Invention Grant
- Patent Title: Machine learning for addressing transmit (Tx) non-linearity
-
Application No.: US17181927Application Date: 2021-02-22
-
Publication No.: US12156221B2Publication Date: 2024-11-26
- Inventor: June Namgoong , Taesang Yoo , Naga Bhushan , Krishna Kiran Mukkavilli , Tingfang Ji
- Applicant: QUALCOMM Incorporated
- Applicant Address: US CA San Diego
- Assignee: QUALCOMM Incorporated
- Current Assignee: QUALCOMM Incorporated
- Current Assignee Address: US CA San Diego
- Agency: QUALCOMM Incorporated
- Main IPC: H04W72/04
- IPC: H04W72/04 ; G06N3/08 ; H04W64/00 ; H04W72/12 ; H04W72/23 ; H04W72/52 ; H04W72/54 ; H04W84/02

Abstract:
A method of wireless communication by a transmitting device transforms a transmit waveform by an encoder neural network to control power amplifier (PA) operation with respect to non-linearities. The method also transmits the transformed transmit waveform across a propagation channel. A method of wireless communication by a receiving device receives a waveform transformed by an encoder neural network. The method also recovers, with a decoder neural network, the encoder input symbols from the received waveform. A transmitting device for wireless communication calculates distortion error based on a non-distorted digital transmit waveform and a distorted digital transmit waveform. The transmitting device also compresses the distortion error with an encoder neural network of an auto-encoder. The transmitting device transmits to a receiving device the compressed distortion error to compensate for power amplifier (PA) non-linearity.
Public/Granted literature
- US20210266875A1 MACHINE LEARNING FOR ADDRESSING TRANSMIT (Tx) NON-LINEARITY Public/Granted day:2021-08-26
Information query