Aspects of this disclosure relate to a receiver for digital predistortion (DPD). The receiver includes an analog-to-digital converter (ADC) having a sampling rate that is lower than a signal bandwidth of an output of a circuit having an input that is predistorted by DPD. DPD can be updated based on feedback from the receiver. According to certain embodiments, the receiver can be a narrowband receiver configured to observe sub-bands of the signal bandwidth. In some other embodiments, the receiver can include a sub-Nyquist ADC.

An example method for facilitating a high power efficient amplifier through digital pre-distortion (DPD) in cable network environments is provided and includes receiving a first signal and a second signal at a DPD coefficient finder in an amplifier module of a cable modem, the second signal including transformations of the first signal from distortions due to channel effects and amplifier nonlinearity, synchronizing the first signal and the second signal, removing the channel effects, computing a first vector representing an inverse of the nonlinearity of the amplifier, computing a second vector representing an inverse of certain channel effects and providing DPD coefficients to a DPD actuator, the DPD coefficients including the first vector and the second vector, the DPD actuator predistorting an input signal to the amplifier module with the DPD coefficients, such that an output signal from the amplifier module retains linearity relative to the input signal.

Example embodiments relate to machine learning based digital pre-distortion for power amplifiers. A device may amplify a signal with a power amplifier and transmit the signal. The signal may be received by an internal feedback receiver of the device. The device may further comprise a first machine learning model configured to emulate an external feedback receiver and to generate an emulated feedback signal based on the internal feedback signal. The device may further comprise a second machine learning model configured to determine digital pre-distortion parameters for the power amplifier based on the emulated feedback signal. Apparatuses, methods, and computer programs are disclosed.

Systems and methods for compensating for non-linearity of a non-linear subsystem using predistortion are disclosed. In one embodiment, a system includes a non-linear subsystem and a predistorter configured to effect predistortion of an input signal of the non-linear subsystem such that the predistortion compensates for a non-linear characteristic of the non-linear subsystem. In addition, the system includes a narrowband filter that filters a feedback signal that is representative of an output signal of the non-linear subsystem to provide a filtered feedback signal, and an adaptor that adaptively configures the predistorter based on the filtered feedback signal and a reference signal that is representative of an input signal of the non-linear subsystem. By utilizing the filtered feedback signal, rather than the feedback signal, a complexity, and therefore, cost of the adaptor is substantially reduced.

A RF-digital hybrid mode power amplifier system for achieving high efficiency and high linearity in wideband communication systems is disclosed. The present invention is based on the method of adaptive digital predistortion to linearize a power amplifier in the RF domain. The power amplifier characteristics such as variation of linearity and asymmetric distortion of the amplifier output signal are monitored by the narrowband feedback path and controlled by the adaptation algorithm in a digital module. Therefore, the present invention could compensate the nonlinearities as well as memory effects of the power amplifier systems and also improve performances, in terms of power added efficiency, adjacent channel leakage ratio and peak-to-average power ratio. The present disclosure enables a power amplifier system to be field reconfigurable and support multi-modulation schemes (modulation agnostic), multi-carriers and multi-channels. As a result, the digital hybrid mode power amplifier system is particularly suitable for wireless transmission systems, such as base-stations, repeaters, and indoor signal coverage systems, where baseband I-Q signal information is not readily available.

A device configured to perform wireless communication includes: a pre-distortion circuit configured to generate a pre-distorted input signal by performing pre-distortion on an input signal based on a parameter set comprising a plurality of coefficients; a power amplifier configured to generate an output signal by amplifying an RF signal based on the pre-distorted input signal; and a parameter obtaining circuit configured to obtain second memory polynomial modeling information corresponding to an operating frequency band based on first memory polynomial modeling information corresponding to each of a plurality of frequency sections and obtain a parameter set according to an indirect learning structure by using the second memory polynomial modeling information.

This invention aims to present a smart and dynamic power amplifier module that features both power combining and power sharing capabilities. The proposed flexible power amplifier (PA) module consists of a pre-processor, N PAs, and a post-processor. The pre-processor is an M-to-N wavefront (WF) multiplexer (muxer), while the post processor is a N-to-M WF de-multiplexer (demuxer), where N≧M≧2. Multiple independent signals can be concurrently amplified by a proposed multi-channel PA module with a fixed total power output, while individual signal channel outputs feature different power intensities with no signal couplings among the individual signals. In addition to basic configurations, some modules can be configured to feature both functions of parallel power amplifiers and also as M-to-M switches. Other programmable features include configurations of power combining and power redistribution functions with a prescribed amplitude and phase distributions, as well as high power PA with a linearizer.

A predistortion processing apparatus: an auxiliary feedback module, configured to: extract a nonlinear distortion signal from an analog signal, and input an obtained feedback signal corresponding to the nonlinear distortion signal into an auxiliary model coefficient training module; the auxiliary model coefficient training module, configured to: train an auxiliary coefficient according to the feedback signal and a predistortion signal, and transmit a first auxiliary coefficient obtained through training to a predistortion processing module; a radio frequency signal feedback module, configured to extract a fundamental wave feedback signal; a predistortion model coefficient training module, configured to: train a predistortion coefficient according to the predistortion signal and the fundamental wave feedback signal, and transmit an obtained predistortion coefficient to the predistortion processing module; the predistortion processing module, configured to: perform predistortion processing on an input intermediate frequency signal by performing nonlinear modeling according to the first auxiliary coefficient and the predistortion coefficient.

A linearization device (380) is disclosed, which is configured to determine pre-distortion parameters associated with a plurality of non-linear amplifiers (331, 332, 333, 334), each associated with a non-linear amplifier characteristic. The linearization device comprises determination circuitry (383), a first port (381) and a second port (382). The first port is configured to receive a plurality of channel coefficients indicative of channel characteristics of a plurality of communication paths (391, 392, 393, 394) between the plurality of non-linear amplifiers and a transmit observation receiver (370). The second port is configured to receive, from the transmit observation receiver, a sum of transmission signals generated by the plurality of non-linear amplifiers and transferred over the plurality of communication paths. The determination circuitry is configured to determine the pre-distortion parameters based on the received plurality of channel coefficients, the received sum of transmission signals, and a model of the non-linear amplifier characteristics of the non-linear amplifiers. Corresponding arrangement, wireless transmitter node, cloud based server node, method and computer program product are also disclosed.

Example embodiments relate to machine learning based digital pre-distortion for power amplifiers. A device may amplify a signal with a power amplifier and transmit the signal. The signal may be received by an internal feedback receiver of the device. The device may further comprise a first machine learning model configured to emulate an external feedback receiver and to generate an emulated feedback signal based on the internal feedback signal. The device may further comprise a second machine learning model configured to determine digital pre-distortion parameters for the power amplifier based on the emulated feedback signal. Apparatuses, methods, and computer programs are disclosed.