Experimental Investigation of Optoelectronic Receiver With Reservoir Computing in Short Reach Optical Fiber Communications

Abstract

The cloud edge data center will enable reliable and low latency options for the network, and the interconnection among these data-centers will demand a scalable lowcomplexity scheme. An intensity-modulated and directed detected transmission system is an attractive solution, but chromatic dispersion is the main limitation for higher symbol rate systems. To overcome this challenge, we have proposed and experimentally demonstrated a receiver with shared-complexity between optical and digital domains that enables 80 km transmission reach below KP4 FEC limit for a 32 GBd on-off keying signal. The optical stage consists of optical filters that slices the signal into smaller sub-bands and each is detected by a photodetector. A feedforward neural network and reservoir computing are compared to reconstruct the full signal from the slices and mitigate the chromatic dispersion. Both equalizers have shown similar performance with the advantage of the reservoir computing requiring fewer inputs and easier training process. In this work, we have compared the linear and nonlinear activation functions in the feedforward neural network to investigate the gain of using a nonlinear equalizer. The maximum transmission reach is reduced almost to half, ≈ 45 km, when using the linear. The performance is also reduced if a reduced number of slices is used in the receiver, as we have demonstrated. In this case, using 2 slices to reduce the complexity of the system, instead of the total 4, we have shown a ≈ 55 km transmission reach below KP4 FEC limit. In this work we have also provided a numerical comparison with 4x8 GBd subcarriers system. The results have shown a 40 km increase in transmission reach compared to the proposed optoelectronic system. The trade-off between performance and complexity should be analyzed for each case, as a different hardware is required in each situation.

Machine-learning-based equalization for short-reach transmission: neural networks and reservoir computing

“…They were varied considering different fiber spools, therefore the receiver SNR does vary only approximately linearly with the fiber length. 11 For the single-PD receiver, the results from all tested equalizers (FFE, TD-FNN, and RC) show similar performance, with only a marginal benefit of the TD-FNN.…”

“…While demonstrations of full RNNs for IM/DD system equalization have been reported, 7 RNNs suffer from training challenges due to vanishing gradients which may prevent the use of standard training methods such as back-propagation. Simplified RNN models have therefore been considered, focusing on TD-FNNs, 5,10,11 and RC. 10,11,[14][15][16] Alternative lower-complexity RNNs architectures such as gated recurrent units (GRUs), 12 and long short-term memory (LSTM) 13 have been applied mainly to coherent transmission so far.…”

“…The second is the spectrally-sliced receiver proposed and discussed in. [9][10][11] We have proposed the spectrally-sliced receiver to reduce the effect of power-fading in the IM/DD systems. This effect is avoided by filtering the received signal in smaller sub-bands with optical filters, before detection.…”

“…More details can be found in. 11 The performance metric considered in the experimental results is the SNR defined by the system. Different from the numerical analyses, the SNR is not varied deliberately.…”

“…In this work, we review our systematic comparison between linear and nonlinear equalizers focusing on a simple OOK transmission system. [9][10][11] In particular, we analyze the performance improvement provided by two recent machine-learning tools which still allow for relatively limited training complexity, i.e. time-delay feed-forward NN (TD-FNN) and reservoir computing (RC).…”