Uplink DPD Signaling Using AI-Based PA Nonlinearity Measurement
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The identification of digital pre-distortion (DPD) functions for user equipment (UE) power amplifiers in wireless communication systems, particularly in 5G NR networks, is computationally intensive and resource-constrained, leading to inefficiencies and reduced uplink performance due to power back-off, which is not feasible for UEs with lower PA grades.
Innovation Solution
Network-assisted signaling using a gNB to measure UE PA nonlinearity through an artificial intelligence-based model, training a neural network to approximate DPD functions, and signaling DPD-related parameters like alpha and beta to the UE for pre-distortion implementation, reducing the computational burden on the UE.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If DPD functions are identified using conventional methods, then PA linearity is improved, but computational complexity and resource consumption increase significantly for UE
Solution Approach 1:
The network (gNB) acts as an intermediary to perform the computationally intensive DPD function identification. The gNB measures UE PA nonlinearity using uplink reference signals and trains an AI-based model to approximate DPD functions, then signals the parameters to the UE. This transfers the computational burden from the resource-constrained UE to the network, resolving the contradiction between achieving good PA linearity and minimizing UE computational complexity.
2Reliability
If power back-off is applied to mitigate PA nonlinearity, then signal quality is improved, but uplink throughput and efficiency deteriorate
Solution Approach 1:
The system performs preliminary action by identifying and compensating for PA nonlinearity through DPD before transmission. The gNB measures PA nonlinearity characteristics and provides DPD parameters to the UE in advance, enabling the UE to pre-distort the signal to counteract PA nonlinearity. This eliminates the need for power back-off while maintaining signal quality, thus resolving the contradiction between signal quality and uplink throughput.
3Reliability
If conventional DPD identification methods are used, then PA nonlinearity compensation is achieved, but signaling overhead and resource consumption increase
Solution Approach 1:
The invention changes the parameter representation from complete DPD function descriptions to compact parameter sets (alpha and beta parameters) that characterize PA nonlinearity. The gNB measures PA nonlinearity using uplink reference signals and extracts essential parameters that capture the dominant nonlinearity characteristics. This parameter compression maintains adequate nonlinearity compensation while significantly reducing signaling overhead and resource consumption.
Data Source
AI summary
Systems, methods, apparatuses, and computer program products for network-assisted signaling for uplink digital pre-distortion (DPD). A gNB may use an uplink reference signal (RS) to measure a user equipment's (UE's) power amplifier (PA) nonlinearity, where the UE may transmit its UE-specific RS with maximum transmit (Tx) power at a PA measurement window in the uplink. The gNB may train an artificial intelligence-based model to approximate the pre-distortion function (with PA parameters). The gNB may signal DPD-related information, and the UE may determine (and adjust) its DPD function based on the gNB signalling.