Information-Theoretic Tools for Optical Communications Engineers

Agrell, Erik; Secondini, Marco

doi:10.1109/ipcon.2018.8527126

Cited by 67 publications

(61 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…This allows the SBRNN autoencoders to significantly outperform FFNN at any examined distance. Moreover, our results indicate that the SBRNN designs can enable communication below the 4 · 10 −3 HD-FEC threshold [25] at distances of 70 km, which is a substantial increase over the achievable distance of 50 km below HD-FEC for the FFNN. The Tx-PAM2 & Rx-FFNN (Z = 61) system, whose receiver simultaneously processes relatively the same number of samples as the SBRNN (488 to 480), is as well outperformed by both the vanilla and the LSTM-GRU designs at all distances up to 80 km.…”

Section: System Performance Validationmentioning

confidence: 75%

End-to-end optimized transmission over dispersive intensity-modulated channels using bidirectional recurrent neural networks

et al. 2019

View full text Add to dashboard Cite

We propose an autoencoding sequence-based transceiver for communication over dispersive channels with intensity modulation and direct detection (IM/DD), designed as a bidirectional deep recurrent neural network (BRNN). The receiver uses a sliding window technique to allow for efficient data stream estimation. We find that this sliding window BRNN (SBRNN), based on end-to-end deep learning of the communication system, achieves a significant bit-error-rate reduction at all examined distances in comparison to previous block-based autoencoders implemented as feed-forward neural networks (FFNNs), leading to an increase of the transmission distance. We also compare the end-to-end SBRNN with a state-of-the-art IM/DD solution based on two level pulse amplitude modulation with an FFNN receiver, simultaneously processing multiple received symbols and approximating nonlinear Volterra equalization. Our results show that the SBRNN outperforms such systems at both 42 and 84 Gb/s, while training fewer parameters. Our novel SBRNN design aims at tailoring the end-to-end deep learning-based systems for communication over nonlinear channels with memory, such as the optical IM/DD fiber channel.blocks are not included in the design structure. Thus, the inter-block interference is treated as extra noise and, as a consequence, the achievable performance, in terms of CD that can be compensated and hence transmission distance, of such systems is limited by the block size.In this work, we address the limitations of the FFNN design for communication over nonlinear channels with memory by implementing sequence-based end-to-end deep learning transceivers using recurrent neural networks (RNN) [1,9]. RNNs have been recently demonstrated as a viable receiver-only signal processing solution in passive optical networks (PON) [10]. We use RNNs to design an end-to-end optimized fiber-optic system resilient to the nonlinearities and inter-symbol interference (ISI) present in IM/DD communications over dispersive channels. More specifically, since CD causes ISI from both preceding and succeeding symbols, we employ in our design bidirectional RNNs (BRNN) [11]. We operate the trained BRNN transceivers in a sliding window sequence estimation scheme (SBRNN), which allows us to estimate the data stream efficiently [12,13]. In contrast to [12,13], where the neural network processing is only at the receiver side, in our work we employ BRNN structures at both transmitter and receiver to allow end-to-end optimization of the transmission over the communication channel. Two variations of the recurrent cell in the RNN structure are examined, a straightforward vanilla concatenation as well as the long short-term memory gated recurrent unit structure (LSTM-GRU), specifically designed to handle long term dependencies in the sequence [1,[14][15][16]. We find that the LSTM-GRU design has a slightly superior bit error rate (BER) performance compared to the vanilla SBRNN, however at a higher computational cost.Our study shows that both SBRNN systems, specifically design...

show abstract

Section: System Performance Validationmentioning

confidence: 75%

End-to-end optimized transmission over dispersive intensity-modulated channels using bidirectional recurrent neural networks

et al. 2019

View full text Add to dashboard Cite

show abstract

“…The performance metric considered to compare the receiver configurations under test is the received SNR required for a BER at the KP4 forward error correction (FEC) threshold (BER = 2.24 · 10 −4 [49]). The receivers will then be benchmarked considering the SNR penalty, i.e., the difference in required receiver SNR, with respect to a simple reference receiver.…”

Section: Short-reach Transmission Systemmentioning

confidence: 99%

Reservoir-Computing Based Equalization With Optical Pre-Processing for Short-Reach Optical Transmission

Ros

Ranzini

Bülow

et al. 2020

IEEE J. Select. Topics Quantum Electron.

View full text Add to dashboard Cite

“…Traditionally, the performance requirement for the optical layer has been a BER after FEC decoding down to 10 −15 following standards for fiber communications [2], [25]. More modern performance metrics are based on information theory, which quantifies achievable information rates (AIRs) to lowerbound the capacity.…”

Section: A Achievable Rates and Metrics As Post-fec Ber Predictormentioning

confidence: 99%

“…The FEC is assumed to be a DVB-S2 low-density parity-check code [46] with codeword length n c = 64800 and code rate R c = 5/6. The modulation 2 Here "instance" refers to the number of DM circuits that have to be implemented in parallel on the ASIC. While the latest CMOS logic circuitry can operate at hundreds of GHz, the throughput of optical communication links reaches hundreds of Gb/s to Tb/s.…”

Section: Frame Structurementioning

confidence: 99%

“…To relax the signal-to-noise ratio (SNR) requirements for such formats, two independent approaches can be employed. The first is coding, or forward error correction (FEC), where hardand soft-decision schemes for fiber-optic communications have demonstrated bit error rates (BER) as low as 10 −15 [1], [2]. The second is shaping, which aims at reducing the average signal energy by spherically confining the modulation levels in signal space.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Hierarchical Distribution Matching for Probabilistically Shaped Coded Modulation

Yoshida

Karlsson

Agrell

2019

J. Lightwave Technol.

Self Cite

View full text Add to dashboard Cite

The implementation difficulties of combining distribution matching (DM) and dematching (invDM) for probabilistic shaping (PS) with soft-decision forward error correction (FEC) coding can be relaxed by reverse concatenation, for which the FEC coding and decoding lies inside the shaping algorithms. PS can seemingly achieve performance close to the Shannon limit, although there are practical implementation challenges that need to be carefully addressed. We propose a hierarchical DM (HiDM) scheme, having fully parallelized input/output interfaces and a pipelined architecture that can efficiently perform the DM/invDM without the complex operations of previously proposed methods such as constant composition DM (CCDM). Furthermore, HiDM can operate at a significantly larger post-FEC bit error rate (BER) for the same post-invDM BER performance, which facilitates simulations. These benefits come at the cost of a slightly larger rate loss and required signal-to-noise ratio at a given post-FEC BER.

show abstract

Information-Theoretic Tools for Optical Communications Engineers

Cited by 67 publications

References 35 publications

End-to-end optimized transmission over dispersive intensity-modulated channels using bidirectional recurrent neural networks

End-to-end optimized transmission over dispersive intensity-modulated channels using bidirectional recurrent neural networks

Reservoir-Computing Based Equalization With Optical Pre-Processing for Short-Reach Optical Transmission

Hierarchical Distribution Matching for Probabilistically Shaped Coded Modulation

Contact Info

Product

Resources

About