Ever-increasing intra-datacenter traffic will spur the introduction of high-baud rates and high-order modulation formats. Increasing symbol rates and modulation levels decreases tolerance against transmission impairment that includes chromatic dispersion. Transmission distance in warehouse-scale datacenters can be several kilometers, and then management of chromatic dispersion is necessary. Dispersion-compensating fibers are widely deployed in backbone networks, however, applying them in datacenters is not cost-effective since wavelength channels are coarsely multiplexed. In digital coherent systems, signal distortion due to chromatic dispersion can be resolved in digital domain; however, it will take long time before coherent systems can be introduced in datacenter networks because of their high cost. In this paper, we propose a novel impairment mitigation method employing machine learning. The proposed method is effective even after non-coherent detection and hence it can be applied to cost-sensitive intra-datacenter networks. The machine learns optimum symbol-decision criteria from a sequence of dispersed training signals, and it discriminates payload signals in accordance with the established decision criteria. With the scheme, the received signals can be demodulated in the presence of large chromatic dispersion. The transmission distance thus can be extended without relying on costly optical dispersion compensation. Since information of transmission links is not a priori required, the proposed scheme can easily be applied to any datacenter network. We conduct transmission experiments using 400-Gbps channels each of which comprises 8-subcarrier 28-Gbaud 4-ary pulse-amplitude-modulation (PAM-4) signals, and confirm the effectiveness of the proposed scheme.

Impairment mitigation in noncoherent optical transmission enabled with machine learning for intra-datacenter networks

A cascaded phase modulation is proposed for auxiliary management and control channel (AMCC) superimposition toward mobile fronthaul employing common public radio interface (CPRI). Different from other AMCC implementations, like the baseband intensity overmodulation scheme and the radio frequency pilot-tone scheme, the proposed cascaded phase overmodulation shows negligible impact on CPRI performance. Differential binary phase-shift keying is employed to encode the AMCC message, which is then overmodulated on CPRI via a cascaded phase modulator. Demodulation of AMCC message is achieved by a delay line interferometer, which converts the phase modulation to amplitude modulation. In the proof-of-concept demonstration, a 500-kb/s AMCC data are superimposed on a 10.1376-Gb/s nonreturn to zero signal with CPRI option 8, which is transmitted over 20-km standard-single-mode fiber. A -30-dBm receiver sensitivity is achieved for CPRI, with negligible penalty compared to the AMCC-free transmission of CPRI data.

Cascaded Phase Modulation for AMCC Superimposition Toward MFH Employing CPRI

We present a systematic comparison of PAM-2 (NRZ), Duobinary-PAM-2, PAM-4, and Duobinary-PAM-4 (duo-quaternary) signaling in the context of short-reach photonic communications systems using a Mach–Zehnder modulator as transmitter. The effect on system performance with a relaxed and constrained system’s opto-electronic bandwidth is analyzed for bit rates ranging from 20 to 116 Gb/s. In contrast to previous analyses, our approach employs the same experimental and simulation conditions for all modulation formats. Consequently, we were able to confidently determine the performance limits of each format for particular values of bit rate, system bandwidth, transmitter chirp, and fiber dispersion. We demonstrate that Duobinary-PAM-4 is a good signaling choice only for bandwidth-limited systems operating at relatively high speed. Otherwise, PAM-4 represents a more sensible choice. Moreover, our analysis put forward the existence of transition points: specific bit rate values where the BER versus bit rate curves for two different formats cross each other. They indicate the bit rate values where, for specific system conditions, switching from one modulation to another guarantees optimum performance. Their existence naturally led to the proposal of a format-selective transceiver, a component that, according to network conditions, operates with the most adequate modulation format. Since all analyzed modulations share similar implementation details, signaling switching is achieved by simply changing the sampling point and threshold count at the receiver, bringing flexibility to IM/DD-based optical networks.

Systematic Performance Comparison of (Duobinary)-PAM-2,4 Signaling under Light and Strong Opto-Electronic Bandwidth Conditions

In this work we introduce P-Torus, a wavelength switching architecture for intra-data-center networks that exploits optical-packet-based transport and is based on 2D torus interconnected clusters. P-Torus does not require optical buffers, as all buffering takes place at the end hosts. The proposed architecture combines torus connectivity richness, time-slotted operation, and efficient wavelength routing in order to provide single-hop, contentionless, and low-latency interconnection among all top-of-rack switches. Wavelength switching is performed in wavelength or waveband granularity with the use of fast wavelength-tunable transmitters, in compliance with the optimal solution of the routing and wavelength assignment problem of the generic torus topology. Numerical simulations are carried out to evaluate the latency and throughput performance of the proposed architecture. Results show that P-Torus exhibits low end-to-end latency and high throughput, even under a high load, in uniform and hot-spot traffic scenarios. This work also includes cost and power consumption analyses showing that P-Torus has significant benefits over other contemporary wavelength-based switching architectures. Comparative simulations and cost analysis validate that P-Torus provides a very good trade-off between performance and cost compared to other wavelength-based switching architectures targeting small to medium data centers, up to 10,000 servers.

Jian Dong

Papers

Transmission of 112(4×28)-Gb/s PAM-4 Signal over 48.6-km SSMF within only 50-GHz Grid