Formulation and Analysis of LMS Adaptive Networks for Distributed Estimation in the Presence of Transmission Errors
Authors:
- 30 June 2015
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 3 (2) , 146-160
Abstract
Wireless sensor network (WSN) technologies and distributed processing are essential to develop ubiquitous sensing in the Internet of Things (IoT) paradigm, wherein sensors pervasively collect data and perform information processing and communication tasks to achieve a common objective. This paper presents the formulation and analysis of distributed estimation algorithms based on the diffusion cooperation scheme in the presence of errors due to the unreliable data transfer among nodes. In particular, we highlight the impact of transmission errors on the least-mean squares (LMS) adaptive networks. We develop the closed-form expressions for the steady-state mean-square deviation (MSD), which is helpful to assess the effects of the imperfect information flow on the behavior of diffusion LMS algorithms in terms of steady-state error. The model is then validated by performing Monte Carlo simulations. It is shown that local and global steady-state MSD values are not necessarily monotonic increasing functions of the error probability. We also assess sufficient conditions that ensure mean and mean-square stability of diffusion LMS strategies in the presence of transmission errors. We examine a practical scenario where errors occur at the medium access control (MAC) level. To overcome the problem of unreliable data exchange, we implement a random pairwise strategy that improves the performance of the estimation algorithm in the presence of high transmission error rates. Moreover, issues such as scalability in the sense of network size and regressor size, convergence behavior during the transient phase, spatially correlated observations, as well as the effect of the distribution of the noise variance are studied.Keywords
All Related Versions
Funding Information
- Hydro-Québec
- Natural Sciences and Engineering Research Council of Canada
- McGill University in the framework of the NSERC/Hydro-Québec/McGill Industrial Research Chair in Interactive Information Infrastructure for the Power Grid
This publication has 38 references indexed in Scilit:
- Diffusion Adaptation Strategies for Distributed Estimation Over Gaussian Markov Random FieldsIEEE Transactions on Signal Processing, 2014
- Optimal variable step-size diffusion LMS algorithms2014
- Diffusion least-mean squares over distributed networks in the presence of MAC errors2012
- MAC Essentials for Wireless Sensor NetworksIEEE Communications Surveys & Tutorials, 2010
- Z-MAC: A Hybrid MAC for Wireless Sensor NetworksIEEE/ACM Transactions on Networking, 2008
- Diffusion recursive least-squares for distributed estimation over adaptive networksIEEE Transactions on Signal Processing, 2008
- Convergence in Multiagent Coordination, Consensus, and Flocking2006
- MAC protocols for wireless sensor networks: a surveyIEEE Communications Magazine, 2006
- Locally constructed algorithms for distributed computations in ad-hoc networks2004
- Performance analysis of the IEEE 802.11 distributed coordination functionIEEE Journal on Selected Areas in Communications, 2000