Distributed channel prediction for multi-agent systems
Paper in proceedings, 2017

Multi-agent systems (MAS) communicate over a wireless network to coordinate their actions and to report their mission status. Connectivity and system-level performance can be improved by channel gain prediction. We present a distributed Gaussian process regression (GPR) framework for channel prediction in terms of the received power in MAS. The framework combines a Bayesian committee machine with an average consensus scheme, thus distributing not only the memory, but also computational and communication loads. Through Monte Carlo simulations, we demonstrate the performance of the proposed GPR.

Author

V.P. Chowdappa

Universitat de Valencia

Markus Fröhle

Chalmers, Signals and Systems, Kommunikationssystem, informationsteori och antenner, Communication Systems

Henk Wymeersch

Chalmers, Signals and Systems, Kommunikationssystem, informationsteori och antenner, Communication Systems

Carmen Botella Mascarell

Universitat de Valencia

2017 IEEE International Conference on Communications, ICC 2017, Paris, France, 21-25 May 2017

1550-3607 (ISSN)

Subject Categories

Communication Systems

DOI

10.1109/ICC.2017.7997044

ISBN

978-1-4673-8999-0

More information

Latest update

3/8/2018 1