Adaptive Distributed Estimation Based on Recursive Least-Squares and Partial Diffusion

Using the diffusion strategies, an unknown parameter vector can be estimated over an adaptive network by combining the intermediate estimates of neighboring nodes at each node. We propose an extension to the diffusion recursive least-squares algorithm by allowing partial sharing of the entries of th...

Celý popis

Uložené v:

Podrobná bibliografia
Vydané v:	IEEE transactions on signal processing Ročník 62; číslo 14; s. 3510 - 3522
Hlavní autori:	Arablouei, Reza, Dogancay, Kutluyil, Werner, Stefan, Huang, Yih-Fang
Médium:	Journal Article
Jazyk:	English
Vydavateľské údaje:	New York, NY IEEE 15.07.2014 Institute of Electrical and Electronics Engineers The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Predmet:	Adaptive networks Adaptive systems Algorithm design and analysis Algorithms Applied sciences Convergence Detection, estimation, filtering, equalization, prediction Diffusion diffusion adaptation distributed estimation Educational institutions Electronic mail Estimates Estimation Exact sciences and technology Information, signal and communications theory Least squares method Mathematical analysis partial diffusion Recursive recursive least-squares Signal and communications theory Signal processing algorithms Signal, noise Telecommunications and information theory Vectors Vectors (mathematics) Performance evaluation distributed estimation Adaptive estimation Recursive algorithm Steady state recursive least-squares partial diffusion Adaptive networks Distributed processing Simulation Least squares method Recursive method Signal processing Partial least squares diffusion adaptation
ISSN:	1053-587X, 1941-0476
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!

Popis
Shrnutí:	Using the diffusion strategies, an unknown parameter vector can be estimated over an adaptive network by combining the intermediate estimates of neighboring nodes at each node. We propose an extension to the diffusion recursive least-squares algorithm by allowing partial sharing of the entries of the intermediate estimate vectors among the neighbors. Accordingly, the proposed algorithm, termed partial-diffusion recursive least-squares (PDRLS), enables a trade-off between estimation performance and communication cost. We analyze the performance of the PDRLS algorithm and prove its convergence in both mean and mean-square senses. We also derive a theoretical expression for its steady-state mean-square deviation. Simulation results substantiate the efficacy of the PDRLS algorithm and demonstrate a good match between theory and experiment.
Bibliografia:	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23
ISSN:	1053-587X 1941-0476
DOI:	10.1109/TSP.2014.2327005