Distributed Kalman Filtering With Quantized Sensing State
Distributed Kalman Filtering With Quantized Sensing State
复制标题
DOI：
10.1109/tsp.2015.2450200
复制
发表时间：
2015-04
影响因子：
5.4
通讯作者：
Di Li;S. Kar;F. Alsaadi;A. Dobaie;Shuguang Cui
中科院分区：
文献类型：
--
作者：
Di Li;S. Kar;F. Alsaadi;A. Dobaie;Shuguang Cui
研究了一种基于量化Gossip的交互式卡尔曼滤波（QGIKF）算法在无线传感器网络中的实现，其中传感器通过传感器间通信与邻居交换其量化状态。我们证明，在可数无限量化字母表的情况下，网络仍然可以实现弱共识，由于量化，即，在随机选择的传感器处的估计误差方差序列可以弱地（在分布中）收敛到唯一不变的测量。为了证明弱收敛性，我们首先将误差方差序列解释为相互作用的粒子，然后将每个序列的演化建模为随机动力系统（RDS），并进一步证明其随机有界性.此外，基于对可数无限量化字母表情形的分析，我们还证明了在一定条件下，当量化字母表是有限的时，网络也可以实现弱一致性，这更具有限制性和实用性。
This paper studies a Quantized Gossip-based Interactive Kalman Filtering (QGIKF) algorithm implemented in a wireless sensor network, where the sensors exchange their quantized states with neighbors via inter-sensor communications. We show that, in the countable infinite quantization alphabet case, the network can still achieve weak consensus with the information loss due to quantization, i.e., the estimation error variance sequence at a randomly selected sensor can converge weakly (in distribution) to a unique invariant measure. To prove the weak convergence, we first interpret error variance sequences as interacting particles, then model each sequence evolution as a Random Dynamical System (RDS), and further prove its stochastically bounded nature. Moreover, based on the analysis for the countable infinite quantization alphabet case, we also prove that under certain conditions the network can also achieve weak consensus, when the quantization alphabet is finite, which is more restricted and practical.