Robust Diffusion Affine Projection Algorithm With Variable Step-Size Over Distributed Networks

被引:15
作者
Song, Pucha [1 ]
Zhao, Haiquan [1 ]
Zeng, Xiangping [1 ]
机构
[1] Southwest Jiaotong Univ, Sch Elect Engn, Key Lab Magnet Suspens Technol & Maglev Vehicle, Minist Educ, Chengdu 610031, Sichuan, Peoples R China
来源
IEEE ACCESS | 2019年 / 7卷
基金
美国国家科学基金会;
关键词
Estimation; Convergence; Adaptive systems; Cost function; Projection algorithms; Standards; Steady-state; Affine projection algorithm; impulsive noise; M-estimate; variable step-size; distributed estimation; LEAST-MEAN SQUARES; LMS ALGORITHM; PERFORMANCE ANALYSIS; STRATEGIES; FORMULATION; ADAPTATION;
D O I
10.1109/ACCESS.2019.2947636
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
The estimation performance of the standard diffusion affine projection algorithm may be degraded when the distributed network nodes are disturbed by impulsive noise. To overcome the limitation, a diffusion affine projection M-estimate (DAPM) algorithm is proposed for distributed estimation in the adaptive diffusion networks. This algorithm uses a robust cost function based on M-estimate function to eliminate the adverse effects of impulsive noise on distributed diffusion network nodes. In order to further enhance the performance of the DAPM algorithm, namely fast convergence rate and low steady-state error, a variable step-size diffusion affine projection M-estimate (VSS-DAPM) algorithm is presented. In addition, the convergence range of the step-size is deduced to ensure the convergence of the proposed algorithms. Computer simulations show that the proposed DAPM and VSS-DAPM algorithms have good convergence performance for distributed estimation in the adaptive diffusion networks. More importantly, the proposed VSS-DAPM algorithm improves convergence rate and the network mean square deviation (MSD) as compared to the DAPM algorithm in the distributed estimation.
引用
收藏
页码:150484 / 150491
页数:8
相关论文
共 36 条
[1]   Distributed Estimation Over an Adaptive Diffusion Network Based on the Family of Affine Projection Algorithms [J].
Abadi, Mohammad Shams Esfand ;
Shafiee, Mohammad Saeed .
IEEE TRANSACTIONS ON SIGNAL AND INFORMATION PROCESSING OVER NETWORKS, 2019, 5 (02) :234-247
[2]   Tracking Performance and Optimal Adaptation Step-Sizes of Diffusion-LMS Networks [J].
Abdolee, Reza ;
Vakilian, Vida ;
Champagne, Benoit .
IEEE TRANSACTIONS ON CONTROL OF NETWORK SYSTEMS, 2018, 5 (01) :67-78
[3]  
[Anonymous], EURASIP J ADV SIGNAL
[4]   Diffusion recursive least-squares for distributed estimation over adaptive networks [J].
Cattivelli, Federico S. ;
Lopes, Cassio G. ;
Sayed, Ali. H. .
IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2008, 56 (05) :1865-1877
[5]   Diffusion LMS Strategies for Distributed Estimation [J].
Cattivelli, Federico S. ;
Sayed, Ali H. .
IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2010, 58 (03) :1035-1048
[6]   On the Performance Analysis of the Least Mean M-Estimate and Normalized Least Mean M-Estimate Algorithms with Gaussian Inputs and Additive Gaussian and Contaminated Gaussian Noises [J].
Chan, S. C. ;
Zhou, Y. .
JOURNAL OF SIGNAL PROCESSING SYSTEMS FOR SIGNAL IMAGE AND VIDEO TECHNOLOGY, 2010, 60 (01) :81-103
[7]   Diffusion generalized maximum correntropy criterion algorithm for distributed estimation over multitask network [J].
Chen, Feng ;
Li, Xinyu ;
Duan, Shukai ;
Wang, Lidan ;
Wu, Jiagui .
DIGITAL SIGNAL PROCESSING, 2018, 81 :16-25
[8]   Diffusion least logarithmic absolute difference algorithm for distributed estimation [J].
Chen, Feng ;
Shi, Tao ;
Duan, Shukai ;
Wang, Lidan ;
Wu, Jiagui .
SIGNAL PROCESSING, 2018, 142 :423-430
[9]   Broken-motifs diffusion LMS algorithm for reducing communication load [J].
Chen, Feng ;
Shao, Xiaodan .
SIGNAL PROCESSING, 2017, 133 :213-218
[10]   Diffusion Adaptation Strategies for Distributed Optimization and Learning Over Networks [J].
Chen, Jianshu ;
Sayed, Ali H. .
IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2012, 60 (08) :4289-4305