贝叶斯预测蜂群算法在无线传感器网络优化中的应用
详细信息    查看全文 | 推荐本文 |
  • 英文篇名:Application of Bayesian predictive bee colony algorithm in WSN optimization
  • 作者:付光杰 ; 胡明哲
  • 英文作者:FU Guangjie;HU Mingzhe;School of Electrical Engineering and Information,Northeast Petroleum University;
  • 关键词:无线传感器网络 ; 节点分布 ; 人工蜂群算法 ; 贝叶斯预测算法 ; 覆盖率
  • 英文关键词:wireless sensor network(WSN);;node distribution;;artificial bee colony algorithm;;Bayesian prediction algorithm;;coverage rate
  • 中文刊名:FIVE
  • 英文刊名:Journal of Chongqing University
  • 机构:东北石油大学电气信息工程学院;
  • 出版日期:2018-05-15
  • 出版单位:重庆大学学报
  • 年:2018
  • 期:v.41
  • 基金:东北石油大学国家基金校内培育基金资助项目(py120219);东北石油大学研究生创新科研资助项目(YJSCX2016-029NEPU)~~
  • 语种:中文;
  • 页:FIVE201805002
  • 页数:8
  • CN:05
  • ISSN:50-1044/N
  • 分类号:18-25
摘要
针对无线传感器网络(WSN,wireless sensor network)节点分布不合理,存在较多的监测盲区等不足,提出了利用贝叶斯预测人工蜂群算法(BPABC,Bayesian predictive artificial bee colony algorithm)制定节点分布方案。BPABC算法借鉴贝叶斯预测算法的思想对蜂群算法中各蜜源存在最优解的概率进行预测,并以此为依据指导跟随蜂寻优工作。采用BPABC算法对WSN中的节点分布进行优化,与人工蜂群算法、全局人工蜂群算法制定的优化方案进行比较。结果表明,BPABC在平均覆盖率、最差覆盖率等方面均优于其他两种算法,并且BPABC算法在迭代收敛速度方面也有明显的优势。为了进一步验证改进算法的实用性,采用BPABC制定不同监测区域的WSN节点分布方案。WSN的覆盖率均在97%左右,并且标准差不超过0.005%。由此可见,基于BPABC的WSN节点分布优化方案具有较高的覆盖率、良好的适应性和稳定性。
        The node distribution of wireless sensor network(WSN)is often unreasonable,and always has many monitoring blind spots.Aiming at this problem,Bayesian predictive artificial bee colony algorithm(BPABC)is proposed to develop a node distribution scheme.Based on the idea of Bayesian prediction algorithm,this algorithm predicts the probability of optimal solution of each nectar source in the bee colony algorithm,and guides the followed bees to seek optimal solution.A designed algorithm is used to optimize the distribution of nodes in WSN,and the effect is compared with those of artificial bee colony algorithm and global artificial bee colony algorithm.The results show that BPABC is superior to the other two algorithms in terms of average coverage and worst coverage.Besides,this algorithm also has obvious advantages in iterative convergence rate.In order to further verify the practicability of the improvedalgorithm,this paper uses BPABC algorithm to develop WSN node distribution scheme for different monitoring areas.Coverage for all WSNs is around 97% with a standard deviation no more than 0.005%.It can be seen that the WSN node distribution optimization scheme based on BPABC has high coverage,good adaptability and stability.
引文
[1]Benatia M A,Sahnoun M,Baudry D,et al.Multi-objective WSN deployment using genetic algorithms under cost,coverage,and connectivity constraints[J].Wireless Personal Communications,2017:1-30.
    [2]Yang H,Xunbo L I,Wang Z,et al.A novel sensor deployment method based on image processing and wavelet transform to optimize the surface coverage in WSNs[J].Chinese Journal of Electronics,2016,25(3):495-502.
    [3]Cong C.A coverage algorithm for WSN based on the improved PSO[C]//International Conference on Intelligent Transportation,Big Data and Smart City.[S.l.]:IEEE,2015:12-15.
    [4]潘丽姣,吴红英.混沌逃逸粒子群优化算法在WSN覆盖优化中的应用[J].重庆邮电大学学报(自然科学版),2014,26(2):177-181.PAN Lijiao,WU Hongying.Application of chaotic escape particle swarm optimization algorithm in coverage optimization of wireless sensor networks[J].Journal of Chongqing University of Posts and Telecommunications(Natural Science Edition),2014,26(2):177-181.(in Chinese)
    [5]姚勇涛,吴雪,吴喆.基于改进的果蝇优化算法的WSN节点部署设计[J].华东理工大学学报(自然科学版),2016,42(4):545-551.YAO Yongtao,WU Xue,WU Zhe.Wireless sensor network node deployment design based on improved fruit fly optimization algorithm[J].Journal of East China University of Science and Technology(Natural Science Edition),2016,42(4):545-551.(in Chinese)
    [6]王长清,黄静.基于协同进化粒子群算法的无线传感器网络节能优化覆盖算法[J].河南师范大学学报(自然版),2016,44(1):54-58.WANG Changqing,HUANG Jing.Energy-saving coverage algorithm for wireless sensor network based on coevolutionary particle swarm optimization[J].Journal of Henan Normal University(Natural Science Edition),2016,44(1):54-58.(in Chinese)
    [7]Xu X,Zhou G,Chen T.Research on coverage optimisation of wireless sensor networks based on an artificial bee colony algorithm[M].Geneva:Inderscience Publishers,2015.
    [8]熊伟丽,刘欣,陈敏芳,等.基于差分蜂群算法的无线传感器网络节点分布优化[J].控制工程,2014,21(6):1036-1040.XIONG Weili,LIU Xin,CHEN Minfang,et al.Node distribution optimization in wireless sensor networks based on differential bee colony algorithm[J].Control Engineering of China,2014,21(6):1036-1040.(in Chinese)
    [9]Yang H,Li X,Wang Z,et al.A novel sensor deployment method based on image processing and wavelet transform to optimize the surface coverage in WSNs[J].Chinese Journal of Electronics,2016,25(3):495-502.
    [10]Guo Y N,Cheng J,Liu H Y,et al.A novel knowledge-guided evolutionary scheduling strategy for energy-efficient connected coverage optimization in WSNs[J].Peer-to-Peer Networking and Applications,2017,10(3):547-558.
    [11]陈树,钱成.一种多目标的覆盖优化策略在WSNs中的应用[J].传感器与微系统,2014,33(10):151-154.CHEN Shu,QIAN Cheng.Application of a multi-objective coverage optimization strategy in WSNs[J].Transducer and Microsystem Technologies,2014,33(10):151-154.(in Chinese)
    [12]朱志洁,张宏伟,王春明.基于人工蜂群算法优化支持向量机的采场底板破坏深度预测[J].重庆大学学报:自然科学版,2015,38(6):37-43.ZHU Zhijie,ZHANG Hongwei,WANG Chunming.Prediction of floor damaged depth in working area based on support vector machine and artificial bee colony algorithm[J].Journal of Chongqing University.2015,38(6):37-43.(in Chinese)
    [13]Kiran M S,Hakli H,Gunduz M,et al.Artificial bee colony algorithm with variable search strategy for continuous optimization[J].Information Sciences,2015,300(S):140-157.
    [14]Brajevic I.Crossover-based artificial bee colony algorithm for constrained optimization problems[J].Neural Computing&Applications,2015,26(7):1587-1601.
    [15]Maeda M,Tsuda S.Reduction of artificial bee colony algorithm for global optimization[J].Neurocomputing,2015,148(33):70-74.
    [16]姜允志,郝志峰,张宇山,等.贝叶斯预测型进化算法[J].计算机学报,2014,37(8):1846-1858.JIANG Yunzhi,HAO Zhifeng,ZHANG Yushan,et al.Bayesian forecasting evolutionary algorithm[J].Chinese Journal of Computers,2014,37(8):1846-1858.(in Chinese)

© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号

地址:北京市海淀区学院路29号 邮编:100083

电话:办公室:(+86 10)66554848;文献借阅、咨询服务、科技查新:66554700