Weighted error optimization for digital pre-distortion
Various aspects of the present disclosure generally relate to wireless communication. In some aspects, a wireless node may receive a configuration indicating a parameter of a signal to be optimized for a portion of a frequency range. The wireless node may transform a feedback signal and a reference signal into a frequency domain. The wireless node may generate an error signal based at least in part on transforming the feedback signal and the reference signal. The wireless node may assign weights to the error signal to generate a weighted error signal. The weights may be assigned to the error signal in the portion of the frequency range and a remaining portion of the frequency range according to the configuration. The wireless node may transmit the signal based at least in part on utilizing the weighted error signal to apply digital pre-distortion to the signal. Numerous other aspects are described.
1. A method of wireless communication performed by a wireless node, comprising:
receiving a configuration indicating one or more parameters of a signal to be optimized for a portion of a frequency range over which the signal is transmitted;
transforming a feedback signal and a reference signal from a time domain into a frequency domain;
generating an error signal based at least in part on the feedback signal and the reference signal being transformed into the frequency domain;
assigning weights to the error signal to generate a weighted error signal, wherein the weights are assigned to the error signal in the portion of the frequency range and a remaining portion of the frequency range according to the configuration; and
transmitting the signal based at least in part on applying digital pre-distortion (DPD) to the signal, wherein the DPD is computed based at least in part on the weighted error signal.
2. The method of claim 1 , wherein the configuration indicates that an adjacent channel leakage ratio parameter is optimized over an error vector magnitude parameter, and wherein assigning the weights to the error signal to generate the weighted error signal comprises:
assigning a first weight to an out-of-channel portion of the error signal and a second weight to an in-channel portion of the error signal, wherein the first weight is a higher weight relative to the second weight.
3. The method of claim 1 , wherein the configuration indicates that an error vector magnitude parameter is optimized over an adjacent channel leakage ratio parameter, and wherein assigning the weights to the error signal to generate the weighted error signal comprises:
assigning a first weight to an in-channel portion of the error signal and a second weight to an out-of-channel portion of the error signal, wherein the first weight is a higher weight relative to the second weight.
4. The method of claim 1 , wherein the configuration indicates that an adjacent channel leakage ratio parameter associated with a side-band is optimized, and wherein assigning the weights to the error signal to generate the weighted error signal comprises:
assigning a first weight to a portion of the error signal associated with the side-band and a second weight to a remaining portion of the error signal, wherein the first weight is a higher weight relative to the second weight.
5. The method of claim 1 , wherein the DPD is computed based at least in part on a memoryless model, a memory polynomial, a direct learning architecture, an indirect learning architecture, an adaptive calibration process, or a static calibration process.
6. The method of claim 1 , wherein the configuration indicates an in-band frequency range and a weight coefficient for the portion of the frequency range, and wherein assigning the weights to the error signal to generate the weighted error signal comprises:
applying the weight coefficient to the portion of the error signal associated with the portion of the frequency range based at least in part on an in-band frequency associated with the wireless node corresponding to the in-band frequency indicated in the configuration.
7. The method of claim 1 , wherein the wireless node comprises a user equipment, a base station, a central unit, a distributed unit, or a transmit receive point.
8. A wireless node for wireless communication, comprising:
a memory; and
one or more processors, coupled to the memory, configured to:
receive a configuration indicating one or more parameters of a signal to be optimized for a portion of a frequency range over which the signal is transmitted;
transform a feedback signal and a reference signal from a time domain into a frequency domain;
generate an error signal based at least in part on the feedback signal and the reference signal being transformed into the frequency domain;
assign weights to the error signal to generate a weighted error signal, wherein the weights are assigned to the error signal in the portion of the frequency range and a remaining portion of the frequency range according to the configuration; and
transmit the signal based at least in part on applying digital pre-distortion (DPD) to the signal, wherein the DPD is computed based at least in part on the weighted error signal.
9. The wireless node of claim 8 , wherein the configuration indicates that an adjacent channel leakage ratio parameter is optimized over an error vector magnitude parameter, and wherein the one or more processors, to assign the weights to the error signal to generate the weighted error signal, are configured to:
assign a first weight to an out-of-channel portion of the error signal and a second weight to an in-channel portion of the error signal, wherein the first weight is a higher weight relative to the second weight.
10. The wireless node of claim 8 , wherein the configuration indicates that an error vector magnitude parameter is optimized over an adjacent channel leakage ratio parameter, and wherein the one or more processors, to assign the weights to the error signal to generate the weighted error signal, are configured to:
assign a first weight to an in-channel portion of the error signal and a second weight to an out-of-channel portion of the error signal, wherein the first weight is a higher weight relative to the second weight.
11. The wireless node of claim 8 , wherein the configuration indicates that an adjacent channel leakage ratio parameter associated with a side-band is optimized, and wherein the one or more processors, to assign the weights to the error signal to generate the weighted error signal, are configured to:
assign a first weight to a portion of the error signal associated with the side-band and a second weight to a remaining portion of the error signal, wherein the first weight is a higher weight relative to the second weight.
12. The wireless node of claim 8 , wherein the DPD is computed based at least in part on a memoryless model, a memory polynomial, a direct learning architecture, an indirect learning architecture, an adaptive calibration process, or a static calibration process.
13. The wireless node of claim 8 , wherein the configuration indicates an in-band frequency range and a weight coefficient for the portion of the frequency range, wherein the one or more processors, to assign the weights to the error signal to generate the weighted error signal, are configured to:
apply the weight coefficient to the portion of the error signal associated with the portion of the frequency range based at least in part on an in-band frequency associated with the wireless node corresponding to the in-band frequency indicated in the configuration.
14. The wireless node of claim 8 , wherein the wireless node comprises a user equipment, a base station, a central unit, a distributed unit, or a transmit receive point.
15. A non-transitory computer-readable medium storing a set of instructions for wireless communication, the set of instructions comprising:
one or more instructions that, when executed by one or more processors of a wireless node, cause the wireless node to:
receive a configuration indicating one or more parameters of a signal to be optimized for a portion of a frequency range over which the signal is transmitted;
transform a feedback signal and a reference signal from a time domain into a frequency domain;
generate an error signal based at least in part on the feedback signal and the reference signal being transformed into the frequency domain;
assign weights to the error signal to generate a weighted error signal, wherein the weights are assigned to the error signal in the portion of the frequency range and a remaining portion of the frequency range according to the configuration; and
transmit the signal based at least in part on applying digital pre-distortion (DPD) to the signal, wherein the DPD is computed based at least in part on the weighted error signal.
16. The non-transitory computer-readable medium of claim 15 , wherein the configuration indicates that an adjacent channel leakage ratio parameter is optimized over an error vector magnitude parameter, and wherein the one or more instructions, that cause the wireless node to assign the weights to the error signal to generate the weighted error signal, cause the wireless node to:
assign a first weight to an out-of-channel portion of the error signal and a second weight to an in-channel portion of the error signal, wherein the first weight is a higher weight relative to the second weight.
17. The non-transitory computer-readable medium of claim 15 , wherein the configuration indicates that an error vector magnitude parameter is optimized over an adjacent channel leakage ratio parameter, and wherein the one or more instructions, that cause the wireless node to assign the weights to the error signal to generate the weighted error signal, cause the wireless node to:
assign a first weight to an in-channel portion of the error signal and a second weight to an out-of-channel portion of the error signal, wherein the first weight is a higher weight relative to the second weight.
18. The non-transitory computer-readable medium of claim 15 , wherein the configuration indicates that an adjacent channel leakage ratio parameter associated with a side-band is optimized, and wherein the one or more instructions, that cause the wireless node to assign the weights to the error signal to generate the weighted error signal, cause the wireless node to:
assign a first weight to a portion of the error signal associated with the side-band and a second weight to a remaining portion of the error signal, wherein the first weight is a higher weight relative to the second weight.
19. The non-transitory computer-readable medium of claim 15 , wherein the DPD is computed based at least in part on a memoryless model, a memory polynomial, a direct learning architecture, an indirect learning architecture, an adaptive calibration process, or a static calibration process.
20. The non-transitory computer-readable medium of claim 15 , wherein the configuration indicates a weight coefficient associated with the portion of the frequency range and an in-band frequency range, and wherein the one or more instructions, that cause the wireless node to assign the weights to the error signal to generate the weighted error signal, cause the wireless node to:
apply the weight coefficient to the portion of the error signal associated with the portion of the frequency range based at least in part on an in-band frequency associated with the wireless node corresponding to the in-band frequency indicated in the configuration.
21. The non-transitory computer-readable medium of claim 15 , wherein the wireless node comprises a user equipment, a base station, a central unit, a distributed unit, or a transmit receive point.
22. An apparatus for wireless communication, comprising:
means for receiving a configuration indicating one or more parameters of a signal to be optimized for a portion of a frequency range over which the signal is transmitted;
means for transforming a feedback signal and a reference signal from a time domain into a frequency domain;
means for generating an error signal based at least in part on the feedback signal and the reference signal being transformed into the frequency domain;
means for assigning weights to the error signal to generate a weighted error signal, wherein the weights are assigned to the error signal in the portion of the frequency range and a remaining portion of the frequency range according to the configuration; and
means for transmitting the signal based at least in part on applying digital pre-distortion to the signal, wherein the digital pre-distortion is computed based at least in part on the weighted error signal.
23. The apparatus of claim 22 , wherein the configuration indicates that an adjacent channel leakage ratio parameter is optimized over an error vector magnitude parameter, and wherein the means for assigning the weights to the error signal to generate the weighted error signal comprises:
means for assigning a first weight to an out-of-channel portion of the error signal and a second weight to an in-channel portion of the error signal, wherein the first weight is a higher weight relative to the second weight.
24. The apparatus of claim 22 , wherein the configuration indicates that an error vector magnitude parameter is optimized over an adjacent channel leakage ratio parameter, and wherein the means for assigning the weights to the error signal to generate the weighted error signal comprises:
means for assigning a first weight to an in-channel portion of the error signal and a second weight to an out-of-channel portion of the error signal, wherein the first weight is a higher weight relative to the second weight.
25. The apparatus of claim 22 , wherein the configuration indicates that an adjacent channel leakage ratio parameter associated with a side-band is optimized, and wherein the means for assigning the weights to the error signal to generate the weighted error signal comprises:
means for assigning a first weight to a portion of the error signal associated with the side-band and a second weight to a remaining portion of the error signal, wherein the first weight is a higher weight relative to the second weight.
26. The apparatus of claim 22 , wherein the digital pre-distortion is computed based at least in part on a memoryless model, a memory polynomial, a direct learning architecture, an indirect learning architecture, an adaptive calibration process, or a static calibration process.
27. The apparatus of claim 22 , wherein the configuration indicates a weight coefficient associated with the portion of the frequency range and an in-band frequency range, and wherein the means for assigning the weights to the error signal to generate the weighted error signal comprises:
means for applying the weight coefficient to the portion of the error signal associated with the portion of the frequency range based at least in part on an in-band frequency associated with the apparatus corresponding to the in-band frequency indicated in the configuration.
28. The apparatus of claim 22 , wherein the apparatus comprises a user equipment, a base station, a central unit, a distributed unit, or a transmit receive point.