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

Abstract

The substantial increase in communication throughput driven by the ever-growing machine-to-machine communication within a data center and between data centers is straining the short-reach communication links. To satisfy such demand-while still complying with the strict requirements in terms of energy consumption and latency-several directions are being investigated with a strong focus on equalization techniques for intensitymodulation/direct-detection (IM/DD) transmission. In particular, the key challenge equalizers need to address is the inter-symbol interference introduced by the fiber dispersion when making use of the low-loss transmission window at 1550 nm. Standard digital equalizers such as feed-forward equalizers (FFEs) and decision-feedback equalizers (DFEs) can provide only limited compensation. Therefore more complex approaches either relying on maximum likelihood sequence estimation (MLSE) or using machine-learning tools, such as neural network (NN) based equalizers, are being investigated. Among the different NN architectures, the most promising approaches are based on NNs with memory such as time-delay feedforward NN (TD-FNN), recurrent NN (RNN), and reservoir computing (RC). In this work, we review our recent numerical results on comparing TD-FNN and RC equalizers, and benchmark their performance for 32-GBd on-off keying (OOK) transmission. A special focus will be dedicated to analyzing the memory properties of the reservoir and its impact on the full system performance. Experimental validation of the numerical findings is also provided together with reviewing our recent proposal for a new receiver architecture relying on hybrid optoelectronic processing. By spectrally slicing the received signal, independently detecting the slices and jointly processing them with an NN-based equalizer (wither TD-FNN or RC), significant extension reach is shown both numerically and experimentally.

Reservoir-computing and neural-network-based equalization for short reach communication

“…Tikhonov regularization [13]. Reports in the literature have been considering either digital RC [13,16,17] or moving part of the complexity in the optical domain with optoelectronics RC [14,15]. The use of optoelectronics approaches could provide an advantage in terms of power consumption, however, the two main proposed schemes (on-chip photonic RC [14] and delay-based RC [15]) face challenges in terms of fabrication tolerances (precise delay tuning, [14,15]) and operating speed (upsampling required for masking [15]).…”

Symbol error rate minimization using deep learning approaches for short-reach optical communication networks

“…These studies highlight that neural networks outperform traditional equalizers, positioning them as a sought-after technology with significant value in short-reach applications [8]. Various architectural designs have been proposed for this purpose, including feedforward neural networks (FFNNs) [9][10][11], reservoir computing (RC) [12][13][14][15][16][17][18], and recurrent neural networks (RNNs) [19,20]. These architectures can be effectively utilized for both linear and nonlinear equalization tasks.…”

Design of Mode-Locked Fibre Laser with Non-Linear Power and Spectrum Width Transfer Functions with a Power Threshold

“…Since the transition is governed by a power threshold, the system can be used for spectrum coding as a novel type of neural coding. The presented fibre mode-locked laser system is simple and flexible and can be used in a wide range of applications, including in photonics and medicine, such as self-tuning lasers [44,45] and smart sensors [46], as well as optical communications [47,48] and in 5G and 6G networks [22,49].…”