煤矿井下WSN中基于自适应粒子群聚类算法的多sink节点部署  

Multi-sink Deployment in Wireless Sensor Networks for Underground Coal Mine Based on Adaptive Particle Swarm Optimization Clustering Algorithm

作　　者：胡长俊 袁树杰[1,3] HU Chang-jun;YUAN Shu-jie(Key Laboratory of Safety and High-efficiency Coal Mining,Ministry of Education,Anhui University of Science and Technology,Huainan,Anhui 232001,China;School of Electrical and Information Engineering,Anhui University of Science and Technology,Huainan,Anhui 232001,China;School of Energy and Safety,Anhui University of Science and Technology,Huainan,Anhui 232001,China)

机构地区：[1]安徽理工大学煤矿安全高效开采省部共建教育部重点实验室,安徽淮南232001 [2]安徽理工大学电气与信息工程学院,安徽淮南232001 [3]安徽理工大学能源与安全学院,安徽淮南232001

出　　处：《计算机科学》2018年第11期103-107,123,共6页Computer Science

基　　金：国家自然科学青年基金项目(61300001;51404008;61401003);安徽省矿用电子工程技术研究中心开放基金项目(2013KF04)资助

摘　　要：多sink节点的部署是井下传感器网络的重要研究课题,对网络性能的影响很大。针对目前采用的部署方法存在计算过程复杂、收敛速度慢、容易陷入局部最优等问题,在标准粒子群聚类算法的基础上,提出一种基于自适应粒子群聚类算法的井下多sink节点部署算法(简称A-PSOCA算法),在惯性权重系数中考虑了粒子的进化和聚合状况,使改进的算法的自适应能力更强,并在算法迭代过程中引入预防粒子位置重叠策略,防止粒子搜索局部最优化。仿真结果表明,A-PSOCA算法可以得到合理的sink节点位置,算法的收敛速度比标准粒子群聚类算法快1倍,所对应的网络的平均能耗和均衡性以及网络生存期也优于其他基于粒子群算法,适用于井下通信环境。Multi-sink deployment is an important research topic in underground sensor networks,which has a great influence on network performance.In view of the defect of complex calculation process,slow convergence rate,and trapping into local optimization existing in current deployment methods,on the basis of standard particle swarm optimization algorithm,a multi-sink deployment algorithm(A-PSOCA)based on adaptive particle swarm optimization clustering algorithm was proposed.In the A-PSOCA algorithm,the status of particle evolution and aggregation is introduced in the inertia weight coefficient to make the proposed algorithm more adaptive,and a preventive strategy from position overlapping in the iterative process of the algorithm is introduced to prevent particle swarm search from local optimization.Simulation results show that the A-PSOCA algorithm obtains reasonable locations for sink nodes,and its convergence rate is twice as faster as the standard particle swarm clustering algorithm.Compared with the other algorithms based on particle swarm optimization,the A-PSOCA approach has obvious advantages in terms of average energy consumption,proportionality and the lifetime of corresponding network.It is more suitable for underground communication environment.

关 键 词：矿井监测 多sink节点部署 自适应算法 粒子群算法 聚类算法 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]