	US 11,817,976 B2
	Adaptive coding and modulation
Mohammad Sadegh Safari, Yazd (IR); Vahid Pourahmadi, Tehran (IR); and Patrick Mitran, Waterloo (CA)
Filed by Mohammad Sadegh Safari, Yazd (IR); Vahid Pourahmadi, Tehran (IR); and Patrick Mitran, Waterloo (CA)
Filed on Apr. 15, 2022, as Appl. No. 17/721,519.
Claims priority of provisional application 63/228,168, filed on Aug. 2, 2021.
Prior Publication US 2022/0239534 A1, Jul. 28, 2022
Int. Cl. H04L 25/03 (2006.01); H04L 25/06 (2006.01); H04L 25/02 (2006.01)

CPC H04L 25/03929 (2013.01) [H04L 25/023 (2013.01); H04L 25/066 (2013.01)]

20 Claims

1. A method for adaptive coding and modulation, the method comprising:

training, utilizing one or more processors, a set of recurrent neural networks (RNNs) based on a set of communication channels; and

transmitting a t^thset of transmit symbols in a t^thtime interval by transmitting an (i, t)^thtransmit symbol in the t^thset of transmit symbols by an i^thtransmitter in a set of transmitters where 1≤i≤N, N is a size of the set of transmitters, 1≤t≤T, and T is a maximum number of symbol transmissions, transmitting the (i, t)^thtransmit symbol comprising:

generating an (i, t)^thset of mapped symbols by:

obtaining an (i, t)^thhidden states set of an i^thRNNs subset of the set of RNNs based on an (i, r)^thset of mapped symbols where 0≤r≤T; and

applying the i^thRNNs subset on one of an i^thdata vector and a set of channel state information (CSI) samples of an i^thchannels subset of the set of communication channels based on the (i, t)^thhidden states set,

wherein:

each mapped symbol in the (i, t)^thset of mapped symbols comprises a respective complex value; and

each mapped symbol in an (i, 0)^thset of mapped symbols is zero;

generating the (i, t)^thtransmit symbol from the (i, t)^thset of mapped symbols; and

transmitting the (i, t)^thtransmit symbol through the i^thchannels subset.