Diffusion LMS strategies for parameter estimation over fading wireless channels

We propose a modified diffusion strategy for parameter estimation in sensor networks where nodes exchange information over fading wireless channels. We show that the effect of fading can be mitigated by incorporating local equalization coefficients into the diffusion process. We explain how the equalization coefficients are chosen and show that the (mean) stability of the network continues to be insensitive to the choice of the combination weights and to the network topology. Our computer experiments demonstrate that the performance of the modified diffusion algorithm in fading scenario is nearly identical to that of centralized least-mean square (LMS) with equalized input data.

[1]  Soummya Kar,et al.  Distributed Consensus Algorithms in Sensor Networks With Imperfect Communication: Link Failures and Channel Noise , 2007, IEEE Transactions on Signal Processing.

[2]  Ali H. Sayed,et al.  Diffusion Least-Mean Squares Over Adaptive Networks: Formulation and Performance Analysis , 2008, IEEE Transactions on Signal Processing.

[3]  Ali H. Sayed,et al.  Diffusion LMS Strategies for Distributed Estimation , 2010, IEEE Transactions on Signal Processing.

[4]  Ali H. Sayed,et al.  Diffusion Adaptation Over Networks Under Imperfect Information Exchange and Non-Stationary Data , 2011, IEEE Transactions on Signal Processing.

[5]  Ananthram Swami,et al.  Consensus algorithms over fading channels , 2010, 2010 - MILCOM 2010 MILITARY COMMUNICATIONS CONFERENCE.

[6]  Ali H. Sayed,et al.  Diffusion Adaptation over Networks , 2012, ArXiv.

[7]  Benoît Champagne,et al.  Diffusion LMS algorithms for sensor networks over non-ideal inter-sensor wireless channels , 2011, 2011 International Conference on Distributed Computing in Sensor Systems and Workshops (DCOSS).

[8]  Ali H. Sayed,et al.  Diffusion strategies for adaptation and learning over networks: an examination of distributed strategies and network behavior , 2013, IEEE Signal Processing Magazine.

[9]  Soummya Kar,et al.  Distributed Consensus Algorithms in Sensor Networks: Link Failures and Channel Noise , 2007, ArXiv.

[10]  Azam Khalili,et al.  Transient analysis of diffusion least‐mean squares adaptive networks with noisy channels , 2012 .

[11]  Azam Khalili,et al.  Steady-State Analysis of Diffusion LMS Adaptive Networks With Noisy Links , 2012, IEEE Transactions on Signal Processing.

[12]  S. Leigh,et al.  Probability and Random Processes for Electrical Engineering , 1989 .