In this paper, we consider transmissions with superimposed (SI) demodulation-reference-symbol (DMRS) and data in orthogonal frequency-division multiplexing (OFDM) based multiple-input multiple-output (MIMO) systems. First, we derive an analytical framework to characterize the iterative behavior between the mean-square errors (MSEs) of channel estimation (CE) and MIMO detection (MD) within an iterative CE and detection (ICED) process. This framework is subsequently utilized to optimize power allocation and pilot patterns between the DMRS and data symbols for SI-DMRS transmission. Second, we design an artificial intelligence (AI) based receiver built upon Transformer encoders for SI-DMRS transmissions, which incorporates an iterative CE and detection (ICED) structure. Simulation results demonstrate that the proposed AI-ICED receiver, combined with SI-DMRS, effectively increases spectral efficiency (SE) compared to conventional systems using non-overlapped DMRS and data symbols.
Figures & tables
Fig. 1: Example patterns of DMRS and data transmission in standard 5G-NR (top) versus with SI-DMRS (bottom). The bandwidth is 2 physical resource block (2PRB) with Nsc=24 , and two OFDM symbols are used for control channel such that Nsym=12 for the SI-DMRS case. In both cases, the transmit power per RE is normalized to unity. Under the SI-DMRS scheme, superimposing additional DMRS symbols onto data introduces no pilot overhead, however, because total transmit power is split between the DMRS and data components, both CE and MD become more challenging
Fig. 2: The equilibrium state of CE-MSE and MD-MSE based on Property 1 with ( a=1 , γ=2 , Nt=4 , N=264 , M=24 ).
Fig. 3: The effective MD-MSE based on MIESM mapping of p and t with ( a=1 , γ=2 , Nt=4 , N=264 , M=24 ) and σ2=−15 dB.
Fig. 4: 2D contour of effective MD-MSE for joint power allocations over (a,b) with ( γ=2 , Nt=4 , N=264 , M=24 ) and σ2=−15 dB.
Fig. 5: The minimal effective MIESM with different configurations of M , i.e., for superimposing more DMRS with data. The gains are limited even under the idea assumption that the de-nosing gain of CE linearly increases in the number of DMRS.
Fig. 6: The structure of the MIMO-OFDM system and the proposed AI-ICED receiver, along with details regarding the NN construction and configurations provided in Appendix F through I and Table III.
Fig. 7: The VWN-TPA-MoE architecture enhanced Transformer encoder design.
Fig. 8: CE-MSE over iteration stages for 4×4 MIMO and 16QAM modulation.
Fig. 9: BLER performance with the same configurations in Fig. 8.
Fig. 10: CE-MSE under 2×2 MIMO and 16-QAM across a wide SNR range.
Fig. 11: Throughput envelopes under the 2×2 and 16-QAM modulation.
Fig. 12: Throughput envelopes under the 4×4 and 16-QAM modulation.
Operation
Dense Transformer block
Proposed backbone
Latent memory width
dmodel
dvirtual=(n/m)dmodel
Q/K/V projections
O(Ldmodel2)
O(Ldmodel(rq+2r))
FFN computation
O(Ldmodeldff)
O(Ldmodeldff)
Attention score
O(L2dmodel)
O(L2dmodel)
TABLE I: Dominant inference complexity per stage.
Symbol
Description
Value
Nr×Nt
MIMO size
2×2 , 4×4
A
Modulation scheme
16QAM, 64QAM
Nsym
Number of OFDM symbols carrying data
12
Nsc
Active subcarriers
24
N
Number of REs carrying only data
240
M
Number of REs carrying both SI-DMRS and data
48
TABLE II: System parameters.
Modulation
a1
b1
a2
b2
a3
b3
QPSK
0.9810
1.0420
0.0190
4.2500
0.0000
0.0000
16-QAM
0.6053
0.2845
0.3541
1.2562
0.0406
5.3784
64-QAM
0.4076
0.0717
0.3951
0.3556
0.1973
1.8315
TABLE III: Three-term exponential MI mapping parameters.
Symbol
Description
Value
Transformer Backbone
dmodel
Latent dimension
512
Nhead
Number of attention heads
8
m/n
VWN memory / compute slots
2/3
dvirtual
Virtual memory width (n/m)⋅dmodel
768
rq/r
TPA query rank / key-value rank
16/16
TABLE IV: Hyperparameter Configuration of the Proposed AI-ICED Receiver
AI-based structured interference rejection has grown more popular because deep learning approaches can outperform traditional methods by jointly considering the signal of interest (SOI) and the signal mixture (SOI plus interference). This work builds on a previous AI-enabled approach utilizing autoregressive transformer-based models by adding a Finite Scalar Quantization (FSQ) tokenizer layer which aims to improve the interference rejection performance while keeping overall latency to a minimum. Additionally, we experiment with other inference optimization techniques with the goal of speeding up inference without much accuracy loss. We explore this space with an experiment where the SOI is a digitally modulated radio frequency (RF) signal and the structured interference is a digital television signal, an extremely common type of Orthogonal Frequency-Division Multiplexing (OFDM) transmission. Our results achieve low latency and increased interference rejection over traditional techniques and prior work with other AI-enabled methods. We demonstrate the benefits of the AI-enabled approaches via audio metrics such as Perceptual Evaluation of Speech Quality (PESQ). Additionally, we explore a variety of applications and detail how our interference rejection algorithm may be used in operationally-relevant scenarios.
AI-enhanced interference rejection in radio frequency (RF) transmissions has recently attracted interest because deep learning approaches trained on both the signal of interest (SOI) and the signal mixture (SOI plus interference) can outperform traditional approaches which only consider the SOI. The goal is to detect, demodulate, and decode signals over a range of signal-to-interference-plus-noise (SINR) levels without having a detailed, design-level knowledge of the interfering signal or the propagation conditions. Our present AI interference suppression results are based on Autoregressive Transformer Decoder models which exhibit orders of magnitude faster throughput at inference time than WaveNet models developed in earlier work. As a specific example, we investigate an analog FM "Walkie Talkie" radio signal of interest in the presence of an Orthogonal Frequency-Division Multiplexing (OFDM) interferer. This type of interferer is near-ubiquitous in the current RF landscape. Our results clearly show the benefits of transformer-based interference mitigation in tactical settings. We show that unintelligible transmissions become intelligible via metrics such as Perceptual Evaluation of Speech Quality (PESQ), while overall latency is kept to a minimum using readily available lightweight GPUs such as a Jetson AGX Orin. We believe these same techniques can also be applied to a broader set of national security scenarios, as well as having commercial applications.
One of the major transformative factors in 6G will be the integration of Artificial Intelligence (AI) to become a native part of Radio Access Network (RAN). While most physical-layer AI features have so far been evaluated in isolation using link-level simulations, their combined behavior in a realistic multi-cell, multi-UE deployment has remained largely unexplored. In this paper, we present system-level performance results when multiple uplink AI features are enabled together, achieved by integrating accurate link-level and system-level simulators. To infer state-of-the-art deep-learning-aided Multiple Input Multiple Output (MIMO) receivers under the dynamic allocations produced by a realistic uplink scheduler, we propose a mirrored data augmentation method that decouples receiver performance from scheduled allocation size. In addition to these Physical Layer (PHY) receiver features, we combine several recent advances in deep reinforcement learning to train uplink power control and link adaptation that outperform a heuristic baseline and further boost the gains obtainable from the AI receiver alone. The system-level results show that the combined AI features improve the mean uplink user throughput by roughly 27% compared to a non-AI baseline, confirming that the individual PHY and Medium Access Control (MAC) AI features provide complementary gains when deployed jointly.
Petteri Kela, Dani Korpi, Mikko Honkala
Nokia Technologies Espoo, Finland · Nokia Bell Labs Espoo, Finland