English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The deployment of artificial neural networks-based optical channel equalizerson edge-computing devices is critically important for the next generation ofoptical communication systems. However, this is still a highly challengingproblem, mainly due to the computational complexity of the artificial neuralnetworks (NNs) required for the efficient equalization of nonlinear opticalchannels with large dispersion-induced memory. To implement the NN-basedoptical channel equalizer in hardware, a substantial complexity reduction isneeded, while we have to keep an acceptable performance level of the simplifiedNN model. In this work, we address the complexity reduction problem by applyingpruning and quantization techniques to an NN-based optical channel equalizer.We use an exemplary NN architecture, the multi-layer perceptron (MLP), tomitigate the impairments for 30GBd 1000km transmission over a standardsingle-mode fiber, and demonstrate that it is feasible to reduce theequalizer's memory by up to 87.12%, and its complexity by up to 78.34%, withoutnoticeable performance degradation. In addition to this, we accurately definethe computational complexity of a compressed NN-based equalizer in the digitalsignal processing (DSP) sense. Further, we examine the impact of usingdifferent CPU and GPU settings on the power consumption and latency for thecompressed equalizer. We also verify the developed technique experimentally, byimplementing the reduced NN equalizer on two standard edge-computing hardwareunits: Raspberry Pi 4 and Nvidia Jetson Nano, which are used to process thedata generated via simulating the signal's propagation down the optical-fibersystem.

Experimental implementation of a neural network optical channel equalizer in restricted hardware using pruning and quantization