从被噪声污染的信号测量值中获得对某一参数的估计,从而确定不同物理量间的相互依赖关系是传感器网络的一个重要应用,然而测量环境可能存在冲击噪声或脉冲干扰,导致获得的测量数据中包含了大大偏离实际范围的离群值(outliers),从而无法获得有效的参数估计.为了解决这个问题,论文提出了一种分布式鲁棒自适应估计算法,该算法基于离群值稀疏性的思想,在代价函数中引入?1范数,对可能的离群值进行识别并剔除,同时利用网络各节点的相互协作,进一步提高参数估计的性能.通过计算机仿真实验,验证了该算法具有较好的鲁棒性.%As an important task,sensor networks acquire an estimate of some parameter from their measurements corrupted by noises,so as to determine the interdependency and interrelationship of different physical quantities. However,the network environment may suffer from impulse interferences,resulting in some outliers mixed in the measurements. Consequently,many existing algorithms fail to yield effective estimation results. In order to solve this problem,we propose a distributed robust adaptive estimation algorithm in this paper. This algorithm introduces an?1-norm in cost function based on the sparisty of outliers,arming at detect and then reject these outliers,and moreover,exploits data exchange and cooperation between neighbors to further improve the estimation performance. The simulation experiments are carried out and the effectiveness of the algorithm is verified.
展开▼
