基于传感器网络的1比特RLS算法

在基于传感器网络的参数估计中，如何尽可能降低网络的使用成本，同时又能获得较好的参数估计性能，是近年来受到国内外学者广泛关注的一个研究问题。为了减小网络的能量消耗和节省带宽、存储资源，本文考虑将传感器网络中每个节点的测量值压缩成1比特数据，然后将其传输到中心节点进行集中处理，并在此基础上提出了一种基于期望最大和递归最小二乘的自适应参数估计算法。论文通过一系列MATLAB仿真实验，验证了该算法具有较好的收敛性和鲁棒性，并能获得与使用非量化测量值的经典RLS算法相近的估计精度。

One-Bit Recursive Least-Square Algorithm over Sensor Networks

For the problem of parameter estimation over wireless sensor networks, how to reduce the cost of using the network as much as possible, and at the same time get better parameter estimation performance has been widely concerned by scholars at home and abroad in recent years. In order to reduce the energy consumption, save bandwidth and storage resources of the network, this paper considers compressing the measurements of each node into 1-bit data, and then transmitting them to the central node for centralized processing. Based on this, an effective adaptive parameter estimation algorithm combining the expectation-maximization and recursive least-squares method is proposed. Through a series of MATLAB simulation experiments, the paper proves that the algorithm has good convergence and robustness, and can obtain similar estimation accuracy with the classical RLS algorithm using non-quantized measurements.