Distributed multichannel adaptive filtering

Abstract

A new distributed multichannel technique is proposed for networks in which a different set of parameters is estimated by each node. The technique is proposed for non fully-connect topologies, so that nodes must store data and re-transmit information to other network elements. To reduce the amount of terms stored by each node, pre-computation of the data required by other elements is performed before the data sharing. The proposed method is adequate for implementation in networks with a large number of nodes, for which straightforward implementations would be prohibitive in terms of cost and memory.