pith. sign in

arxiv: 1110.5092 · v1 · pith:NS6OE3ECnew · submitted 2011-10-23 · 💻 cs.IT · math.IT

Geometry of the 3-user MIMO interference channel

classification 💻 cs.IT math.IT
keywords alignmentinterferencefeasibilitychannelantennascountingcriterionequations
0
0 comments X
read the original abstract

This paper studies vector space interference alignment for the three-user MIMO interference channel with no time or frequency diversity. The main result is a characterization of the feasibility of interference alignment in the symmetric case where all transmitters have M antennas and all receivers have N antennas. If N >= M and all users desire d transmit dimensions, then alignment is feasible if and only if (2r+1)d <= max(rN,(r+1)M) for all nonnegative integers r. The analogous result holds with M and N switched if M >= N. It turns out that, just as for the 3-user parallel interference channel \cite{BT09}, the length of alignment paths captures the essence of the problem. In fact, for each feasible value of M and N the maximum alignment path length dictates both the converse and achievability arguments. One of the implications of our feasibility criterion is that simply counting equations and comparing to the number of variables does not predict feasibility. Instead, a more careful investigation of the geometry of the alignment problem is required. The necessary condition obtained by counting equations is implied by our new feasibility criterion.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.