%。因此,改进K-means算法更适合运用于观光园区节点的布局优化,得到的节点最终位置即为该观光园区节点最优位置。【建议】在面向农业观光服务的混合型无线传感器网络建设中,应基于社会力模型预估游客空间分布,实现观光服务优化;通过合理部署节点位置,延长融合智能设备的混合型无线传感器网络生存时间;更好地打造面向游客服务、整合移动智能设备的农业物联网系统。【Objective】In order to improve the service quality of the agricultural sightseeing garden and enhance the tourists experience,this study proposed a node layout optimization scheme for wireless sensor network targeting agricultural sightseeing gardens.【Method】Firstly,the spatial distribution data of tourists in the garden was obtained by using the social force model and the sightseeing garden planning information on the Anylogic pedestrian simulation platform.Then the traditional Kmeans algorithm and the improved K-means algorithm were separately used to cluster the tourists'spatial distribution data.Finally,according to the node optimization layout evaluation metric,the optimal location of the nodes was calculated.【Result】The traditional K-means algorithm and the improved K-means algorithm were used to cluster the spatial distribution data of the 12 groups of tourists,and the final node position of the two sets were obtained.The final node position obtained by the improved K-means algorithm was compared with the K-means algorithm,and the portfolio effect of final nodes accessed times was greatly reduced.The average of the standard deviation of nodes accessed times was reduced by 41.8%.Therefore,the improved Kmeans algorithm was more suitable for the layout optimization of the nodes in the sightseeing garden,and the finalized position of the nodes were the optimal position of the nodes in the sightseeing garden.【Suggestion】Following suggestions are proposed in order to build a hybrid wireless sensor network for agricultural tourism services:estimating the spatial distribution of tourists based on the social force model to achieve the optimization of the sightseeing service;deploying node locations reasonably to extend the hybrid wireless sensor network lifetime of the converged smart device;building an agricultural IoT system that is targeted at tourist services and integrates mobile smart devices.

关 键 词：农业观光园区 社会力模型 K-MEANS算法 无线传感器网络 节点布局 

分 类 号：S126[农业科学—农业基础科学] TN709[电子电信—电路与系统]