基于动态加权的量化分布式卡尔曼滤波  

Quantized distributed Kalman filtering based on dynamic weighting

作　　者：陈小龙[1] 马磊[1] 张文旭[1] 

机构地区：[1]西南交通大学系统科学与技术研究所,成都610031

出　　处：《计算机应用》2015年第7期1824-1828,共5页journal of Computer Applications

基　　金：国家自然科学基金资助项目(61075104)

摘　　要：针对一个无融合中心传感器网络中的状态估计问题,提出一种基于量化信息的分布式卡尔曼滤波(QDKF)算法。首先,在分布式卡尔曼滤波(DKF)中,以节点状态估计精度为加权准则,动态选取加权矩阵,使得全局估计误差的协方差最小;然后,进一步考虑了网络带宽受限制的情况,在DKF算法中加入均匀量化器,节点之间通信使用量化后的信息,以减少网络通信的带宽需求。QDKF算法仿真采用了8 bit的均匀量化器,与Metropolis加权法和最大度加权法相比,动态加权法的状态估计均方根误差分别降低了25%和27.33%。实验结果表明,采用动态加权法的QDKF算法能提高系统的状态估计精度,减少带宽需求,适用于网络通信受限制的应用场合。Focusing on the state estimation problem of a Wireless Sensor Network （WSN） without a fusion center, a Quantized Distributed Kalman Filtering （QDKF） algorithm was proposed. Firstly, based on the weighting criterion of node estimation accuracy, a weight matrix was dynamically chosen in the Distributed Kalman Filtering （DKF） algorithm to minimize the global estimation Error Covariance Matrix （ECM）. And then, considering the bandwidth constraint of the network, a uniform quantizer was added into the DKF algorithm. The requirement of the network bandwidth was reduced by using the quantized information during the communication. Simulations were conducted by using the proposed QDKF algorithm with an 8-bit quantizer. In the comparison experiments with the Metropolis weighting and the maximum degree weighting, the estimation Root Mean Square Error （RMSE） of the mentioned dynamic weighting method decreased by 25% and 27.33% respectively. The simulation results show that the QDKF algorithm using dynamic weighting can improve the estimation accuracy and reduce the requirement of network bandwidth, and it is suitable for network communications limited applications.

关 键 词：无线传感器网络 分布式算法 量化信息 一致性滤波 动态加权 

分 类 号：TP391[自动化与计算机技术—计算机应用技术] TN915.04[自动化与计算机技术—计算机科学与技术]