Polarization-multiplexed QPSK Research Articles

Digital pre-equalization for performance improvement in coherent PON

As high-speed optical access networks continue to evolve, reducing the computational complexity at the optical network unit (ONU) side remains a significant challenge in coherent passive optical network (PON). This paper presents a pre-equalization scheme that integrates digital pre-distortion (DPD) and pre-emphasis techniques in 200 Gb/s coherent PON. The focus is on three modulation formats: 50 Gbaud polarization multiplexing-quadrature phase shift keying (PM-QPSK), 50 Gbaud Alamouti-coded polarization multiplexing-16 quadrature amplitude modulation (PM-16QAM), and 25 Gbaud PM-16QAM, using intradyne or heterodyne detection schemes. Through comprehensive numerical simulations and experimental evaluations, we demonstrate significant improvements in receiver sensitivity and power budget in 200 Gb/s coherent PON. When the number of digital filtering taps is small, the proposed scheme achieves power budget enhancements of 3 dB for 50 Gbaud PM-QPSK, 7 dB for 50 Gbaud Alamouti-coded PM-16QAM, and 2.1 dB for 25 Gbaud PM-16QAM in the downlink. These findings highlight the potential of pre-equalization techniques in enhancing the performance of next-generation coherent PON with low computational complexity at the ONU side.

Demonstration of Uncoupled 4-Core Multicore Fiber in Submarine Cable Prototype With Integrated Multicore EDFA

We developed a 15.2-km submarine cable prototype which can accommodate up to 16 fiber pairs (FPs) of 125 μm standard cladding diameter 4-core uncoupled multicore fiber (UC-MCF). Fiber properties such as loss, chromatic dispersion, and inter-core crosstalk were measured and compared before and after cabling. We found that the cabling process, such as fiber rewinding, copper tubing and polyethylene coating completion, did not significantly change the fiber properties such as loss. To verify the influence of cabling process on long-haul transmission performance, we fabricated a 60.8-km length 4-core UC-MCF transmission span by serially splicing four FPs from the 15.2-km length cabled 4-core UC-MCF. An experimental loop transmission setup was established using the cabled transmission span, and Q-value was measured in real-time. The 120 wavelength multiplexed channels were transmitted. The five channels were modulated by 100 Gbps 34.7 GBd polarization multiplexed quadrature phase shift keying (PM-QPSK) signal and the other channels were loading channels shaped from amplified spontaneous emission (ASE). We changed the transmission direction one core at a time in the 4-core UC-MCF based transmission line to examine the effect of inter-core crosstalk on the transmission line. The −25-dB inter-core crosstalk caused negligible signal degradation in the 4-core UC-MCF and fan-in fan-out (FIFO) a total of 88 spans. Furthermore, we found that the 5,350-km transmission using cabled 4-core UC-MCF was limited by optical signal to noise ratio (OSNR). We integrated the transmission 4-core UC-MCF with the 4-core UC-MC-erbium doped fiber amplifier (EDFA) without using FIFO and clarified experimentally a Q-value improvement of 0.6 dB by removing half number of the FIFOs.

Low-complexity two-stage equalizer for receiver IQ imbalance compensation and polarization demultiplexing for real-time System

Reducing the complexity of adaptive equalizer is significant for realizing real-time hardware systems. In this paper, we propose a low-complexity two-stage equalizer that can be used in real-time systems. The performance of the proposed equalizer was verified through a 112 Gbit/s polarization multiplexing quadrature phase shift keying (PM-QPSK) back-to-back experiment with a receiver IQ impairment emulation module. The results revealed that, as for FIR module, compared with the conventional 2 × 2 MIMO, the number of multipliers in the proposed equalizer can be reduced by approximately 70% by use of 21 taps, while this equalizer is less sensitive to IQ impairment.

Application scheme and performance analysis of free space optical communication technology in INMARSAT

Abstract In this study, we propose an application scheme of free space optical communication technology in INMARSAT, and propose a 1.12 Tbit/s coherent free-space optical (FSO) communication system based on wavelength division multiplexing (WDM) and polarization-multiplexing quadrature phase shift keying (PM-QPSK) modulation technology. Based on optisystem software platform, the spectrum, bit error rate (BER), received power, error vector magnitude (EVM), and receiver sensitivity of the edge and middle channels of the system are analyzed. The simulation results show that the transmission rate and channel capacity of INMARSAT communication system are greatly improved by selecting the channel spacing and transmission environment reasonably.

Multiplier-Free Parallel Fixed-Point Adaptive Equalizer for Real-Time Digital Coherent Communication

Multiplier-free adaptive equalizers are significant for improving utilization, reducing costs, and ensuring robustness in real-time hardware implementation. In this letter, we demonstrate that using only one bit shift and one XOR operation to replace a real multiplier is a feasible and low-complexity way to obtain a multiplier-free parallel fixed-point adaptive equalizer (PFAEQ). The performances of the multiplier-free PFAEQ (MF-PFAEQ) are verified by a 112 Gbits/s polarization multiplexing quadrature phase shift keying (PM-QPSK) back-to-back experiment. It can be found that, under different parallels and different bit width of signals, MF-PFAEQ shows similar performances to traditional PFAEQ. Besides, in some cases, compared with the traditional PFAEQ, MF-PFAEQ also shows the similar convergent speed. In addition, according to the Quartus 15.0 synthesis, compared to traditional PFAEQ, the logic utilization and total registers of MF-PFAEQ reduce by 51.8% and 45.2%, respectively. This study is novel in using rather less shift operations to obtain a multiplier-free adaptive equalizer.

Hybrid compensation of polarization-multiplexed QPSK optical format for high bit rate networks

<span lang="EN-GB">Transmitting the highest capacity throughput over the longest possible distance without any regeneration stage is an important goal of any long-haul optical network system. Accordingly, Polarization-Multiplexed Quadrature Phase-Shift-Keying (PM-QPSK) was introduced lately to achieve high bit-rate with relatively high spectral efficiency. Unfortunately, the required broad bandwidth of PM-QPSK increases the linear and nonlinear impairments in the physical layer of the optical fiber network. Increased attention has been spent to compensate for these impairments in the last years. In this paper, Single Mode Fiber (SMF), single channel, PM-QPSK transceiver was simulated, with a mix of optical and electrical (Digital Signal Processing (DSP)) compensation stages to minimize the impairments. The behaviour of the proposed system was investigated under four conditions: without compensation, with only optical compensator, with only DSP compensator and finally with both compensators. An evidence improvement was noticed in the case of hybrid compensation, where the transmission distance was multiplied from (720 km) to more than (3000 km) at 40 Gb/s.</span>

A novel DSP scheme for eliminating the interaction between dispersion and transient frequency offset in optical burst-mode coherent systems

Optical coherent burst-mode transmission can offer not only flexibility but also efficiency of the network resource utilization in elastic optical networks. We propose a new digital signal processing (DSP) scheme of coherent burst reception with a training sequence (TS) to solve the convergence problem of equalization caused by the interaction between fast-changing transient frequency offset (TFO) and fiber chromatic dispersion (CD) compensation in optical burst (OB)-mode systems. The DSP scheme is demonstrated to perform well by the simulation and experimentation on 128 Gbps polarization multiplexing quadrature phase-shift keying (PM-QPSK) coherent systems. Thanks to the DSP scheme, a guard interval between two OBs is no longer needed, and the valid payload can be transmitted during TFO changing from wavelength tuning. The proposed DSP scheme can reduce the overhead by ∼73% for wavelength-tunable OB-mode coherent systems compared with using guard intervals, which significantly improves the spectral efficiency of burst-mode systems.

Modulation format identification based on phase statistics in Stokes space

In this work, a high-performance, low-complexity modulation format identification (MFI) technique is proposed and experimentally demonstrated for coherent optical receivers using features extracted from phase statistics in Stokes space. Numerical simulations as well as long-haul experiments are carried out to validate the proposed MFI scheme. Successful identification is demonstrated among polarization-multiplexed (PM) QPSK, 8PSK, 8QAM, 16QAM, 32QAM and 64QAM signals. Compared with existing modulation identification schemes, the proposed MFI method has an excellent recognition performance with a low computational complexity.

IQ imbalance compensation based on simplified GSOP and FPGA implementation in optical coherent QPSK receiver

Abstract In this paper, a simplified Gram-Schmidt orthogonalization procedure (SG) method was proposed for in-phase/quadrature (IQ) imbalance compensation based on the Gram-Schmidt orthogonalization procedure (GSOP) algorithm. The proposed method can compensate IQ imbalance in the optical coherent system by two steps of phase orthogonalization and amplitude balance. In addition, this method avoids square root operation compared to the GSOP in the field programmable gate array (FPGA) hardware implementation, therefore it is easier to implement in terms of resources and complexity. Two steady states are achieved by accumulating scale factor to reduce resource consumption in FPGA hardware implementation of the proposed scheme. Finally, a FPGA design with 32 parallel units is performed to demonstrate the proposed method in a polarization multiplexed quadrature phase shift keying (PM-QPSK) system, the results show the proposed algorithm simplifies FPGA implementation complexity and maintains compensation performance comparable to GSOP algorithms.

Dual Polarization Full-Field Signal Waveform Reconstruction Using Intensity Only Measurements for Coherent Communications

Conventional optical coherent receivers capture the full electrical field, including amplitude and phase, of a signal waveform by measuring its interference against a stable continuous-wave local oscillator (LO). In optical coherent communications, powerful digital signal processing (DSP) techniques operating on the full electrical field can effectively undo transmission impairments such as chromatic dispersion (CD), and polarization mode dispersion (PMD). Simpler direct detection techniques do not have access to the full electrical field and therefore lack the ability to compensate for these impairments. We present a full-field measurement technique using only direct detection that does not require any beating with a strong carrier LO. Rather, phase retrieval algorithms based on alternating projections that makes use of dispersive elements are discussed, allowing to recover the optical phase from intensity-only measurements. In this demonstration, the phase retrieval algorithm is a modified Gerchberg Saxton (GS) algorithm that achieves a simulated optical signal-to-noise ratio (OSNR) penalty of less than 4dB compared to theory at a bit-error rate of 2 times 10-2. Based on the proposed phase retrieval scheme, we experimentally demonstrate signal detection and subsequent standard 2x2 multiple-input-multiple-output (MIMO) equalization of a polarization-multiplexed 30-Gbaud QPSK transmitted over a 520-km standard single-mode fiber (SMF) span.

Chirp-Filtering for Low-Complexity Chromatic Dispersion Compensation

Current chromatic dispersion compensation algorithms use frequency-domain equalization for efficient filtering. Nonetheless it is one of the most power-hungry blocks of the digital signal processing chain for high baud rate and/or long haul transmission systems. The computational complexity of frequency-domain compensation algorithms is dominated by two fast Fourier transforms for high values of accumulated dispersion. In this article we propose a discrete-time filtering strategy called chirp chromatic dispersion compensation that can be efficiently computed using one single fast Fourier transform. A thorough mathematical description of the method is presented, showing the considered approximations and possible limitations of the new technique. Experimental results indicate that chirp filtering achieves equivalent performance as the frequency-domain technique with overlap-save reconstruction for 32-GBd polarization-multiplexed QPSK and 16 QAM signals at potentially half the complexity if the minimum overlap is respected.

0.55 Tb/s heterogeneous Nyquist-WDM superchannel using different polarization multiplexed subcarriers

This paper depicts the design of 0.55 Tb/s heterogeneous Flexi-rate Nyquist-wavelength division multiplexed (Nyquist-WDM) Superchannel. Here, for the first time, four subcarriers of different modulation formats are accommodated, namely polarization multiplexed-binary phase-shift keying, polarization multiplexed-quadrature phase-shift keying (PM-QPSK), polarization multiplexed-8-quadrature amplitude modulation and PM-16QAM, each with 27.75 Gbaud symbol rate. The system transmission performance with acceptable bit error rate (BER) 4 × 10−3 is analyzed over pure silica core fiber (PSCF) in the presence of hybrid optical amplification, i.e., Raman amplifier along with a counter-propagating pump and Erbium-doped fiber amplifier. The presence of this hybrid optical amplification unit results in a limited optical signal-to-noise ratio requirement and makes the whole system cost-effective. The proposed work delivers excellent spectral efficiency of 4.5 b/s/Hz and highest transmission reach of 5500 km for PM-QPSK subcarrier and 2300 km for PM-16QAM subcarrier in the presence of PSCF. The system performance against intersymbol interference and noise is also analyzed with the aid of eye pattern plot at a minimum and maximum transmission length.

A Phase-Retrieving Coherent Receiver Based on Two-Dimensional Photodetector Array

To achieve an ultra-compact and flexible coherent transceiver solution, a carrier-less coherent detection technique using a two-dimensional (2-D) photodetector array (PDA) is proposed based on the idea of phase retrieval (PR). In the proposed PR-based coherent receiver, the optical phase information is digitally reconstructed from multiple intensity-only measurements acquired by arrayed photodetectors; neither local light sources, optical hybrids, nor spatial demultiplexers are needed. We develop a robust and low-complexity PR algorithm, which exploits prior knowledge on the optical modulation format, for the proposed PR receiver. As a proof-of-concept, the coherent detection of 10-Gbaud optical phase-modulated signals, including QPSK, 16-QAM, coherent optical OFDM, and polarization-multiplexed QPSK signals, using only a 2-D PDA is demonstrated experimentally.

Performance evaluation of 100 and 200-Gb/s WDM PM-QPSK transmission systems: tolerance analysis to the optical link impairments according to the optical carrier shape

Polarization-multiplexing quadrature phase shift keying (PM-QPSK) has become a key ingredient in the design of 100 and 200-Gb/s dense wavelength-division multiplexed (DWDM) networks. The performance of the system using these formats varies according to the shape of the pulses employed by the optical carrier: non-return to zero (NRZ), return to zero (RZ) or carrier-suppressed return to zero (CSRZ). In this paper, we analyse the tolerance of PM-QPSK to linear and nonlinear optical impairments, including amplified spontaneous emission (ASE) noise, crosstalk, distortion by optical filtering, chromatic dispersion (CD), polarization mode dispersion (PMD) and fibre Kerr nonlinearities. The simulation results show that RZ formats with a low-duty cycle have a higher tolerance to CD, PMD and intrachannel nonlinearities due to the reduction of pulse-to-pulse interaction. Conversely, the PM–NRZ-QPSK format has a higher spectral efficiency (SE) than other options and shows better tolerance to filtering distortion and CD in filterless networks.

Frequency-Domain Hybrid Modulation Formats for High Bit-Rate Flexibility and Nonlinear Robustness

Since the deployment of the first commercial polarization-multiplexed (PM) QPSK 100G systems, the evolution of coherent optical communications in the last decade has been largely dominated by single-carrier quadrature amplitude modulation (QAM) based modulation of increasing constellation size. However, as the data traffic becomes more dynamic and heterogeneous, an efficient use of the optical link requires more flexible modulation schemes, capable of adapting data-rate and distance with fine granularity. While typical multi-carrier modulation schemes composed of hundreds of subcarriers may be inadequate for optical transmission, namely due its high peak-to-average power ratio and increased nonlinearity penalties, it has been recently shown that few-carrier modulation (with symbol rate in the order of 2–4 GBaud) can provide an increased robustness to nonlinear propagation impairments. In this paper, we exploit the concept of frequency-domain hybrid modulation formats (FDHMF) based on electronic subcarrier multiplexing with the use of different QAM formats on each subcarrier to simultaneously enhance the data-rate flexibility and the nonlinear propagation performance of the optical link. In addition, by properly designing the FDHMF signal, an increased tolerance against optical filtering can also be achieved. Using the enhanced Gaussian noise model, we report a comprehensive theoretical study on the performance of FDHMF, considering independent- and joint-subcarrier forward-error correction strategies, optimization of power ratio between subcarriers, and corresponding impact of fiber nonlinearities. These theoretical insights are then validated by a broad range of wavelength-division multiplexing experiments with per-channel bit-rates in the range of 150G to 250G. The obtained results demonstrate that FDHMF is an effective solution for the implementation of flexible transponders capable of adapting the data rate to the lightpath quality of transmission: An enabling technology for the introduction of future elastic optical networks.

Spectrally efficient 1.55 Tb/s Nyquist-WDM superchannel with mixed line rate approach using 27.75 Gbaud PM-QPSK and PM-16QAM

This paper investigates the transmission performance of a 1.55-Tb/s Nyquist-wavelength division multiplexing superchannel along with a mixed line rate approach using 4 × 111 Gb / s polarization-multiplexed quadrature phase shift keying (PM-QPSK) and 5 × 222 Gb / s polarization-multiplexed quadrature amplitude modulation (PM-16QAM) formats. The system transmission performance with acceptable bit error rate of 4 × 10 − 3 is analyzed over standard single mode fiber (SSMF), large effective area fiber (LEAF), and pure silica core fiber (PSCF). It is observed that SSMF increases 45% reach over LEAF, whereas PSCF increases 66% to 84% reach over LEAF for 4.5 b/s/Hz spectral efficiency of the system. Also, spectral efficiency × distance product of 24,750 and 10,350 b/s/Hz.km are obtained for PM-QPSK and PM-16QAM, respectively, which is, to the best of our knowledge, better in comparison with the other existing literatures for single core channel investigations.

Coherent 16 Quadrature Amplitude Modulation (16QAM) Optical Communication Systems

Coherent optical fiber communications for data rates of 100Gbit/s and beyond have recently been studied extensively primarily because high sensitivity of coherent receivers could extend the transmission distance. Spectrally efficient modulation techniques such as M-ary quadrature amplitude modulation (M-QAM) can be employed for coherent optical links. The integration of multi-level modulation formats based on coherent technologies with wavelength-division multiplexed (WDM) systems is key to meet the aggregate bandwidth demand. This paper reviews coherent 16 quadrature amplitude modulation (16QAM) systems to scale the network capacity and maximum reach of current optical communication systems to accommodate traffic growth. Full Text: PDF ReferencesK. Kikuchi, "Fundamentals of Coherent Optical Fiber Communications", J. Lightwave Technol., vol. 34, no. 1, pp. 157-179, 2016. CrossRef S. Tsukamoto, D.-S. Ly-Gagnon, K. Katoh, and K. Kikuchi, "Coherent Demodulation of 40-Gbit/s Polarization-Multiplexed QPSK Signals with16-GHz Spacing after 200-km Transmission", Proc. OFc, Paper PDP29, (2005). DirectLink K. Kikuchi, "Coherent Optical Communication Technology", Proc. OFC, Paper Th4F.4, (2015). CrossRef J. M. Kahn and K.-P. Ho, "Spectral efficiency limits and modulation/detection techniques for DWDM systems", IEEE J. Sel. Topics Quantum Electron., vol. 10, no. 2, pp. 259–272, (2004). CrossRef S. Tsukamoto, K. Katoh, and K. Kikuchi, "Coherent demodulation of optical multilevel phase-shift-keying signals using homodyne detection and digital signal processing", IEEE Photon. Technol. Lett., vol. 18, no. 10, pp. 1131–1133, (2006). CrossRef Y. Mori, C. Zhang, K. Igarashi, K. Katoh, and K. Kikuchi, "Unrepeated 200-km transmission of 40-Gbit/s 16-QAM signals using digital coherent receiver", Opt. Exp., vol. 17, no. 32, pp. 1435–1441, (2009). CrossRef H. Nakashima, Et al., "Digital Nonlinear Compensation Technologies in Coherent Optical Communication Systems", Proc. OFC, Paper W1G.5, (2017). CrossRef S. J. Savory, "Digital filters for coherent optical receivers", Opt. Exp., vol. 16, no. 2, pp. 804–817, (2008). CrossRef D. S. Millar, T. Koike-Akino, S. Ö. Arık, K. Kojima, K. Parsons, T. Yoshida, and T. Sugihara, "High-dimensional modulation for coherent optical communications systems", Opt. Express, vol. 22, no. 7, pp 8798-8812, (2014). CrossRef R. Griffin and A. Carter, "Optical differential quadrature phase-shift key (oDQPSK) for high capacity optical transmission", Proc. OFC, Paper WX6, (2002). DirectLink K. Kikuchi, "Digital coherent optical communication systems: fundamentals and future prospects", IEICE Electron. Exp., vol. 8, no. 20, pp. 1642–1662, (2011). CrossRef F. Derr, "Optical QPSK transmission system with novel digital receiver concept", Electron Lett., vol. 27, no. 23, pp. 2177–2179, (1991). CrossRef R. No’e, "Phase noise tolerant synchronous QPSK receiver concept with digital I&Q baseband processing", Proc. OECC, Paper 16C2-5, (2004). DirectLink D.-S. Ly-Gagnon, S. Tsukamoto, K. Katoh, and K. Kikuchi, "Coherent detection of optical quadrature phase-shift keying signals with carrier phase estimation", J. Lightw. Technol., vol. 24, no. 1, pp. 12–21, (2006). CrossRef M. Taylor, "Coherent detection method using DSP for demodulation of signal and subsequent equalization of propagation impairments", IEEE Photon. Technol. Lett., vol. 16, no. 2, pp. 674–676, (2004). CrossRef S. Tsukamoto, K. Katoh, and K. Kikuchi, "Unrepeated transmission of 20-Gb/s optical quadrature phase-shift-keying signal over 200-km standard single-mode fiber based on digital processing of homodyne-detected signal for Group-velocity dispersion compensation", IEEE Photon. Technol. Lett., vol. 18, no. 9, pp. 1016–1018, (2006). CrossRef S. Tsukamoto, Y. Ishikawa, and K. Kikuchi, "Optical Homodyne Receiver Comprising Phase and Polarization Diversities with Digital Signal Processing", Proc. ECOC, Paper Mo4.2.1, (2006). CrossRef K. Kikuchi and S. Tsukamoto, "Evaluation of Sensitivity of the Digital Coherent Receiver", J. Lightw. Technol., vol. 20, no. 13, pp. 1817–1822, (2008). CrossRef S. Ishimura and K. Kikuchi, "Multi-dimensional Permutation Modulation Aiming at Both High Spectral Efficiency and High Power Efficiency", Proc. OFC/NFOEC, Paper M3A.2, (2014). CrossRef F. I. El-Nahal and A. H. M. Husein, "Radio over fiber access network architecture employing RSOA with downstream OQPSK and upstream re-modulated OOK data", (Optik) Int. J. Light Electron Opt., vol. 123, no. 14, pp: 1301-1303, (2012). CrossRef T. Koike-Akino, D. S. Millar, K. Kojima, and K. Parsons, "Eight-Dimensional Modulation for Coherent Optical Communications", Proc. ECOC, Paper Tu.3.C.3, (2013). DirectLink B. Sklar, Digital communications: Fundamentals and Applications, Prentice-Hall, (2001).

Nonlinearity-tolerant OSNR estimation method based on correlation function and statistical moments

Abstract We propose a fiber nonlinearity-tolerant optical signal-to-noise ratio (OSNR) estimation method for high speed long haul coherent optical fiber transmission system. The correlation function of the amplitude noise and a calibration factor ξ are utilized to correct nonlinearity-induced distortions for the first time when the statistical moments-based method (SMB method) is applied. ξ depends on not only transmission distances but also launch powers. Besides, we put forward a fitting formula for optimal ξ and OSNR estimation results still keep valid regardless of transmission distances and launch powers. Compared with current existing OSNR estimation methods, the proposed method functions well in highly nonlinear systems and is demonstrated to be feasible and more accurate. OSNR estimation errors are below 0.94 dB after calibration over a wide OSNR range from 10 dB to 28 dB in a 112-Gb/s polarization-multiplexed quadrature phase shift keying (PM-QPSK) system when the launch power is up to 8 dBm and the transmission distance is as long as 2000 km.

Subtraction-Clustering-Based Modulation Format Identification in Stokes Space

A Stokes-space-based modulation format identification (MFI) technique with low complexity is proposed for coherent optical receivers, on the basis of the subtraction clustering algorithm. Successful MFI with good optical signal-to-noise ratio performance can be realized among polarization-multiplexed BPSK, QPSK, 8PSK, 8QAM, and 16QAM signals. Experimental verifications are also performed to prove the feasibility of the proposed MFI in long-distance optical fiber transmission systems.

Joint OSNR monitoring and modulation format identification in digital coherent receivers using deep neural networks.

We experimentally demonstrate the use of deep neural networks (DNNs) in combination with signals' amplitude histograms (AHs) for simultaneous optical signal-to-noise ratio (OSNR) monitoring and modulation format identification (MFI) in digital coherent receivers. The proposed technique automatically extracts OSNR and modulation format dependent features of AHs, obtained after constant modulus algorithm (CMA) equalization, and exploits them for the joint estimation of these parameters. Experimental results for 112 Gbps polarization-multiplexed (PM) quadrature phase-shift keying (QPSK), 112 Gbps PM 16 quadrature amplitude modulation (16-QAM), and 240 Gbps PM 64-QAM signals demonstrate OSNR monitoring with mean estimation errors of 1.2 dB, 0.4 dB, and 1 dB, respectively. Similarly, the results for MFI show 100% identification accuracy for all three modulation formats. The proposed technique applies deep machine learning algorithms inside standard digital coherent receiver and does not require any additional hardware. Therefore, it is attractive for cost-effective multi-parameter estimation in next-generation elastic optical networks (EONs).