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
|
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.
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.
引文
[1]SUN J P.Revision amendments for sensor setting of AQ 1029-2007 Use and Management specification of Coal Mine Safety Monitoring System and Testing Instrument[J].Industry and Mine Automation,2016,42(4):1-6.(in Chinese)孙继平.AQ 1029-2007《煤矿安全监控系统及检测仪器使用管理规范》传感器设置修订意见[J].工矿自动化,2016,42(4):1-6.
[2]DANDEKAR D,DESHMUKH P R.Energy balancing multiple sink optimal deployment in multi-hop Wireless Sensor Networks[C]∥2013IEEE 3rd International Advance Computing Conference(IACC).IEEE,2013:408-412.
[3]SAFA H,ELHAJJ W,ZOUBIAN H.Particle swarm optimization based approach to solve the multiple sink placement problem in WSNs[C]∥2012IEEE International Conference on Communications(ICC).IEEE,2012:5445-5450.
[4]FLATHAGEN J,KURE Q,ENGELSTAD P E.Constrainedbased multiple sink placement foe wireless sensor networks[C]∥2011IEEE 8th International Conference on IEEE.Valencia,2011:783-788.
[5]DAI S,TANG C,QIAO S,et al.Optimal multiple sink nodes deployment in wireless sensor networks based on gene expression programming[C]∥2010ICCSN’10Second International Conference on IEEE.Chengdu,2010:355-359.
[6]LIU Q,MAO Y M.Algorithm of multi-sink placement in Wireless Sensor Networks with random distribution[J].Computer Engineering and Applications,2013,49(22):82-85.
[7]纪震,廖惠连,吴青华.粒子群算法及应用[M].北京:科学出版社,2009:1-17.
[8]YANG C W,GAO W,LIU N G,et al.Low-Discrepancy Sequence Initialized Particle Swarm Optimization Algorithm with High-Order Nonlinear Time-Varying Inertia Weight[J].Applied Soft Computing,2015,29(4):386-394.
[9]WANG R Y,LIU H,WU D P,et al.Low-cost Optical Network Unit Deployment Strategy with Survivability Aware in Hybrid Optical-wireless Broadband Access Networks[J].Journal of E-lectronics&Information Technology,2016,38(6):1354-1361.(in Chinese)王汝言,刘辉,吴大鹏,等.带有生存性感知的低成本光无线混合网络无线功能部署策略[J].电子与信息学报,2016,38(6):1354-1361.
[10]GAO F R,WANG J J,XI X G,et al.Gait Recognition for Lower Extremity Electromyography Signals Based on PSO-SVM Method[J].Journal of Electronics&Information Technology,2015,37(5):1154-1159.(in Chinese)高发荣,王佳佳,席旭刚,等.基于粒子群优化-支持向量机方法的下肢肌电信号步态识别[J].电子与信息学报,2015,37(5):1154-1159.
[11]WU J H,WANG B H,ZHANG X G,et al.Cloud model particle swarm optimization algorithm based on pattern search method[J].Control and Decision,2017,32(11):2076-2080.(in Chinese)吴建辉,王博华,张小刚,等.基于模式搜索法的云模型粒子群算法[J].控制与决策,2017,32(11):2076-2080.
[12]ZHANG C,LI Q,WANG W Q,et al.Immune particle swarm optimization algorithm based on the adaptive search strategy[J].Chinese Journal of Engineering,2017,39(1):125-132.(in Chinese)张超,李擎,王伟乾,等.基于自适应搜索的免疫粒子群算法[J].工程科学学报,2017,39(1):125-132.
[13]JIANG G Q,YANG X Y,WANG Z H,et al.Crop rows detection based on image characteristic point and particle swarm optimization-clustering algorithm[J].Transactions of the Chinese Society of Agricultural Engineering,2017,33(11):165-170.(in Chinese)姜国权,杨小亚,王志衡,等.基于图像特征点粒子群聚类算法的麦田作物行检测[J].农业工程学报,2017,33(11):165-170.
[14]WANG R H,CUI X M,ZHOU W,et al.Simplified particle swarm K-means clustering algorithm for merging adjacent disturbances[J/OL].Application Research of Computers,2018,35(11):1-7.(in Chinese)王日宏,崔兴梅,周炜,等.融合邻域扰动的简化粒子群K-均值聚类算法[J/OL].计算机应用研究,2018,35(11):1-7.
[15]VAN D W,ENGELBRECHT A P.Data clustering using particle swarm optimization[C]∥The 2003Congress on Evolutionary Computation,2003.IEEE,2003(1):215-220.
[16]KAO Y C,LEE S Y.Combining K-means and particle swarm optimization for dynamic data clustering problems[C]∥Proceedings of IEEE International Conference on Intelligent Computing and Intelligent Systems,2009:757-761.
[17]ANIL K J.Data clustering:50years beyond K-Means[J].Pattern Recognition Letters,2010,31(8):651-666.
[18]WENDI B H,ANANTHA P C,HARI B.An application-specific protocol architecture for wireless micro sensor networks[J].IEEE Trans on Wireless Communications,2002,1(4):660-670.
[19]MARGI CB,PETKOV V,OBRACZKA K,et al.Characterizing energy consumption in a visual sensor network testbed[C]∥International Conference on Testbeds and Research Infrastructures for the Development of Networks and Communities(Trident Com).Barcelona,Spain,2006:335-339.
[2]DANDEKAR D,DESHMUKH P R.Energy balancing multiple sink optimal deployment in multi-hop Wireless Sensor Networks[C]∥2013IEEE 3rd International Advance Computing Conference(IACC).IEEE,2013:408-412.
[3]SAFA H,ELHAJJ W,ZOUBIAN H.Particle swarm optimization based approach to solve the multiple sink placement problem in WSNs[C]∥2012IEEE International Conference on Communications(ICC).IEEE,2012:5445-5450.
[4]FLATHAGEN J,KURE Q,ENGELSTAD P E.Constrainedbased multiple sink placement foe wireless sensor networks[C]∥2011IEEE 8th International Conference on IEEE.Valencia,2011:783-788.
[5]DAI S,TANG C,QIAO S,et al.Optimal multiple sink nodes deployment in wireless sensor networks based on gene expression programming[C]∥2010ICCSN’10Second International Conference on IEEE.Chengdu,2010:355-359.
[6]LIU Q,MAO Y M.Algorithm of multi-sink placement in Wireless Sensor Networks with random distribution[J].Computer Engineering and Applications,2013,49(22):82-85.
[7]纪震,廖惠连,吴青华.粒子群算法及应用[M].北京:科学出版社,2009:1-17.
[8]YANG C W,GAO W,LIU N G,et al.Low-Discrepancy Sequence Initialized Particle Swarm Optimization Algorithm with High-Order Nonlinear Time-Varying Inertia Weight[J].Applied Soft Computing,2015,29(4):386-394.
[9]WANG R Y,LIU H,WU D P,et al.Low-cost Optical Network Unit Deployment Strategy with Survivability Aware in Hybrid Optical-wireless Broadband Access Networks[J].Journal of E-lectronics&Information Technology,2016,38(6):1354-1361.(in Chinese)王汝言,刘辉,吴大鹏,等.带有生存性感知的低成本光无线混合网络无线功能部署策略[J].电子与信息学报,2016,38(6):1354-1361.
[10]GAO F R,WANG J J,XI X G,et al.Gait Recognition for Lower Extremity Electromyography Signals Based on PSO-SVM Method[J].Journal of Electronics&Information Technology,2015,37(5):1154-1159.(in Chinese)高发荣,王佳佳,席旭刚,等.基于粒子群优化-支持向量机方法的下肢肌电信号步态识别[J].电子与信息学报,2015,37(5):1154-1159.
[11]WU J H,WANG B H,ZHANG X G,et al.Cloud model particle swarm optimization algorithm based on pattern search method[J].Control and Decision,2017,32(11):2076-2080.(in Chinese)吴建辉,王博华,张小刚,等.基于模式搜索法的云模型粒子群算法[J].控制与决策,2017,32(11):2076-2080.
[12]ZHANG C,LI Q,WANG W Q,et al.Immune particle swarm optimization algorithm based on the adaptive search strategy[J].Chinese Journal of Engineering,2017,39(1):125-132.(in Chinese)张超,李擎,王伟乾,等.基于自适应搜索的免疫粒子群算法[J].工程科学学报,2017,39(1):125-132.
[13]JIANG G Q,YANG X Y,WANG Z H,et al.Crop rows detection based on image characteristic point and particle swarm optimization-clustering algorithm[J].Transactions of the Chinese Society of Agricultural Engineering,2017,33(11):165-170.(in Chinese)姜国权,杨小亚,王志衡,等.基于图像特征点粒子群聚类算法的麦田作物行检测[J].农业工程学报,2017,33(11):165-170.
[14]WANG R H,CUI X M,ZHOU W,et al.Simplified particle swarm K-means clustering algorithm for merging adjacent disturbances[J/OL].Application Research of Computers,2018,35(11):1-7.(in Chinese)王日宏,崔兴梅,周炜,等.融合邻域扰动的简化粒子群K-均值聚类算法[J/OL].计算机应用研究,2018,35(11):1-7.
[15]VAN D W,ENGELBRECHT A P.Data clustering using particle swarm optimization[C]∥The 2003Congress on Evolutionary Computation,2003.IEEE,2003(1):215-220.
[16]KAO Y C,LEE S Y.Combining K-means and particle swarm optimization for dynamic data clustering problems[C]∥Proceedings of IEEE International Conference on Intelligent Computing and Intelligent Systems,2009:757-761.
[17]ANIL K J.Data clustering:50years beyond K-Means[J].Pattern Recognition Letters,2010,31(8):651-666.
[18]WENDI B H,ANANTHA P C,HARI B.An application-specific protocol architecture for wireless micro sensor networks[J].IEEE Trans on Wireless Communications,2002,1(4):660-670.
[19]MARGI CB,PETKOV V,OBRACZKA K,et al.Characterizing energy consumption in a visual sensor network testbed[C]∥International Conference on Testbeds and Research Infrastructures for the Development of Networks and Communities(Trident Com).Barcelona,Spain,2006:335-339.