.png){kind=icon}
Return
Multi-Channel Receiver Nonlinearity Cancellation Using Channel Speculation Passing Algorithm
.png){kind=icon}
OA
AI
DOI：10.1109/TCSII.2021.3096852.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
This brief investigates a linearization method for multi-channel receivers based on speculations over the decision symbols that are used to cancel out the third order harmonic distortions and inter-modulation products in a feedback scheme. Although the optimal solution requires joint speculations across all channels, we show that using only channel-by-channel speculation is sufficient to provide significant system improvement at a fraction of the complexity of the all-channel optimal solution. The output symbol from a channel is replaced by its speculative nearest constellation point and used by the following channels in an iterative fashion until the nonlinearity cancellation process minimizes the errors for all channels without jointly searching for the solution. Mathematical analysis showing fast convergence and low complexity of the proposed machine learning algorithm is provided. The simulation results of a 5-channel receiver with the proposed channel speculation passing (CSP) algorithm show the improvement in signal-to-noise and distortion ratio (SNDR) and bit error rate (BER).
Keywords:
Receivers
Baseband
Machine learning algorithms
Quadrature amplitude modulation
Bit error rate
Simulation
Signal to noise ratio
Speculation
linearization technique
multi-channel receiver
3rd order non-linearity
inter-modulation product
machine learning
reinforcement learning
Journal
I
IF:
4.9
Papers:
8.8K
Citations:
2.5W
Organization
Cited Papers
.png){kind=icon}
ShareSaveShareSaveShareSaveShareSaveShareSave
View more