An Iterative Scheme for Computing Combination Weights in Diffusion Wireless Networks
Authors:
- 31 May 2017
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Wireless Communications Letters
- Vol. 6 (4) , 510-513
Abstract
In this letter, we propose an iterative scheme for computing combination matrices of adaptive networks used in diffusion of data among nodes. In particular, we study the performance of diffusion least-mean-squares algorithms over wireless networks for different choices of left-stochastic combination matrices. We formulate a convex optimization problem using an upper bound of the mean-squares deviation of the network and obtain a closed-form expression to find these matrices. We also propose an adaptive scheme to obtain the optimal weights that runs in real-time along with the estimation process over the network. Numerical experiments support the theoretical findings of this letter.Keywords
This publication has 14 references indexed in Scilit:
- Diffusion Adaptation over Multi-Agent Networks with Wireless Link ImpairmentsIEEE Transactions on Mobile Computing, 2015
- Adaptation, Learning, and Optimization over NetworksFoundations and Trends in Machine Learning, 2014
- Estimation of Space-Time Varying Parameters Using a Diffusion LMS AlgorithmIEEE Transactions on Signal Processing, 2013
- Diffusion LMS strategies for parameter estimation over fading wireless channels2013
- Diffusion strategies for adaptation and learning over networks: an examination of distributed strategies and network behaviorIEEE Signal Processing Magazine, 2013
- Diffusion Adaptation Over Networks Under Imperfect Information Exchange and Non-Stationary DataIEEE Transactions on Signal Processing, 2012
- Optimal combination rules for adaptation and learning over networks2011
- Diffusion Least-Mean Squares With Adaptive Combiners: Formulation and Performance AnalysisIEEE Transactions on Signal Processing, 2010
- Weight Optimization for Consensus Algorithms With Correlated Switching TopologyIEEE Transactions on Signal Processing, 2010
- Convex Optimization2004