Neural-Network Constellation Modulation for Phase-Noise Robust Uplink
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing modulation methods such as QAM and APSK suffer significant performance loss due to phase noise, and adaptive modulation and coding (AMC) fail to account for non-linear factors like phase noise, leading to substantial impact on transmission performance.
Innovation Solution
A terminal equipped with a control unit that maps bit sequences to indices and pre-trains a neural network to output modulated symbols, using a transmitting unit to transmit symbols selected based on a constellation generated by the pre-trained NN, which considers phase noise variance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If higher frequency and wider bandwidth are used for transmission, then data transmission speed is improved, but phase noise increases causing performance degradation
Solution Approach 1:
The patent changes the modulation scheme from conventional QAM/APSK to spiral constellation modulation, which is specifically designed to be robust against phase noise. The spiral constellation's continuous rotational symmetry allows it to maintain performance even when phase noise is present, effectively changing the modulation parameter to counteract the harmful phase noise effect at higher frequencies
Solution Approach 2:
The patent converts the harmful phase noise into a beneficial factor by designing the spiral constellation such that the phase noise actually helps rotate the constellation points along the spiral path, maintaining their relative positions and detection accuracy. This transforms what was previously a degrading factor into an element that does not harm performance
2Device complexity
If existing modulation methods (QAM, APSK) are used, then device complexity is low, but performance loss due to phase noise is significant
Solution Approach 1:
The patent changes the fundamental parameter of constellation geometry from the standard rectangular (QAM) or circular (APSK) arrangements to a spiral pattern. This spiral parameter change provides inherent robustness against phase noise while maintaining similar implementation complexity, as the spiral constellation can be generated using straightforward mathematical formulas similar to conventional modulations
3Adaptability or versatility
If adaptive modulation and coding is implemented, then adaptability to channel conditions is improved, but non-linear factors like phase noise are not accounted for causing performance impact
Solution Approach 1:
The patent introduces dynamic adaptation by selecting different spiral constellation parameters (such as spiral density, rotation speed, and point distribution) based on the measured phase noise variance. This dynamic adjustment allows the modulation scheme to adapt to changing channel conditions while specifically accounting for phase noise characteristics, unlike static conventional AMC schemes
Solution Approach 2:
The patent implements a feedback mechanism where the receiver measures the phase noise variance and feeds this information back to the transmitter. The transmitter then uses this feedback to adjust the spiral constellation parameters, creating a closed-loop adaptive system that continuously optimizes performance in the presence of phase noise
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A terminal includes: a control unit configured to: map bit sequences to indices; output one-hot encoder vectors associated with the indices; and pre-train a neural network (NN) to output modulated symbols in response to the one-hot encoder vectors and a variance of phase noise as inputs; and a transmitting unit configured to carry out a transmission to a base station by using modulated symbols that are selected based on a constellation generated by the pre-trained NN.