Distortion probing reference signals
Methods, systems, and devices for wireless communications are described. A first device and a second device may communicate via a channel. The first device may generate and transmit a reference signal, which may be a distortion probing reference signal with a high peak to average power ratio. In one implementation, the first device may use the reference signal as an input for a neural network model to learn a nonlinear response of the second device transmission components. In another implementation, the second device may sample the generated reference signal, and use the samples as inputs for a neural network model to learn the nonlinear response. The first device and the second device may exchange signaling based on learning the nonlinear response, and each device may compensate for the nonlinear response when communicating via the channel.
1. A method for wireless communications at a first device, comprising:
transmitting an indication configuring a second device for transmission of a first reference signal with a first peak to average power ratio and for transmission of a second reference signal with a second peak to average power ratio that is greater than the first peak to average power ratio;
receiving, from the second device, the first reference signal and the second reference signal based at least in part on transmitting the indication;
estimating, using a neural network model and one or more neural network weights corresponding to one or more transmission parameters associated with the second device and based at least in part on a channel estimate from the first reference signal and the second reference signal, a nonlinear response associated with the second device;
estimating a transmission encoding metric and a reception decoding metric based at least in part on the nonlinear response associated with the second device;
transmitting signaling associated with the neural network model and the one or more neural network weights based at least in part on estimating the transmission encoding metric and the reception decoding metric; and
communicating with the second device based at least in part on the reception decoding metric.
2. The method of claim 1 , wherein transmitting the signaling comprises:
transmitting an indication of the transmission encoding metric.
3. The method of claim 1 , wherein:
transmitting the signaling comprises transmitting a grant scheduling a transmission that is encoded based at least in part on the transmission encoding metric; and
communicating with the second device comprises receiving the scheduled transmission.
4. The method of claim 3 , wherein:
the grant comprises an uplink grant in a downlink control information message; and
the scheduled transmission comprises an uplink shared channel transmission.
5. The method of claim 1 , further comprising:
determining the channel estimate based at least in part on receiving the first reference signal, wherein communicating with the second device is further based at least in part on the determined channel estimate.
6. The method of claim 1 , wherein:
the neural network model and the one or more neural network weights correspond to the nonlinear response associated with the second device;
the transmission encoding metric is associated with a second neural network model and a second one or more neural network weights associated with encoding transmissions at the second device based at least in part on the nonlinear response; and
the reception decoding metric is associated with a third neural network model and a third one or more neural network weights associated with decoding transmissions received at the first device based at least in part on the nonlinear response.
7. The method of claim 1 , wherein the first reference signal comprises a demodulation reference signal.
8. The method of claim 1 , wherein the second reference signal comprises a set of contiguous symbols in a time domain.
9. A method for wireless communications at a second device, comprising:
receiving an indication configuring the second device for transmission of a first reference signal with a first peak to average power ratio and for transmission of a second reference signal with a second peak to average power ratio that is greater than the first peak to average power ratio;
transmitting, to a first device, the first reference signal and the second reference signal based at least in part on receiving the indication;
receiving signaling associated with a neural network model and one or more neural network weights corresponding to one or more transmission parameters, wherein the neural network model and the one or more neural network weights are based at least in part on a channel estimate from the first reference signal and the second reference signal;
estimating, using the neural network model and the one or more neural network weights, a nonlinear response associated with transmission components of the second device;
estimating a transmission encoding metric based at least in part on the nonlinear response associated with the transmission components of the second device or based at least in part on the signaling comprising an indication of the transmission encoding metric; and
communicating with the first device based at least in part on the transmission encoding metric.
10. The method of claim 9 , wherein:
the neural network model and the one or more neural network weights correspond to the nonlinear response associated with the transmission components of the second device, and
the transmission encoding metric is associated with a second neural network model and a second one or more neural network weights associated with encoding transmissions at the second device based at least in part on the nonlinear response.
11. A method for wireless communications at a second device, comprising:
receiving an indication configuring the second device for generation of a reference signal;
capturing one or more samples of the reference signal generated at the second device based at least in part on receiving the indication;
estimating, using a neural network model and one or more neural network weights corresponding to one or more transmission parameters associated with the second device and based at least in part on the one or more samples of the reference signal, a nonlinear response of transmission components of the second device;
estimating a transmission encoding metric and a reception decoding metric based at least in part on the nonlinear response of the transmission components of the second device;
transmitting signaling associated with the neural network model and the one or more neural network weights based at least in part on estimating the transmission encoding metric and the reception decoding metric; and
communicating with a first device based at least in part on the transmission encoding metric.
12. The method of claim 11 , wherein transmitting the signaling comprises:
transmitting, to the first device, an indication of the reception decoding metric.
13. The method of claim 11 , further comprising:
receiving an indication configuring a periodicity of the signaling associated with the neural network model and the one or more neural network weights, wherein transmitting the signaling is based at least in part on the configured periodicity.
14. The method of claim 11 , wherein:
the neural network model and the one or more neural network weights correspond to the nonlinear response associated with the transmission components at the second device;
the reception decoding metric is associated with a second neural network model and a second one or more neural network weights associated with decoding transmissions received at the first device based at least in part on the nonlinear response; and
the transmission encoding metric associated with a third neural network model and a third one or more neural network weights associated with encoding transmissions at the second device based at least in part on the nonlinear response.
15. A method for wireless communications at a first device, comprising:
transmitting an indication configuring a second device for transmission of a first reference signal with a first peak to average power ratio and for transmission of a second reference signal with a second peak to average power ratio that is greater than the first peak to average power ratio;
receiving, from the second device, the first reference signal and the second reference signal based at least in part on transmitting the indication;
receiving signaling associated with a neural network model and one or more neural network weights corresponding to one or more transmission parameters, wherein the neural network model and the one or more neural network weights are based at least in part on a channel estimate from the first reference signal and the second reference signal;
estimating, using the neural network model and the one or more neural network weights, a nonlinear response associated with transmission components of the second device;
estimating a reception decoding metric based at least in part on the nonlinear response associated with the second device or based at least in part on the signaling comprising an indication of the reception encoding metric; and
communicating with the second device based at least in part on the reception decoding metric.
16. The method of claim 15 , further comprising:
transmitting a grant scheduling a transmission comprising the signaling, wherein receiving the signaling is based at least in part on the grant, and wherein the grant comprises an uplink grant in a downlink control information message and the scheduled transmission comprises an uplink shared channel transmission.