A Novel PAPR Reduction Scheme for OFDM System Based on Deep Learning
The DOI matches its Crossref record; 15 of the 17 references it cites were found in a registry or an index.
Abstract
High peak-to-average power ratio (PAPR) has been one of the major drawbacks of orthogonal frequency division multiplexing (OFDM) systems. In this letter, we propose a novel PAPR reduction scheme, known as PAPR reducing network (PRNet), based on the autoencoder architecture of deep learning. In the PRNet, the constellation mapping and demapping of symbols on each subcarrier is determined adaptively through a deep learning technique, such that both the bit error rate (BER) and the PAPR of the OFDM system are jointly minimized. We used simulations to show that the proposed scheme outperforms conventional schemes in terms of BER and PAPR.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Furthermore, DNN based architectures for symbol detection in MIMO systems have been proposed in [98], and a DNN-based localization method exploiting fingerprintbased and channel measurements for M-MIMO systems has been proposed in [99].”
From Quantum Machine Learning for 6G Communication Networks: State-of-the-Art and Vision for the Future (2019) · cites this paper as [98]
Citations
Cites
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Ioffe, S., & Szegedy, C. (2015) · arXiv · doi:10.48550/arxiv.1502.03167 · Cited by 27,818 · cited 1×
“The output of FC is fed into the Batchnorm unit, which normalizes the input of the ReLU unit such that the PRNet can be trained more efficiently [13].”
MethodBatch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Ioffe, S. (2024) · arXiv (Cornell University) · doi:10.57702/o9raffed · Cited by 14,214
(2010) · International Conference on Machine Learning · Cited by 13,995
(2010) · Journal of Machine Learning Research · doi:10.5555/1756006.1953039 · Cited by 4,051 · cited 1×
“, an autoencoder, which is usually used for denoising corrupted data [9].”
BackgroundConvolutional Radio Modulation Recognition Networks
O’Shea, T. J., Corgan, J., & Clancy, T. C. (2016) · Communications in Computer and Information Science · doi:10.1007/978-3-319-44188-7_16 · Cited by 1,584 · cited 1×
“Moreover, radio modulation recognition using convolution neural networks was investigated in [6].”
MethodAn Overview: Peak-to-Average Power Ratio Reduction Techniques for OFDM Signals
Jiang, T., & Wu, Y. (2008) · IEEE Transactions on Broadcasting · doi:10.1109/tbc.2008.915770 · Cited by 1,483 · cited 1×
“It is worth noting that in an OFDM system without PAPR reduction, the distribution of the real part of the time domain signal, R{x[n]}, and that of the imaginary part, I{x[n]}, become Gaussian distribution as N is sufficiently large according to the central limit theorem, which results in a high PAPR [11].”
BackgroundOFDM with reduced peak-to-average power ratio byoptimum combination of partial transmit sequences
Müller, S. H., & Huber, J. B. (1997) · Electronics Letters · doi:10.1049/el:19970266 · Cited by 1,303 · cited 1×
“Other notable schemes for PAPR reduction are signal scrambling techniques, such as partial transmission sequence (PTS) and selective mapping (SLM) [2], [3].”
BackgroundPerformance analysis of deliberately clipped OFDM signals
Ochiai, H., & Imai, H. (2002) · IEEE Transactions on Communications · doi:10.1109/26.975762 · Cited by 667 · cited 2×
“One of most well known schemes for reducing the PAPR in an OFDM system is the clipping scheme [1] in which the original signal is distorted deliberately such that the distribution of the transmitted signal is within the proper range of the power amplifier.”
BackgroundExponential companding technique for PAPR reduction in OFDM systems
Jiang, T., Yang, Y., & Song, Y.-H. (2005) · IEEE Transactions on Broadcasting · doi:10.1109/tbc.2005.847626 · Cited by 340 · cited 2×
“[4]; however, the BER of this system was degraded due to the signal distortion, just as it is in the clipping scheme.”
BackgroundMethodGeneralized Denoising Auto-Encoders as Generative Models
Bengio, Y., Yao, L., Alain, G., & Vincent, P. (2013) · arXiv · doi:10.48550/arxiv.1305.6663 · Cited by 324 · cited 2×
“In this paper, we have used an autoencoder of deep learning, which is one of the most well-known generative models in deep learning [12].”
BackgroundMethod
Research works printed but not linked: 1
- 2017, PRnet Github Code
Cited by
Items 201–258 of 258
Minimize Power Ratio (PR) in OFDM Using Tone Reservation Method
Upadhyaya, Y. K., & Kushwaha, A. K. (2020) · Advances in intelligent systems and computing · doi:10.1007/978-981-15-4032-5_12 · Cited by 1
PAPR Reduction Method based on In-phase/Quadrature Data Symbol Components in MIMO-OFDM Systems
Al‐Rayif, M. I. (2021) · Journal of Communications Software and Systems · doi:10.24138/jcomss-2021-0123 · Cited by 1
“Hence, numerous proposals for PAPR reduction have been developed, for both single-input-single-output (SISO) and multi-inputmulti-output (MIMO) systems, including tone reservation [4], clipping and filtering [5] and [12], block-coding [6] and [11], and probabilistic methods [2], [7], [8].”
BackgroundNeural Network-based scheme for PAPR reduction in OFDM Systems
Chisaguano, D. J. R., Grijalva, F., Paredes, M. C. P., & Carvajal-Rodriguez, J. (2019) · IEEE Ecuador Technical Chapters Meeting (ETCM) · doi:10.1109/etcm48019.2019.9014895 · Cited by 1
“In recent years, several works have addressed the PAPR problem through data-driven techniques using, e.g., neural networks [8, 9, 10, 11, 12].”
BackgroundMethodA Novel Multi-impairment Compensation Scheme Based on Deep Autoencoder for CO-OFDM System
Han, Y. J., Chen, Y., Huang, Y., Fu, J., Lin, S., & Yu, J. (2020) · Opto-Electronics and Communications Conference (OECC) · doi:10.1109/oecc48412.2020.9273675 · Cited by 1
“Recently, a deep learning model called autoencoder (AE) has been proposed for wireless [8], non-coherent optical [9] and visible light communications [10].”
BackgroundA Joint Scheme for PAPR Reduction of OFDM Signals based on 3-D Constellation Rotation Encryption
Lu, X., Lei, J., Li, W., & Shi, Y. (2020) · International Conference on Wireless Communications and Signal Processing (WCSP) · doi:10.1109/wcsp49889.2020.9299870 · Cited by 1
Experimental Evaluation of Machine learning based MIMO-OFDM System for Optimal PAPR and BER
Shobha, Y. K., & Rangaraju, H. G. (2021) · WSEAS TRANSACTIONS ON SYSTEMS AND CONTROL · doi:10.37394/23203.2021.16.27 · Cited by 1
Evaluasi Penerapan Algoritma Neural Network Sebagai Teknik Reduksi PAPR Pada Sistem OFDM
Ridwan, M., Gulo, M. M., Moegiharto, Y., Arifin, A., & Milchan, M. (2021) · INOVTEK Polbeng - Seri Informatika · doi:10.35314/isi.v6i1.1934 · Cited by 1
Development of Improved SoC PTS Algorithm for PAPR Reduction in OFDM Underwater Communication
Asha, M., & Surekha, T. P. (2021) · Lecture notes on data engineering and communications technologies · doi:10.1007/978-981-16-3728-5_48 · Cited by 1
Complexity Suppression of AutoEncoder for PAPR Reduction of OFDM Signals
Nishide, C., & Ohta, M. (2022) · IEEE Global Conference on Consumer Electronics (GCCE) · doi:10.1109/gcce56475.2022.10014220 · Cited by 1
“The model proposed by Kim et al.[1] has a five-layer AE-ENC and a five-layer AE-DEC, and each layer has 2048 units (even Kuwahara’s model[2] has 1024 units); it therefore requires a huge amount of computation.”
MethodPESTnet - Pre-IFFT PAPR Estimation using Neural Networks for Improved OFDM Systems
Mangipudi, P. K., Merugu, M., McNair, J. Y., Terry, J., & Veney, D. (2023) · IEEE Wireless Communications and Networking Conference · doi:10.1109/wcnc55385.2023.10118688 · Cited by 1
“Recently, PAPR reduction techniques use Deep Learning (DL)-based implementations of conventional PAPR reduction approaches [28], [14], [15], [25], while other unconventional algorithms rely on converting OFDM symbols using IFFTs to produce a result [16], [17], [24].”
MethodResultInfluentialDeep Learning-Enhanced Autoencoder for Multi-Carrier Wireless Systems
Aziz, M. A., Rahman, M. H., Tabassum, R., Sejan, M. A. S., Baek, M.-S., & Song, H. (2024) · Mathematics · doi:10.3390/math12233685 · Cited by 1
Kumar, R. (2025) · Sigma Journal of Engineering and Natural Sciences – Sigma Mühendislik ve Fen Bilimleri Dergisi · doi:10.14744/sigma.2025.00067 · Cited by 1
High Performance Signal Design for Optical OFDM Systems Using Variational Autoencoder
Luong, N. N., Nguyen, C. T., & Pham, T. V. (2026) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2026.3676058 · Cited by 1
“Simulation results demonstrated that this approach achieves superior PAPR reduction compared to conventional methods while maintaining a good BER performance.”
深層学習を用いたOFDM信号のPAPR及びOOBE同時抑圧手法
Kuwahara, R., & Ohta, M. (2021) · Institutional Repositories DataBase (IRDB) · Cited by 1
Featureless Wireless Communications using Enhanced AutoencoderPreprint
Zhang, R., Lin, W. J., & Chen, B. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2507.07474 · Cited by 1
“(Email: wei lin@mymail.sutd.edu.sg, binbin chen@sutd.edu.sg) constellation design [9] and for producing OFDM signals with a low peak-to-average power ratio (PAPR) [10] [2], all while maintaining robust signal detection performance.”
Power control with Machine Learning Techniques in Massive MIMO cellular and cell-free systems
Ahmadi, N. (2024) · University of Hertfordshire Research Archive (University of Hertfordshire) · doi:10.18745/th.27691 · Cited by 1
Constant Envelope DCT- and FFT- based Multicarrier Systems
Alsisi, R. H. (2018) · Scholarship@Western (Western University)
On Performance of Deep Learning for Harmonic Spur Cancellation in OFDM Systems
He, Z. (2020) · IEICE Transactions on Fundamentals of Electronics Communications and Computer Sciences · doi:10.1587/transfun.2019eal2114
Clipping Noise Estimation Based on Deep Complex Neural Network with Sparsity Constraint
Zhang, X., Zhang, Y., Chang, X., Wu, Y., & Pan, C. (2020) · IEEE Vehicular Technology Conference · doi:10.1109/vtc2020-spring48590.2020.9128525
“Unlike the works in [9] [12], this paper uses DL to achieve explicit estimation and mitigation of the clipping noise in generic OFDM receivers.”
MethodKim, D., Kim, D., & Lee, I.-H. (2020) · The Journal of the Korean Institute of Information and Communication Engineering
Ali, A., Chen, B., Raza, W., Sun, L. F., Ali, A., & Samo, A. H. (2020) · International journal of scientific and technology research
Learning based Transmitter/Receiver Design for the Nonlinear Channel
Namgoong, J., Yoo, T., Bhushan, N., Mukkavilli, K., & Ji, T. (2021) · International Conference on Communications · doi:10.1109/icc42927.2021.9501000
“A similar work by M. Kim et. al [10] proposed a “PAPR reducing network” (PRNet), based on the denoising autoencoder [11].”
Tian, S., Yang, M., Wang, J., Wang, R., & Adhikary, A. R. (2021) · IEICE Transactions on Fundamentals of Electronics Communications and Computer Sciences · doi:10.1587/transfun.2021eal2060
Networks, Communication, and Computing Vol. 2
(2021) · MDPI eBooks · doi:10.3390/books978-3-0365-1235-8
Autoencoder with Channel Estimation for Marine Communications
Lin, B., Duan, J., Han, M., & Cai, L. X. (2022) · Wireless networks · doi:10.1007/978-3-030-97307-0_3
Applications of artificial intelligence in 6G wireless communications
Alansari, A. A. (2021) · International Journal of Current Engineering and Technology · doi:10.14741/ijcet/v.11.4.5
A Study of Practical FPGA Implementation of AE-OP-OFDM
Kubota, K., Nishide, C., & Ohta, M. (2022) · IEEE Global Conference on Consumer Electronics (GCCE) · doi:10.1109/gcce56475.2022.10014051
“As a result, the complexity of the simplified AE was suppressed to 0.08% compared with that reported by Kim et al.[1].”
MethodResultInfluentialAnalytical Analysis of Bit Error Rate Performance of NOMA-OFDM for 5G Systems
Sahoo, S., & K, A. M. (2023) · International Conference on Computing, Communication and Networking Technologies (ICCCNT) · doi:10.1109/icccnt56998.2023.10307720
Deep Learning Based PAPR Reduction in 4G Mobile Communications
Gupta, S. C. (2024) · Lecture notes in networks and systems · doi:10.1007/978-981-97-2082-8_25
PRNet with Convolution Layer for PAPR Reduction of OFDM Signals and FPGA Implementation
Suzuki, A., & Ohta, M. (2024) · International Technical Conference on Circuits/Systems, Computers and Communications (ITC-CSCC) · doi:10.1109/itc-cscc62988.2024.10628425
“Recent advances in deep learning have led to the development of a method known as the PAPR-reducing network (PRNet) [3] for PAPR reduction.”
BackgroundMethodA Low-PAPR Scheme for Millimeter-Wave Communication Systems Based on Neural Network
Hou, L. (2024) · International Conference on Communication and Information Systems (ICCIS) · doi:10.1109/iccis63642.2024.10779431
“Another approach, presented in [6], introduces a PRNet based on neural network modules to reduce PAPR while preventing BER degradation through unsupervised learning.”
Communications using deep learning techniques
Pachpande, P. G. (2019) · Scholars Archive - University at Albany (University at Albany, State University of New York) · doi:10.54014/bbyy-ngty
Improvement of PAPR and OOBE Suppression of OFDM Signal Using Deep Learning
Okabe, M., Hayakawa, T., & Ohta, M. (2025) · International Technical Conference on Circuits/Systems, Computers and Communications (ITC-CSCC) · doi:10.1109/itc-cscc66376.2025.11137604
“There have been significant advances in the field of deep learning, and a method to use this technology called AutoEn-coder (AE) for PAPR reduction has been proposed [2].”
Wideband digital predistortion via synergistic bias extension and nonlinear feature clustering
Liang, Y. (2025) · Journal of Computational Methods in Sciences and Engineering · doi:10.1177/14727978251380817
AI-Empowered Semantic Communication for IoT
Shao, Y. (2025) · Wireless networks · doi:10.1007/978-3-031-98816-5_3
PAPR Reduction Method for CPM-OFDM System Based on AF-HDC-CPMNet
Wang, Z., Cao, N., Lü, H., & He, Y. (2025) · International Conference on Electronic Information Engineering and Computer Science (EIECS) · doi:10.1109/eiecs67708.2025.11283580
“Literature[8] proposed a novel deep learning-based PAPR reduction scheme for OFDM systems, namely PRNet.”
Receiver Design for Reliable and Secure Wireless Communications
Madeira, J. (2024) · Portuguese National Funding Agency for Science, Research and Technology (RCAAP Project by FCT)
Novel PAPR Reduction Techniques for OFDM Signals
Nguyen, K. T. (2025) · HARVEST (University of Saskatchewan)
김형철 (2024) · Seoul National University Open Repository (Seoul National University)
Digitale Signaalverwerkingsalgoritmen voor Lange-Afstand DSL en Spraak- en Audioverbetering
Sharma, M. (2024) · Lirias
Anusha, C., & Sundru, A. (2026) · Transactions on Emerging Telecommunications Technologies · doi:10.1002/ett.70346
“Recent advancements include the development of autoencoders for end-to-end communication systems [20], PAPR reduction [21], channel estimation [22], and hardware fault detection [23] using deep learning.”
Salih, N. M., Sulong, S. M., Idris, A., Ahmad, I., Said, M. S. M., & Zainal, M. (2025) · IEEE Conference on Systems, Process and Control · doi:10.1109/icspc68261.2025.11325826
“Emerging trends are evident through terms like "deep learning" (31, 98) and "NOMA" (29, 106), pointing toward AI-driven and non-orthogonal access innovations, while niche areas such as "underwater acoustic communication" (40, 104) and "optical wireless communication" (64, 177) demonstrate…”
B-Spline Neural Network-Based Multiuser MIMO-OFDM Nonlinear Uplink
Chen, S., Wang, P., Li, M. Y., Khalaf, E. F., Morfeq, A., & Alotaibi, N. D. (2026) · IEEE Transactions on Communications · doi:10.1109/tcomm.2026.3657448
“This is because the BS can implement highly complicated PAPR reduction techniques [17], [18], [19], [20], [21], [22], [23] to mitigate high PAPR of transmitted OFDM signals as well as employ predistorters [24], [25], [26], [27], [28], [29], [30] to compensate for nonlinear distortions of BS…”
Deep Learning PAPR Reduction Framework For 5G NR Uplink OFDM
Florence, F. D., Molla, A. S., Islam, M. K., & Kabir, M. H. (2025) · International Conference on Electrical Information and Communication Technology (EICT) · doi:10.1109/eict68394.2025.11355619
Deep-Learning-Based Waveform Design for Single-Carrier Satellite Communication Networks
Huleihel, Y., Hirsch, R., Sominsky, G., Ziv, R., & Permuter, H. H. (2026) · IEEE Transactions on Communications · doi:10.1109/tcomm.2026.3668150
“For instance, NNs in [14] simplify active constellation extension combined with CF, and autoencoder (AE)-based approaches [15] also optimize both PAPR and BER.”
Learned Superposition Precoding For PAPR Reduction of OFDMA System
Chang, B., & Kim, H. (2025) · Globecom · doi:10.1109/globecom59602.2025.11431863
“Numerical results show that the proposed method outperforms OFDMA, SC-FDMA, ICF algorithm, PRNet [12], and TDNN [14] in both PAPR and BER, while maintaining lower or comparable computational complexity.”
Anusha, C., & Sundru, A. (2026) · Research Square · doi:10.21203/rs.3.rs-8107878/v1
3次元NOMA無線網のためのAIを活用した物理層とMAC層の最適化法
Gendia, A. (2023) · Institutional Repositories DataBase (IRDB)
S 2 IE: Semantic and Side Information-Embedded PAPR Reduction for OFDM-Based Semantic Communications
Liu, C., Zhao, W., Zhang, Y., Lu, L., Xu, W., Ma, N., & Zhang, P. (2026) · IEEE Transactions on Network Science and Engineering · doi:10.1109/tnse.2026.3697611
“Moreover, several independent network architectures have also been proposed to learn nonlinear mapping methods, further enhancing the performance of PAPR reduction [25], [42], [43].”
InfluentialWaveform Optimization for Semantic Communication in OFDM System
Chen, W. R., & Qin, Z. (2026) · Textbooks in telecommunication engineering · doi:10.1007/978-3-032-11005-3_11
Kang, D., Park, U., & Oh, J. (2026) · doi:10.1109/imsrftt43070.2026.11602523
“While spectrally efficient, these signals exhibit a high peak-to-average power ratio (PAPR) [3], [4].”
Liu, X., Zhang, Y., Guo, J., Zhu, R., Wang, F., & Wang, L. (2026) · PLoS ONE · doi:10.1371/journal.pone.0354675
Coherence-Time-Compliant Amortized PTS for OTSM in 6G V2X
Kumar, A. R., Revathi, V., Masud, M., Alohali, M., Гаур, Н., & Nanthaamornphong, A. (2026) · IEEE Internet of Things Journal · doi:10.1109/jiot.2026.3718730
“Autoencoder-based methods, originating with PRNet [15], learn constellation mapping and demapping jointly so that the transmitted signal has a low PAPR by construction.”
Reducing PAPR in OFDM Systems Using AI
Touzani, H., ELghzaoui, M., Ghazaoui, Y., Mellouli, O., & Oumarbeh, A. (2026) · International Conference on Circuit, Systems and Communication (ICCSC) · doi:10.1109/iccsc71566.2026.11650454
“Gendia and Muta [7] proposed a synchronous neural architecture capable of effectively reducing PAPR while decreasing the complexity of conventional algorithms.”
A PAPR Reduction Method for OFDM Systems Based on CNN and Enhanced Residual Connections
Xiang, H., Wang, A., Shao, Y., Xu, Z., Kuang, F., & Zhang, X. (2026) · International Symposium on Semiconductor and Electronic Technology (ISSET) · doi:10.1109/isset70600.2026.11682251
“In recent years, DL has emerged as a promising alternative due to its powerful non-linear mapping and end-to-end optimization capabilities, enabling adaptive matching of complex system responses and achieving superior trade-offs between PAPR reduction and system complexity[8-10].”
Raveen, P., & Kumari, U. V. R. (2026) · International Journal of Advance Scientific Research and Engineering Trends · doi:10.65521/ijasret.v10i7.3716
“In 2018, Kim et al. [19] have implemented a new PAPR reduction strategy named PRNet with the autoencoder architecture.”
Ding, J., Tong, W., Zhu, M., Zhang, L., Zhang, J., Cai, Y., Hua, B., Lei, M., Ma, K., Pan, P., et al. (2026) · Chinese Optics Letters · doi:10.3788/col202624.100604
Metadata
- Authors
- Kim, M., Lee, W., & Cho, D.-H.
- Affiliations
- Korea Advanced Institute of Science and Technology (KR)
- Gyeongsang National University (KR)
- Venue
- IEEE Communications Letters
- Published
- 2018-03
- Volume
- 22
- Issue
- 3
- Pages
- 510-513
- ISSN
- 1089-7798 (ISSN-L)
- OpenAlex
- W2779699222
- Cited by
- 241
- References
- 17
- Citations by year
- 2026: 16 · 2025: 20 · 2024: 28 · 2023: 19 · 2022: 30 · 2021: 44 · 2020: 44 · 2019: 28 · 2018: 12
- FWCI
- 9.54
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- IEEE Communications Letters (publishedVersion)
- Funders
- Institute for Information & communications Technology Promotion (IITP)
- Korea government (MSIT) (2014-0-00282)
- Development of 5G Mobile Communication Technologies for Hyper-connected smart services
- Topics
- Physical Sciences › Engineering › Electrical and Electronic Engineering › PAPR reduction in OFDM
- Physical Sciences › Engineering › Electrical and Electronic Engineering › Advanced Power Amplifier Design
- Physical Sciences › Engineering › Electrical and Electronic Engineering › Advanced Wireless Communication Techniques
- Keywords
- peak-to-average power ratio reduction, peak-to-average power ratio, OFDM, autoencoder, deep learning, constellation mapping, bit error rate
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.