Machine learning based digital pre-distortion for power amplifiers
US-2021391832-A1 · Dec 16, 2021 · US
US11770145B2 · US · B2
| Field | Value |
|---|---|
| Publication number | US-11770145-B2 |
| Application number | US-202217885187-A |
| Country | US |
| Kind code | B2 |
| Filing date | Aug 10, 2022 |
| Priority date | Aug 27, 2021 |
| Publication date | Sep 26, 2023 |
| Grant date | Sep 26, 2023 |
A practical reading order for non-experts. Skip the full description unless you need deep technical detail.
What the patent document calls the invention.
A short plain-language summary of the technical disclosure.
Who owns or filed the patent and who is credited as inventor.
Filing, priority, publication, and grant dates set the timeline.
The legal scope of protection — read this for what is actually claimed.
Technology tags used to group this patent with similar filings.
Prior art links and similar publications in this corpus.
Official abstract text for this publication.
An electronic device configured to apply, to a first power amplifier (PA) input, one or more updated memory digital pre-distorter (mDPD) coefficient values is provided. The electronic device includes a processor; and a memory including a non-transitory computer readable storage medium storing instructions that, when executed, cause the processor to preload, from values stored in the memory of the electronic device, one or more mDPD coefficient values; transmit a training signal sequence while using the preloaded one or more mDPD coefficient values; receive the training signal sequence; update the one or more mDPD coefficient values based on the transmitted training signal sequence, the received training signal sequence, and the preloaded one or more mDPD coefficient values; and apply the updated one or more mDPD coefficient values to distort the first PA input.
Opening claim text (preview).
What is claimed is: 1. An electronic device configured to apply, to a first power amplifier (PA) input, one or more updated memory digital pre-distorter (mDPD) coefficient values, the electronic device comprising: a processor; and a memory including a non-transitory computer readable storage medium storing instructions that, when executed, cause the processor to: preload, from values stored in the memory of the electronic device, one or more mDPD coefficient values; transmit a first training signal sequence while using the preloaded one or more mDPD coefficient values; receive the first training signal sequence; update the one or more mDPD coefficient values based on the transmitted first training signal sequence, the received first training signal sequence, and the preloaded one or more mDPD coefficient values; and apply the updated one or more mDPD coefficient values to distort the first PA input. 2. The electronic device of claim 1 , wherein applying the updated mDPD coefficient values to distort the PA input linearizes an output of the PA across a range of PA inputs. 3. The electronic device of claim 1 , wherein preloading the one or more mDPD coefficient values includes preloading a plurality of mDPD coefficient values corresponding to a plurality of input PA power levels or frequencies. 4. The electronic device of claim 3 , wherein the plurality of input PA power levels or frequencies are spaced apart by a predetermined power level spacing value or a predetermined frequency spacing value. 5. The electronic device of claim 1 , wherein updating the one or more mDPD coefficient values is performed for PA input values above a predetermined power level threshold. 6. The electronic device of claim 1 , wherein the instructions, when executed, further cause the processor to: transmit a request to send (RTS) signal to reserve a channel for a transmit opportunity (TXOP) duration prior to transmitting the first training signal sequence. 7. The electronic device of claim 6 , wherein the TXOP duration is greater than or equal to a duration of the first training signal sequence. 8. The electronic device of claim 6 , wherein the RTS signal is transmitted in response to a temperature of the electronic device being sensed to be equal to or greater than a predetermined value, after a predetermined amount of time, if an error vector magnitude (EVM) is equal to or greater than a predetermined number, or upon an initial calibration of the electronic device. 9. The electronic device of claim 1 , wherein receiving the first training signal sequence includes receiving a plurality of training sequence copies. 10. The electronic device of claim 1 , wherein the instructions, when executed, further cause the processor to: preload the updated one or more mDPD coefficient values; and apply the updated one or more mDPD coefficient values to distort a second PA input without transmitting a second training signal. 11. A method of applying, to a first power amplifier (PA) input, one or more updated memory digital pre-distorter (mDPD) coefficient values, the method performed by an electronic device and comprising: preloading, from values stored in a memory of the electronic device, one or more mDPD coefficient values; transmitting a first training signal sequence while using the preloaded one or more mDPD coefficient values; receiving the first training signal sequence; updating the one or more mDPD coefficient values based on the transmitted first training signal sequence, the received first training signal sequence, and the preloaded one or more mDPD coefficient values; and applying the updated one or more mDPD coefficient values to distort the first PA input. 12. The method of claim 11 , wherein applying the updated mDPD coefficient values to distort the PA input linearizes an output of the PA across a range of PA inputs. 13. The method of claim 11 , wherein preloading the one or more mDPD coefficient values includes preloading a plurality of mDPD coefficient values corresponding to a plurality of input PA power levels or frequencies. 14. The method of claim 13 , wherein the plurality of input PA power levels or frequencies are spaced apart by a predetermined power level spacing value or a predetermined frequency spacing value. 15. The method of claim 11 , wherein updating the one or more mDPD coefficient values is performed for PA input values above a predetermined power level threshold. 16. The method of claim 11 , further comprising: transmitting a request to send (RTS) signal to reserve a channel for a transmit opportunity (TXOP) duration prior to transmitting the first training signal sequence. 17. The method of claim 16 , wherein the TXOP duration is greater than or equal to a duration of the first training signal sequence. 18. The method of claim 16 , wherein the RTS signal is transmitted in response to a temperature of the electronic device being sensed to be equal to or greater than a predetermined value, after a predetermined amount of time, if an error vector magnitude (EVM) is equal to or greater than a predetermined number, or upon an initial calibration of the electronic device. 19. The method of claim 11 , wherein receiving the first training signal sequence includes receiving a plurality of training sequence copies. 20. The method of claim 11 , further comprising: preloading the updated one or more mDPD coefficient values; and applying the updated one or more mDPD coefficient values to distort a second PA input without transmitting a second training signal sequence.
with means for limiting noise, interference or distortion (H04B1/0483 takes precedence) · CPC title
with linearisation using predistortion · CPC title
Related publications grouped by family.
Answers are generated from the same data shown on this page.