| 1. |
- He, Zonglong, 1994, et al.
(författare)
-
Experimental Demonstration of Learned Pulse Shaping Filter for Superchannels
- 2022
-
Ingår i: 2022 Optical Fiber Communications Conference and Exhibition, OFC 2022 - Proceedings.
-
Konferensbidrag (refereegranskat)abstract
- We demonstrate a pulse shaping filter enabled by machine learning for spectral superchannels. In contrast to a 1% roll-off root-raised cosine filter, our learned filter reduces the adaptive equalizer length by 47% for the same spectral efficiency.
|
|
| 2. |
- He, Zonglong, 1994, et al.
(författare)
-
Periodicity-Enabled Size Reduction of Symbol Based Predistortion for High-Order QAM
- 2022
-
Ingår i: Journal of Lightwave Technology. - 0733-8724 .- 1558-2213. ; 40:18, s. 6168-6178
-
Tidskriftsartikel (refereegranskat)abstract
- We experimentally demonstrate a novel size reduction approach for symbol-based look-up table (LUT) digital predistortion (DPD) of the transmitter impairments taking advantage of the periodicity in the pattern-dependent distortions. Compared to other reduced-size LUT schemes, the proposed method can significantly lessen the storage memory requirements with negligible performance penalty for high-order modulation formats. To further alleviate the storage memory restriction, a twice reduced-size LUT scheme is proposed to provide further size reduction. Importantly, given a targeted memory length, we verify the importance of averaging over sufficient occurrences of the patterns to obtain a well-performing LUT. Moreover, it is necessary to evaluate the performance of LUT-based DPD using random data. Finally, we demonstrate a neural network (NN) based nonlinear predistortion technique, which achieves nearly identical performance to the full-size LUT for all employed constellations and is robust against a change of modulation format. The proposed techniques are verified in a back-to-back transmission experiment of 20 Gbaud 64-QAM, 256-QAM, and 1024-QAM signals considering 3 and 5 symbol memory. The performance of the LUT-based DPD is further validated in a noise loading experiment.
|
|
| 3. |
- He, Zonglong, 1994, et al.
(författare)
-
Symbol-Based Supervised Learning Predistortion for Compensating Transmitter Nonlinearity
- 2021
-
Ingår i: 2021 European Conference on Optical Communication, ECOC 2021. - 9781665438681
-
Konferensbidrag (refereegranskat)abstract
- We experimentally demonstrate a symbol-based nonlinear digital predistortion (DPD) technique utilizing supervised learning, which is robust against a change of modulation format. Back-to-back transmission of 30 Gbaud 32, 64 and 256QAM confirms that our scheme significantly outperforms the baseline of arcsine-based predistortion.
|
|
| 4. |
- Song, Jinxiang, 1995, et al.
(författare)
-
Blind Frequency-Domain Equalization Using Vector-Quantized Variational Autoencoders
- 2023
-
Ingår i: 2023 European Conference on Optical Communications, ECOC 2023. ; In press
-
Konferensbidrag (refereegranskat)abstract
- We propose a novel frequency-domain blind equalization scheme for coherent optical communications. The method is shown to achieve similar performance to its recently proposed time-domain counterpart with lower computational complexity, while outperforming the commonly used CMA-based equalizers.
|
|
| 5. |
- Song, Jinxiang, 1995, et al.
(författare)
-
End-to-end Autoencoder for Superchannel Transceivers with Hardware Impairments
- 2021
-
Ingår i: 2021 Optical Fiber Communications Conference and Exhibition, OFC 2021 - Proceedings.
-
Konferensbidrag (refereegranskat)abstract
- We propose an end-to-end learning-based approach for superchannel systems impaired by non-ideal hardware component. Our system achieves up to 60% SER reduction and up to 50% guard band reduction compared with the considered baseline scheme.
|
|
| 6. |
- Song, Jinxiang, 1995, et al.
(författare)
-
Model-Based End-to-End Learning for WDM Systems With Transceiver Hardware Impairments
- 2022
-
Ingår i: IEEE Journal of Selected Topics in Quantum Electronics. - 1558-4542 .- 1077-260X. ; 28:4
-
Tidskriftsartikel (refereegranskat)abstract
- We propose an AE-based transceiver for a WDM system impaired by hardware imperfections. We design our AE following the architecture of conventional communication systems. This enables to initialize the AE-based transceiver to have similar performance to its conventional counterpart prior to training and improves the training convergence rate. We first train the AE in a single-channel system, and show that it achieves performance improvements by putting energy outside the desired bandwidth, and therefore cannot be used for a WDM system. We then train the AE in a WDM setup. Simulation results show that the proposed AE significantly outperforms the conventional approach. More specifically, it increases the spectral efficiency of the considered system by reducing the guard band by 37% and 50% for a root-raised-cosine filter-based matched filter with 10% and 1% roll-off, respectively. An ablation study indicates that the performance gain can be ascribed to the optimization of the symbol mapper, the pulse-shaping filter, and the symbol demapper. Finally, we use reinforcement learning to learn the pulse-shaping filter under the assumption that the channel model is unknown. Simulation results show that the reinforcement-learning-based algorithm achieves similar performance to the standard supervised end-to-end learning approach assuming perfect channel knowledge.
|
|
| 7. |
- Song, Jinxiang, 1995, et al.
(författare)
-
Over-the-fiber Digital Predistortion Using Reinforcement Learning
- 2021
-
Ingår i: 2021 European Conference on Optical Communication, ECOC 2021. - 9781665438681
-
Konferensbidrag (refereegranskat)abstract
- We demonstrate, for the first time, experimental over-the-fiber training of transmitter neural networks (NNs) using reinforcement learning. Optical back-to-back training of a novel NN-based digital predistorter outperforms arcsine-based predistortion with up to 60% bit-error-rate reduction.
|
|
| 8. |
- Song, Jinxiang, 1995, et al.
(författare)
-
Benchmarking and Interpreting End-to-end Learning of MIMO and Multi-User Communication
- 2022
-
Ingår i: IEEE Transactions on Wireless Communications. - 1558-2248 .- 1536-1276. ; 21:9, s. 7287-7298
-
Tidskriftsartikel (refereegranskat)abstract
- End-to-end autoencoder (AE) learning has the potential of exceeding the performance of human-engineered transceivers and encoding schemes, without a priori knowledge of communication-theoretic principles. In this work, we aim to understand to what extent and for which scenarios this claim holds true when comparing with fair benchmarks. Our particular focus is on memoryless multiple-input multiple-output (MIMO) and multi-user (MU) systems. Four case studies are considered: two point-to-point (closed-loop and open-loop MIMO) and two MU scenarios (MIMO broadcast and interference channels). For the point-to-point scenarios, we explain some of the performance gains observed in prior work through the selection of improved baseline schemes that include geometric shaping as well as bit and power allocation. For the MIMO broadcast channel, we demonstrate the feasibility of a novel AE method with centralized learning and decentralized execution. Interestingly, the learned scheme performs close to nonlinear vector-perturbation precoding and significantly outperforms conventional zero-forcing. Lastly, we highlight potential pitfalls when interpreting learned communication schemes. In particular, we show that the AE for the considered interference channel learns to avoid interference, albeit in a rotated reference frame. After de-rotating the learned signal constellation of each user, the resulting scheme corresponds to conventional time sharing with geometric shaping.
|
|
| 9. |
- Song, Jinxiang, 1995, et al.
(författare)
-
Benchmarking End-to-end Learning of MIMO Physical-Layer Communication
- 2020
-
Ingår i: 2020 IEEE Global Communications Conference, GLOBECOM 2020 - Proceedings.
-
Konferensbidrag (refereegranskat)abstract
- End-to-end data-driven machine learning (ML) of multiple-input multiple-output (MIMO) systems has been shown to have the potential of exceeding the performance of engineered MIMO transceivers, without any a priori knowledge of communication-theoretic principles. In this work, we aim to understand to what extent and for which scenarios this claim holds true when comparing with fair benchmarks. We study closed-loop MIMO, open-loop MIMO, and multi-user MIMO (MU-MIMO) and show that the gains of ML-based communication in the former two cases can be to a large extent ascribed to implicitly learned geometric shaping and bit and power allocation, not to learning new spatial encoders. For MU-MIMO, we demonstrate the feasibility of a novel method with centralized learning and decentralized executing, outperforming conventional zero-forcing. For each scenario, we provide explicit descriptions as well as open-source implementations of the selected neural-network architectures.
|
|
| 10. |
- Srinivasan, Muralikrishnan, 1991, et al.
(författare)
-
End-to-End Learning for VCSEL-based Optical Interconnects: State-of-the-Art, Challenges, and Opportunities
- 2023
-
Ingår i: Journal of Lightwave Technology. - 0733-8724 .- 1558-2213. ; 41:11, s. 3261-3277
-
Tidskriftsartikel (refereegranskat)abstract
- Optical interconnects (OIs) based on vertical-cavity surface-emitting lasers (VCSELs) are the main workhorse within data centers, supercomputers, and even vehicles, providing low-cost, high-rate connectivity. VCSELs must operate under extremely harsh and time-varying conditions, thus requiring adaptive and flexible designs of the communication chain. Such designs can be built based on mathematical models (model-based design) or learned from data (machine learning (ML) based design). Various ML techniques have recently come to the forefront, replacing individual components in the transmitters and receivers with deep neural networks. Beyond such component-wise learning, end-to-end (E2E) autoencoder approaches can reach the ultimate performance through co-optimizing entire parameterized transmitters and receivers. This tutorial paper aims to provide an overview of ML for VCSEL-based OIs, with a focus on E2E approaches, dealing specifically with the unique challenges facing VCSELs, such as the wide temperature variations and complex models.
|
|
