JPWO2021173578A5

JPWO2021173578A5 -

Info

Publication number: JPWO2021173578A5
Application number: JP2022549990A
Authority: JP
Publication date: 2024-02-22

Claims

A method of wireless communication by a transmitting device, the method comprising:
generating an encoder neural network and a decoder neural network;
transmitting the decoder neural network to a receiving device;
transforming the transmitted waveform by the encoder neural network to control the operation of a power amplifier (PA) with respect to nonlinearity;
transmitting the transformed transmit waveform on a propagation channel.

further comprising transforming the transmitted waveform to ensure that the PA operates in a linear region, or
2. The method of claim 1, further comprising transforming the transmit waveform to ensure that the PA operates near a saturation region.

2. The method of claim 1 , further comprising training the encoder neural network and the decoder neural network using artificial channel data.

2. The method of claim 1, further comprising encoding in the frequency domain or time domain by the encoder neural network.

further comprising mapping the output of the encoder neural network to orthogonal frequency division multiplexing (OFDM) symbols corresponding to input data, or
2. The method of claim 1, wherein the encoder neural network loss function is based on a peak-to-average power ratio (PAPR) of the transmitted waveform.

2. The method of claim 1, further comprising inserting a pilot signal before or after encoding by the encoder neural network.

the pilot signal is precoded and inserted after the encoding, and the precoded pilot signal is time division multiplexed with the output from the encoder neural network, or
The pilot signal is inserted before the encoding, the pilot signal is time-division multiplexed with data symbols before encoding by the encoder neural network, and the encoder neural network includes a precoder as side information. 7. The method of claim 6, receiving weights or precoder indices.

the pilot signal is inserted after the encoding, the pilot signal is time division multiplexed with the output from the encoder neural network, and the encoder neural network receives precoder weights or precoder indices as side information. 7. The method according to claim 6 .

A method of wireless communication by a receiving device, the method comprising:
generating an encoder neural network and a decoder neural network;
transmitting the encoder neural network to a transmitting device;
receiving a waveform transformed by the encoder neural network;
using the decoder neural network to recover encoder input symbols from the received waveform.

10. The method of claim 9 , further comprising training the encoder neural network and the decoder neural network with artificial channel data or with real channel measurements.

10. The method of claim 9 , further comprising restoring the encoder input symbols based on side information comprising a precoded channel or a raw propagation channel.

The reconstruction target may be a symbol output from a channel encoder/modulator at the transmitting device, a precoded symbol at the transmitting device, a complex symbol obtained by applying precoding to the symbol, or a precoded symbol at the transmitting device. 10. The method of claim 9 , comprising a linear combination of symbols output from the channel encoder/modulator according to channel coefficients.

9. A transmitting device for wireless communication, comprising means for performing a method according to any one of claims 1 to 8.

Receiving device for wireless communication, comprising means for performing the method according to any one of claims 9 to 12.

A computer program comprising instructions, said instructions causing a method according to any one of claims 1 to 8 and 9 to 12 to be carried out when said computer program is executed by a computer. program.