DeepOFW: Deep Learning-Driven OFDM-Flexible Waveform Modulation for Peak-to-Average Power Ratio Reduction

Ran Greidi; Kobi Cohen

cs.ITMar 15, 2026

DeepOFW: Deep Learning-Driven OFDM-Flexible Waveform Modulation for Peak-to-Average Power Ratio Reduction

Authors: Ran Greidi, Kobi Cohen

Organizations: School of Electrical and Computer Engineering, Ben-Gurion University of the Negev, Beer Sheva 8410501 Israel.

Abstract

Peak-to-average power ratio (PAPR) remains a major limitation of multicarrier modulation schemes such as orthogonal frequency-division multiplexing (OFDM), reducing power amplifier efficiency and limiting practical transmit power. In this work, we propose DeepOFW, a deep learning-driven OFDM-flexible waveform modulation framework that enables data-driven waveform design while preserving the low-complexity hardware structure of conventional transceivers. The proposed architecture is fully differentiable, allowing end-to-end optimization of waveform generation and receiver processing under practical physical constraints. Unlike neural transceiver approaches that require deep learning inference at both ends of the link, DeepOFW confines the learning stage to an offline or centralized unit, enabling deployment on standard transmitter and receiver hardware without additional computational overhead. The framework jointly optimizes waveform representations and detection parameters while explicitly incorporating PAPR constraints during training. Extensive simulations over 3GPP multipath channels demonstrate that the learned waveforms significantly reduce PAPR compared with classical OFDM while simultaneously improving bit error rate (BER) performance relative to state-of-the-art transmission schemes. These results highlight the potential of data-driven waveform design to enhance multicarrier communication systems while maintaining hardware-efficient implementations. An open-source implementation of the proposed framework is released to facilitate reproducible research and practical adoption.

Figures & tables

Notation	Description
$N$	Number of waveforms used in a single DeepOFW symbol
$M$	Number of bits per symbol
$B_{n,m}$	$m$ th bit from constellation symbol $n$
$f_{k}(\cdot)$	$k$ th waveform function
$T$	Transmit block symbol length
$T_{g}$	Transmit block guard interval length

Table I : Summary of Notation

Panel of Figure 1 — Figure 1: Illustration of the proposed OFDM-type transmission framework in continuous-time and discrete-time implementations.

Figure 2: Possible deployment strategy of DeepOFW in a star topology, suitable for WLAN 802.11 standards. Each station interacts with the AP to obtain $\mathbf{q}$ and $\mathbf{Q}$ . The channel state information is first delivered to the AP by the stations. The AP, equipment with DL accelerators, generate $\mathbf{q}_{i},\mathbf{Q}_{i}$ for station $i$ accordingly, and and communicates them back to the station.

Figure 3: An illustration of the element-wise multiplication detector $D_{\mathbf{q}}\{\mathbf{r}\}$ .

Figure 4: E2E model architecture. The transmitter–receiver chain is trained end-to-end to learn a complex waveform matrix $\mathbf{Q}$ and detector parameters $\mathbf{q}$ from instantaneous time-domain channel impulse responses. A GRU-based network generates $\mathbf{Q}$ and $\mathbf{q}$ , which are applied by the $\mathbf{Q}$ modulator and $\mathbf{Q}$ demodulator together with a one-tap detector to produce LLRs for decoding. An uncertainty network and a PAPR network predict per-sample weighting factors and a regularization coefficient, enabling joint optimization of BER and PAPR during training.

Figure 5: CCDF comparison between conventional OFDM (green curve with star markers) and DeepOFW. Each DeepOFW curve corresponds to a different RMS delay spread realization, color-coded from blue (low delay spread) to red (high delay spread).

Figure 6: BER performance of DeepOFW compared with conventional OFDM, SC/FDE, and E2EWL. Each point is averaged over 1,000 channel realizations with RMS delay spreads ranging from 10ns to 600ns.

Panel of Figure 7 — Figure 7: Frequency-domain representations of the first eight generated waveforms for different RMS delay spread conditions.

Panel of Figure 8 — Figure 8: Time-domain representations of the first eight DeepOFW-generated waveforms for an RMS delay spread of 10 ns.

Panel of Figure 10 — Figure 10: Time-domain representations of the first eight DeepOFW-generated waveforms for an RMS delay spread of 250 ns.

Wireless Communications

Wireless communications studies how information is sent over radio links and how networks manage signals, spectrum, and resources reliably.

See all 399 papers

Deep Learning-Driven Black-Box Doherty Power Amplifier with Pixelated Output Combiner and Extended Efficiency Range
Mar 17, 2026Han Zhou, Haojie Chang, David WidenNeural Surrogate Modeling Inverse Design
Tampere University, 33720 Tampere, Finland · Chalmers University of Technology, 41296 Gothenburg, Sweden
Learning During Detection: Continual Learning for Neural OFDM Receivers via DMRS
Feb 23, 2026Mohanad Obeed, Ming JianWireless Communications Online Continual Learning
Advanced Wireless Technology Lab, Huawei Technologies Canada Co. Ltd, ON K2K 3J1, Canada
Deep Learning for Joint Narrowband Interference Cancellation and Soft Demodulation in OFDM Systems
Jul 9, 2026Emmanouil Kavvousanos, Francky Catthoor, Vassilis PaliourasWireless Communications Convolutional Neural Networks
Department of Electrical and Computer Engineering, University of Patras, Greece · Department of Electrical and Computer Engineering, National Technical University of Athens, Greece

Mar 17, 2026J/K move · Enter open · S save

Deep Learning-Driven Black-Box Doherty Power Amplifier with Pixelated Output Combiner and Extended Efficiency Range

Han Zhou, Haojie Chang, David Widen

Tampere University, 33720 Tampere, Finland · Chalmers University of Technology, 41296 Gothenburg, Sweden

Neural Surrogate Modeling Inverse Design

Open paper AskPDF arXiv

This article presents a deep learning-driven inverse design methodology for Doherty power amplifiers (PA) with multi-port pixelated output combiner networks. A deep convolutional neural network (CNN) is developed and trained as an electromagnetic (EM) surrogate model to accurately and rapidly predict the S-parameters of pixelated passive networks. By leveraging the CNN-based surrogate model within a blackbox Doherty framework and a genetic algorithm (GA)-based optimizer, we effectively synthesize complex Doherty combiners that enable an extended back-off efficiency range using fully symmetrical devices. As a proof of concept, we designed and fabricated two Doherty PA prototypes incorporating three-port pixelated combiners, implemented with GaN HEMT transistors. In measurements, both prototypes demonstrate a maximum drain efficiency exceeding 74% and deliver an output power surpassing 44.1 dBm at 2.75 GHz. Furthermore, a measured drain efficiency above 52% is maintained at the 9-dB back-off power level for both prototypes at the same frequency. To evaluate linearity and efficiency under realistic signal conditions, both prototypes are tested using a 20-MHz 5G new radio (NR)-like waveform exhibiting a peak-to-average power ratio (PAPR) of 9.0 dB. After applying digital predistortion (DPD), each design achieves an average power added efficiency (PAE) above 51%, while maintaining an adjacent channel leakage ratio (ACLR) better than -60.8 dBc.

Abstract

Wireless Communications

Explore similar work

Deep Learning-Driven Black-Box Doherty Power Amplifier with Pixelated Output Combiner and Extended Efficiency Range

Learning During Detection: Continual Learning for Neural OFDM Receivers via DMRS

Deep Learning for Joint Narrowband Interference Cancellation and Soft Demodulation in OFDM Systems