Abstract

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).

© 2017 Optical Society of America

1. Introduction

The capacity of optical networks has been increasing steadily and the network architectures are continuously becoming more dynamic, complex, and transparent in nature. The optical signals in high-speed fiber-optic networks are vulnerable to various transmission impairments which can vary dynamically over time. Therefore, it is imperative to have appropriate monitoring mechanisms across the whole optical network which can provide precise and real-time information about the quality of transmission links and the health of optical signals [1,2]. Fortunately, due to incredible advances in digital signal processing (DSP) technologies over the past decade, the linear impairments can be fully compensated in digital coherent receivers and the transmission performance is mainly determined by OSNR [3]. Consequently, OSNR is one of the most important parameters to be monitored in coherent optical networks due to its direct relation with bit-error ratio (BER). OSNR information is also vital for automatic fault detection and diagnosis as well as for in-service characterization of signal quality [4]. OSNR monitoring is typically realized in digital coherent receivers as a by-product of DSP algorithms. Existing OSNR monitoring techniques for coherent detection systems include statistical moments [5], error vector magnitude (EVM) [6], delay-line interferometer (DLI) [7,8], Stokes parameters [9], Golay sequences [10], offset filtering and optical power measurement [11], RF spectrum [12], and amplitude noise correlation [13] based methods.

Elastic optical networks (EONs) have gained significant attention over the past few years. One salient feature of EONs is that different transmission parameters like modulation format, data rate, signal power etc. can be adjusted adaptively (based on time-varying channel conditions and traffic demands) in order to maximize the bandwidth and energy efficiencies of the network [14]. The dynamic variation of transmission parameters in EONs imposes new requirements on DSP algorithms employed in the optical receivers. For example, the OSNR monitoring technique utilized in the receiver must be appropriate for the incoming signal type. Similarly, the carrier recovery module used in the receiver must be suitable for the received modulation format. The above examples clearly suggest that MFI is indispensable for digital coherent receivers used in EONs. The real-time information about modulation formats of received signals (obtained through MFI) can enable the receivers to adopt algorithms most appropriate for these formats types [15]. Recently, several techniques for MFI in digital coherent receivers have been presented. These include k-means algorithm [16], signal cumulants [17], variational Bayesian expectation maximization algorithm [18], and peak-to-average-power ratio evaluation [19] based methods.

The above-mentioned methods for OSNR monitoring and MFI suffer from one or more of the following drawbacks. (i) All these techniques focus on either OSNR monitoring or MFI and not joint estimation of both parameters. (ii) Many of these techniques require extra hardware components like filters, interferometers, polarimeters, power meters etc., which can significantly increase implementation complexity (and cost). (iii) Some of these techniques necessitate modification of transmitters for the purpose of inserting pilot tones into the signals, which in turn limits their application in many practical scenarios. (iv) Some of these techniques are based on transmission of training sequences which may reduce the spectral efficiency of the system. (v) Many of these techniques use complex iterative algorithms requiring significant computation time which may be problematic in situations where OSNRs and modulation formats change quite rapidly.

Recently, there has been a dramatic increase in the popularity of deep learning, a machine learning approach based on the concept of hierarchical representation of data [20]. A deep learning system has the ability to automatically learn powerful features of data at multiple levels of abstraction and this allows it to learn complex functions mapping the input to the output directly from the data. Over the past few years, deep learning architectures like DNNs, autoencoders, deep recurrent neural networks (DRNNs), long short-term memory (LSTM) networks etc. have been applied successfully in tasks such as classification, regression, dimensionality reduction, information retrieval, natural language processing etc. and have achieved state-of-the-art results in many cases [21,22]. Recently, we demonstrated a DNN-based technique for MFI in coherent receivers [23]. However, that method focuses merely on identifying the modulation format of received signal and does not provide any information about the quality of signal in terms of OSNR. In this paper, we extend our previous work and propose a technique which hierarchically employs multiple DNNs in conjunction with signals’ AHs for joint OSNR monitoring and MFI in digital coherent receivers. In the proposed scheme, first a single DNN is used to perform MFI by exploiting modulation format-dependent features of AHs. In the second stage, we employ several DNNs each of which is trained for OSNR monitoring of a specific modulation format by utilizing OSNR-sensitive features of corresponding AHs. The MFI information provided by the DNN in first stage is used to select a suitable DNN (i.e. the one dedicated for OSNR monitoring of identified signal type) in the second stage. Experimental results obtained for 112 Gbps PM QPSK, 112 Gbps PM 16-QAM, and 240 Gbps PM 64-QAM signals show that in contrast to existing methods, this technique enables joint determination of both OSNR and modulation format with good accuracies. Furthermore, unlike some previous methods, this technique requires neither additional hardware nor any modification of transmitters. The proposed technique does not decrease spectral efficiency of the system since it is completely non-data-aided (NDA).

2. Operating principle

The DSP configuration used in digital coherent receiver including the proposed OSNR monitoring and MFI stage is shown in Fig. 1. First, standard modulation format-independent chromatic dispersion (CD) compensation and timing phase recovery algorithms are used. Next, we employ CMA-based equalization for compensating nearly all linear transmission impairments. Hence, the signals after this stage are mainly affected by amplified spontaneous emission (ASE) noise. The samples available after CMA equalization are processed using the proposed technique as clear from Fig. 1. For this purpose, first AHs with 80 bins are generated from the samples. The AHs for three signal types considered in this work are shown in Fig. 2 for three different OSNRs. It is evident from the figure that AHs exhibit unique and distinctive patterns for different OSNRs and modulation formats. The OSNR and modulation format sensitive features of AHs can thus be exploited for joint estimation of these parameters by employing DNNs-based pattern recognition. As shown in Fig. 1, the OSNR information provided by the proposed technique can be used to assess the quality of received optical signals. On the other hand, the MFI information can be exploited by subsequent DSP stages like multi-modulus algorithm (MMA) equalization for realizing modulation format-optimized signal processing. Note that instead of performing both MFI and OSNR monitoring after CMA equalization stage, we can alternatively determine OSNR after carrier phase estimation stage. However, our choice of monitoring OSNR also at an earlier stage of DSP chain is motivated by following two practical reasons. (i) OSNR monitoring and MFI may not only be required at the transmission end points but also in OPMdevices installed at the intermediate network nodes which can only afford limited complexity due to cost constraints [2,4,24,25]. By estimating OSNR and modulation format after CMA equalization stage, our proposed approach requires only few DSP blocks and thus it can enable reduced-complexity (and hence low-cost) OPM devices for the intermediate network nodes. (ii) Performing OSNR monitoring after carrier phase estimation stage would require generation and processing of additional AHs (apart from the ones used for MFI after CMA equalization stage) which will in turn increase the computational complexity and processing time of the proposed technique. Due to above-mentioned reasons, we chose to estimate both OSNR and modulation format directly after CMA equalization stage.

 figure: Fig. 1

Fig. 1 DSP configuraion used in the receiver with the proposed OSNR monitoring and MFI stage highlighted in red colour.

Download Full Size | PPT Slide | PDF

 figure: Fig. 2

Fig. 2 AHs for three different OSNRs for QPSK (first row), 16-QAM (second row), and 64-QAM (third row) signals after CMA equalization.

Download Full Size | PPT Slide | PDF

In the proposed technique, we use four DNNs in a hierarchical manner for MFI and OSNR monitoring tasks as shown in Fig. 3. A single DNN (called DNN-MFI) is employed in first stage for MFI purpose. The MFI information provided by DNN-MFI is then utilized to select another DNN (called DNN-OSNR) in the second stage which is customized for OSNR monitoring of identified modulation format. Some important network parameters of DNNs used in this work are given in Fig. 3. In order to train the DNNs, we generated a large data set, called training data set, containing numerous AHs corresponding to three modulation formats and different OSNRs. Each AH in this data set is expressed as an 80 × 1 vector x of bin-counts. Similarly, for each AH, a 3 × 1 binary vector y1 (with single non-zero element whose location signifies the modulation format type corresponding to that AH) and a scalar y2 indicating the OSNR value associated with that AH are also obtained. Vector y1 and scalar y2 are called labels of a bin-count vector x. For the training of DNN-MFI, vectors x and labels y1 are utilized as shown in Fig. 3. The DNN-MFI first hierarchically extracts characteristic feature vectors f of all input vectors x. The reduced-size feature vectors f and corresponding labels y1 are then used for supervised training of DNN-MFI. During the training process, DNN-MFI is made to learn the mapping between vector pairs (f, y1) by optimizing its variousparameters. The training procedure of three DNN-OSNR, dedicated for individual modulation formats, is similar except that vectors x and labels y2 (pertaining to respective signal types) are employed for training in this case as shown in Fig. 3.

 figure: Fig. 3

Fig. 3 DNNs with bin-count vectors x as inputs and estimated modulation formats/OSNRs as outputs. During testing, a suitable DNN-OSNR is chosen based on identified modulation format for the given input vector x.

Download Full Size | PPT Slide | PDF

Once the training phase is over, the performances of trained DNNs are evaluated by using an independent set of data namely testing data set. During the testing phase, bin-count vectors x in the testing data set are first applied at the input of trained DNN-MFI and corresponding output vectors v1 are obtained. Taking argmax{v1} then provides estimated modulation formats. Next, based on identified signal types, the bin-count vectors x are presented to their respective DNN-OSNR and the resulting scalar outputs v2 then give OSNR estimates. Finally, the estimated modulation formats and OSNRs are compared with the actual ones given by labels y1 and y2 of the testing data set, respectively, and the estimation accuracies are determined.

3. Experimental setup

The experimental setup for the demonstration of proposed OSNR monitoring and MFI technique is shown in Fig. 4. We generated 28 Gbaud QPSK, 14 Gbaud 16-QAM, and 20 Gbaud 64-QAM optical signals by modulating a carrier signal, provided by an external cavity laser (ECL), using I/Q modulators which are driven by multi-level electrical signals. Thecentre wavelength of ECL is 1550.12 nm and its linewidth is 150 kHz. Polarization multiplexing is then realized by utilizing polarization beam splitters (PBSs), polarization beam combiners (PBCs), and optical delay lines. The resulting 112 Gbps PM QPSK, 112 Gbps PM 16-QAM, and 240 Gbps PM 64-QAM signals are amplified using an erbium-doped fiber amplifier (EDFA) and sent over a fiber recirculating loop. As shown in Fig. 4, the recirculating loop consists of an 80 km long standard single-mode fiber (SSMF), a variable optical attenuator (VOA), an EDFA, and a 5 nm bandwidth optical band-pass filter (OBPF) for the equalization of channel power. The VOA is utilized to alter OSNRs of QPSK, 16-QAM, and 64-QAM signals in the ranges of 10−23 dB, 17−26 dB, and 25−37 dB, respectively, in steps of ∼1 dB. The optical signals at the output of recirculating loop are filtered using a 0.4 nm bandwidth OBPF and then detected by a coherent receiver. The local oscillator (LO) laser used has a linewidth of 100 kHz and its frequency offset with respect to transmitter laser is ∼1 GHz. The electrical signals after optical-to-electronic (O/E) conversion are sampled by utilizing an oscilloscope with 50 Gsamples/s sampling rate and 56,000 samples are collected which are then processed offline using a DSP core. As clear from Fig. 1, the proposed technique processes polarization de-multiplexed signals after CMA equalization. For this purpose, first AHs with 80 bins are synthesized. We generated a large data set encompassing 190 AHs corresponding to different modulation formats and OSNRs. The AHs in this data set are divided into training and testing data sets by randomly selecting 70% (i.e. 133) and 30% (i.e. 57) of overall AHs, respectively. We obtained bin-count vector x as well as labels y1 and y2 for each AH in the two data sets, which are then employed for training/testing of four DNNs using the procedure described earlier.

 figure: Fig. 4

Fig. 4 Experimental setup for joint OSNR monitroing and MFI in coherent receivers using DNNs.

Download Full Size | PPT Slide | PDF

4. Results and discussion

Figure 5 shows three elements of DNN-MFI output vectors v1 in response to 57 input vectors x belonging to testing data set. It is clear from the figure that one particular element of v1 is significantly larger than the others for each test case, thus indicating that all three modulation formats are clearly identified. Table 1 summarizes MFI results for 57 test cases in the testing data set. It is evident from the table that all three modulation formats under consideration are identified with an accuracy of 100%, as expected. Once modulation formats associated with 57 bin-count vectors x in the testing data set have been identified by DNN-MFI, the corresponding OSNRs are estimated by applying vectors x at the inputs of their respective DNN-OSNR. The OSNR monitoring results for three signal types are shown in Fig. 6. It is clear from the figure that OSNR estimates are quite accurate and the mean estimation errors for 112 Gbps PM QPSK, 112 Gbps PM 16-QAM, and 240 Gbps PM 64-QAM signals are 1.2 dB, 0.4 dB, and 1 dB, respectively. Hence, the mean OSNR estimation error for the three signal types considered in this work is 0.86 dB which is comparable to the ones reported for the existing OSNR monitoring techniques [5–13]. The OSNR estimation errors can potentially be reduced by employing relatively large training data sets. It can be concluded from the above results that the proposed technique can determine both OSNRs and modulation formatsof received signals with good accuracies. Furthermore, the OSNR monitoring and MFI accuracies demonstrated by this technique are comparable with those of methods dedicated for estimating either OSNR [5–13] or modulation format [16–19].

 figure: Fig. 5

Fig. 5 Elements of output vectors v1 for (a) QPSK, (b) 16-QAM, and (c) 64-QAM modulation formats when 57 vectors x belonging to testing data set are applied at DNN-MFI’s input.

Download Full Size | PPT Slide | PDF

Tables Icon

Table 1. Identification accuracies for different modulation formats using the proposed technique.

 figure: Fig. 6

Fig. 6 True versus estimated OSNRs for (a) QPSK, (b) 16-QAM, and (c) 64-QAM signals using the proposed technique.

Download Full Size | PPT Slide | PDF

The experimental results validate following main advantages of proposed technique over existing methods. (i) This technique enables joint estimation of OSNR and modulation format while all the previous methods focus on either OSNR monitoring or MFI but not joint determination of these parameters. (ii) Unlike some contemporary methods which require additional hardware components, this technique achieves desired functionalities by utilizing standard digital coherent receiver, thus eliminating extra implementation costs. (iii) The proposed technique is completely non-intrusive as well as NDA. This is in contrast to some existing methods which necessitate insertion of pilot tones into the signals or the transmissionof additional training sequences for monitoring purposes. (iv) This technique is also non-iterative and hence joint OSNR monitoring and MFI can be performed swiftly. In comparison, many current methods employ iterative algorithms which intrinsically take longer computation time, thus limiting their use in EONs involving fast variations of OSNRs/modulation formats.

The proposed technique can enable joint OSNR monitoring and MFI for several other signal types as well, provided that AHs corresponding to these signals exhibit unique and distinctive patterns. As far as parallel processing ability of the proposed method is concerned, there have been several works recently exploiting the inherent parallelism of the DNN models for real-time implementation [26–28]. Therefore, we believe that the proposed DNNs-based technique is feasible for real-time implementation in digital coherent receivers. Finally, regarding computational complexity of the proposed method, it should be noted that the training process of DNNs used in this work may indeed require considerable computational resources as well as processing time. However, we would like to emphasize that the training procedure of DNNs is carried out completely offline. Once the parameters of DNNs are optimized offline, the actual OSNR monitoring/MFI process in an optical network employing trained DNNs involves simple matrix multiplications. Thus, we believe that the computational complexity of the proposed technique using trained DNNs will be comparable to those of existing OSNR monitoring/MFI methods.

5. Conclusions

In this paper, we proposed and experimentally demonstrated a joint OSNR monitoring and MFI technique in digital coherent receivers by using DNNs in conjunction with signals’ AHs. Experimental results show good OSNR monitoring accuracies for three widely-used signal types. Moreover, NDA MFI with an accuracy of 100% has been validated. The proposed technique employs standard digital coherent receiver and avoids the use of pilot tones or training sequences. Therefore, it is ideal for simple and low-cost OSNR monitoring/MFI in future EONs.

Funding

Hong Kong Government General Research Fund (PolyU 152079/14E, PolyU 152109/14E, PolyU 152757/16E); National Natural Science Foundation of China (NSFC) (61435006); The Hong Kong Polytechnic University (PolyU 4-BCCK).

References and links

1. Z. Dong, F. N. Khan, Q. Sui, K. Zhong, C. Lu, and A. P. T. Lau, “Optical performance monitoring: a review of current and future technologies,” IEEE/OSA J. Lightwave Technol. 34(2), 525–543 (2016). [CrossRef]  

2. F. N. Khan, Z. Dong, C. Lu, and A. P. T. Lau, “Optical performance monitoring for fiber-optic communication networks,” in Enabling Technologies for High Spectral-Efficiency Coherent Optical Communication Networks, X. Zhou and C. Xie, eds. (Wiley, 2016), Chap. 14.

3. S. J. Savory, “Digital coherent optical receivers: algorithms and subsystems,” IEEE J. Sel. Top. Quantum Electron. 16(5), 1164–1178 (2010). [CrossRef]  

4. C. K. Chan, Optical Performance Monitoring (Academic, 2010).

5. M. S. Faruk, Y. Mori, and K. Kikuchi, “In-band estimation of optical signal-to-noise ratio from equalized signals in digital coherent receivers,” IEEE Photonics J. 6(1), 7800109 (2014). [CrossRef]  

6. R. Schmogrow, B. Nebendahl, M. Winter, A. Josten, D. Hillerkuss, S. Koenig, J. Meyer, M. Dreschmann, M. Huebner, C. Koos, J. Becker, W. Freude, and J. Leuthold, “Error vector magnitude as a performance measure for advanced modulation formats,” IEEE Photonics Technol. Lett. 24(1), 61–63 (2012). [CrossRef]  

7. M. R. Chitgarha, S. Khaleghi, W. Daab, A. Almaiman, M. Ziyadi, A. Mohajerin-Ariaei, D. Rogawski, M. Tur, J. D. Touch, V. Vusirikala, W. Zhao, and A. E. Willner, “Demonstration of in-service wavelength division multiplexing optical-signal-to-noise ratio performance monitoring and operating guidelines for coherent data channels with different modulation formats and various baud rates,” Opt. Lett. 39(6), 1605–1608 (2014). [CrossRef]   [PubMed]  

8. A. S. Ahsan, M. S. Wang, M. R. Chitgarha, D. C. Kilper, A. E. Willner, and K. Bergman, “Autonomous OSNR monitoring and cross-Layer control in a mixed bit-rate and modulation format system using pilot tones,” in Proc. Advanced Photon. Comm. (APC, 2014), paper NT4C.3.

9. L. Lundberg, H. Sunnerud, and P. Johannisson, “In-band OSNR monitoring of PM-QPSK using the Stokes parameters,” in Proc. Optical Fiber Comm. Conf. (OFC, 2015), paper W4D. 5. [CrossRef]  

10. C. Do, A. V. Tran, C. Zhu, D. Hewitt, and E. Skafidas, “Data-aided OSNR estimation for QPSK and 16-QAM coherent optical system,” IEEE Photonics J. 5(5), 6601609 (2013). [CrossRef]  

11. S. Oda, J. Y. Yang, Y. Akasaka, K. Sone, Y. Aoki, M. Sekiya, and J. C. Rasmussen, “In-band OSNR monitor using an optical bandpass filter and optical power measurements for superchannel signals,” in Proc. European Conference and Exhibition on Optical Communication (ECOC, 2013), paper P.3.12. [CrossRef]  

12. T. S. R. Shen, Q. Sui, and A. P. T. Lau, “OSNR monitoring for PM-QPSK systems with large inline chromatic dispersion using artificial neural network technique,” IEEE Photonics Technol. Lett. 26(13), 1291–1294 (2012).

13. Z. Dong, A. P. T. Lau, and C. Lu, “OSNR monitoring for QPSK and 16-QAM systems in presence of fiber nonlinearities for digital coherent receivers,” Opt. Express 20(17), 19520–19534 (2012). [CrossRef]   [PubMed]  

14. I. Tomkos, S. Azodolmolky, J. Sole-Pareta, D. Careglio, and E. Palkopoulou, “A tutorial on the flexible optical networking paradigm: state of the art, trends, and research challenges,” Proc. IEEE 102(9), 1317–1337 (2014). [CrossRef]  

15. F. N. Khan, Y. Zhou, A. P. T. Lau, and C. Lu, “Modulation format identification in heterogeneous fiber-optic networks using artificial neural networks,” Opt. Express 20(11), 12422–12431 (2012). [CrossRef]   [PubMed]  

16. N. G. Gonzalez, D. Zibar, and I. T. Monroy, “Cognitive digital receiver for burst mode phase modulated radio over fiber links,” in Proc. European Conference and Exhibition on Optical Communication (ECOC, 2010), paper P6.11. [CrossRef]  

17. P. Isautier, K. Mehta, A. J. Stark, and S. E. Ralph, “Robust architecture for autonomous coherent optical receivers,” IEEE J. Opt. Commun. Netw. 7(9), 864–874 (2015). [CrossRef]  

18. R. Borkowski, D. Zibar, A. Caballero, V. Arlunno, and I. T. Monroy, “Stokes space-based optical modulation format recognition in digital coherent receivers,” IEEE Photonics Technol. Lett. 25(21), 2129–2132 (2013). [CrossRef]  

19. S. M. Bilal, G. Bosco, Z. Dong, A. P. T. Lau, and C. Lu, “Blind modulation format identification for digital coherent receivers,” Opt. Express 23(20), 26769–26778 (2015). [CrossRef]   [PubMed]  

20. Y. Bengio, A. Courville, and P. Vincent, “Representation learning: a review and new perspectives,” IEEE Trans. Pattern Anal. Mach. Intell. 35(8), 1798–1828 (2013). [CrossRef]   [PubMed]  

21. F. N. Khan, C. Lu, and A. P. T. Lau, “Joint modulation format/bit-rate classification and signal-to-noise ratio estimation in multipath fading channels using deep machine learning,” IET Electron. Lett. 52(14), 1272–1274 (2016). [CrossRef]  

22. Y. Bengio, “Learning deep architectures for AI,” Found. Trends Mach. Learn. 2(1), 1–127 (2009). [CrossRef]  

23. F. N. Khan, K. Zhong, W. H. Al-Arashi, C. Yu, C. Lu, and A. P. T. Lau, “Modulation format identification in coherent receivers using deep machine learning,” IEEE Photonics Technol. Lett. 28(17), 1886–1889 (2016). [CrossRef]  

24. C. Lu, A. P. T. Lau, F. N. Khan, Q. Sui, J. Zhao, Z. Li, H.-Y. Tam, and P. K. A. Wai, “Optical performance monitoring techniques for high capacity optical networks,” in Proc. International Symposium on Communication Systems, Networks and Digital Signal Processing (CSNDSP, 2010), pp. 678−681.

25. F. N. Khan, A. P. T. Lau, T. B. Anderson, J. C. Li, C. Lu, and P. K. A. Wai, “Simultaneous and independent OSNR and chromatic dispersion monitoring using empirical moments of asynchronously sampled signal amplitudes,” IEEE Photonics J. 4(5), 1340–1350 (2012). [CrossRef]  

26. A. Ardakani, F. L. -Primeau, N. Onizawa, T. Hanyu, and W. J. Gross, “VLSI implementation of deep neural network using integral stochastic computing,” IEEE Transactions on very large scale integration (VLSI) systems (to be published).

27. F. O. -Zamorano, J. M. Jerez, I. Gómez, and L. Franco, “Deep neural network architecture implementation on FPGAs using a layer multiplexing scheme,” in Proc. International Conference on Distributed Computing and Artificial Intelligence (DCAI, 2016), pp. 79−86.

28. A. Ardakani, C. Condo, and W. J. Gross, “Sparsely-connected neural networks: towards efficient VLSI implementation of deep neural networks,” in Proc. International Conference on Learning Representations (ICLR, 2017).

References

  • View by:
  • |
  • |
  • |

  1. Z. Dong, F. N. Khan, Q. Sui, K. Zhong, C. Lu, and A. P. T. Lau, “Optical performance monitoring: a review of current and future technologies,” IEEE/OSA J. Lightwave Technol. 34(2), 525–543 (2016).
    [Crossref]
  2. F. N. Khan, Z. Dong, C. Lu, and A. P. T. Lau, “Optical performance monitoring for fiber-optic communication networks,” in Enabling Technologies for High Spectral-Efficiency Coherent Optical Communication Networks, X. Zhou and C. Xie, eds. (Wiley, 2016), Chap. 14.
  3. S. J. Savory, “Digital coherent optical receivers: algorithms and subsystems,” IEEE J. Sel. Top. Quantum Electron. 16(5), 1164–1178 (2010).
    [Crossref]
  4. C. K. Chan, Optical Performance Monitoring (Academic, 2010).
  5. M. S. Faruk, Y. Mori, and K. Kikuchi, “In-band estimation of optical signal-to-noise ratio from equalized signals in digital coherent receivers,” IEEE Photonics J. 6(1), 7800109 (2014).
    [Crossref]
  6. R. Schmogrow, B. Nebendahl, M. Winter, A. Josten, D. Hillerkuss, S. Koenig, J. Meyer, M. Dreschmann, M. Huebner, C. Koos, J. Becker, W. Freude, and J. Leuthold, “Error vector magnitude as a performance measure for advanced modulation formats,” IEEE Photonics Technol. Lett. 24(1), 61–63 (2012).
    [Crossref]
  7. M. R. Chitgarha, S. Khaleghi, W. Daab, A. Almaiman, M. Ziyadi, A. Mohajerin-Ariaei, D. Rogawski, M. Tur, J. D. Touch, V. Vusirikala, W. Zhao, and A. E. Willner, “Demonstration of in-service wavelength division multiplexing optical-signal-to-noise ratio performance monitoring and operating guidelines for coherent data channels with different modulation formats and various baud rates,” Opt. Lett. 39(6), 1605–1608 (2014).
    [Crossref] [PubMed]
  8. A. S. Ahsan, M. S. Wang, M. R. Chitgarha, D. C. Kilper, A. E. Willner, and K. Bergman, “Autonomous OSNR monitoring and cross-Layer control in a mixed bit-rate and modulation format system using pilot tones,” in Proc. Advanced Photon. Comm. (APC, 2014), paper NT4C.3.
  9. L. Lundberg, H. Sunnerud, and P. Johannisson, “In-band OSNR monitoring of PM-QPSK using the Stokes parameters,” in Proc. Optical Fiber Comm. Conf. (OFC, 2015), paper W4D. 5.
    [Crossref]
  10. C. Do, A. V. Tran, C. Zhu, D. Hewitt, and E. Skafidas, “Data-aided OSNR estimation for QPSK and 16-QAM coherent optical system,” IEEE Photonics J. 5(5), 6601609 (2013).
    [Crossref]
  11. S. Oda, J. Y. Yang, Y. Akasaka, K. Sone, Y. Aoki, M. Sekiya, and J. C. Rasmussen, “In-band OSNR monitor using an optical bandpass filter and optical power measurements for superchannel signals,” in Proc. European Conference and Exhibition on Optical Communication (ECOC, 2013), paper P.3.12.
    [Crossref]
  12. T. S. R. Shen, Q. Sui, and A. P. T. Lau, “OSNR monitoring for PM-QPSK systems with large inline chromatic dispersion using artificial neural network technique,” IEEE Photonics Technol. Lett. 26(13), 1291–1294 (2012).
  13. Z. Dong, A. P. T. Lau, and C. Lu, “OSNR monitoring for QPSK and 16-QAM systems in presence of fiber nonlinearities for digital coherent receivers,” Opt. Express 20(17), 19520–19534 (2012).
    [Crossref] [PubMed]
  14. I. Tomkos, S. Azodolmolky, J. Sole-Pareta, D. Careglio, and E. Palkopoulou, “A tutorial on the flexible optical networking paradigm: state of the art, trends, and research challenges,” Proc. IEEE 102(9), 1317–1337 (2014).
    [Crossref]
  15. F. N. Khan, Y. Zhou, A. P. T. Lau, and C. Lu, “Modulation format identification in heterogeneous fiber-optic networks using artificial neural networks,” Opt. Express 20(11), 12422–12431 (2012).
    [Crossref] [PubMed]
  16. N. G. Gonzalez, D. Zibar, and I. T. Monroy, “Cognitive digital receiver for burst mode phase modulated radio over fiber links,” in Proc. European Conference and Exhibition on Optical Communication (ECOC, 2010), paper P6.11.
    [Crossref]
  17. P. Isautier, K. Mehta, A. J. Stark, and S. E. Ralph, “Robust architecture for autonomous coherent optical receivers,” IEEE J. Opt. Commun. Netw. 7(9), 864–874 (2015).
    [Crossref]
  18. R. Borkowski, D. Zibar, A. Caballero, V. Arlunno, and I. T. Monroy, “Stokes space-based optical modulation format recognition in digital coherent receivers,” IEEE Photonics Technol. Lett. 25(21), 2129–2132 (2013).
    [Crossref]
  19. S. M. Bilal, G. Bosco, Z. Dong, A. P. T. Lau, and C. Lu, “Blind modulation format identification for digital coherent receivers,” Opt. Express 23(20), 26769–26778 (2015).
    [Crossref] [PubMed]
  20. Y. Bengio, A. Courville, and P. Vincent, “Representation learning: a review and new perspectives,” IEEE Trans. Pattern Anal. Mach. Intell. 35(8), 1798–1828 (2013).
    [Crossref] [PubMed]
  21. F. N. Khan, C. Lu, and A. P. T. Lau, “Joint modulation format/bit-rate classification and signal-to-noise ratio estimation in multipath fading channels using deep machine learning,” IET Electron. Lett. 52(14), 1272–1274 (2016).
    [Crossref]
  22. Y. Bengio, “Learning deep architectures for AI,” Found. Trends Mach. Learn. 2(1), 1–127 (2009).
    [Crossref]
  23. F. N. Khan, K. Zhong, W. H. Al-Arashi, C. Yu, C. Lu, and A. P. T. Lau, “Modulation format identification in coherent receivers using deep machine learning,” IEEE Photonics Technol. Lett. 28(17), 1886–1889 (2016).
    [Crossref]
  24. C. Lu, A. P. T. Lau, F. N. Khan, Q. Sui, J. Zhao, Z. Li, H.-Y. Tam, and P. K. A. Wai, “Optical performance monitoring techniques for high capacity optical networks,” in Proc. International Symposium on Communication Systems, Networks and Digital Signal Processing (CSNDSP, 2010), pp. 678−681.
  25. F. N. Khan, A. P. T. Lau, T. B. Anderson, J. C. Li, C. Lu, and P. K. A. Wai, “Simultaneous and independent OSNR and chromatic dispersion monitoring using empirical moments of asynchronously sampled signal amplitudes,” IEEE Photonics J. 4(5), 1340–1350 (2012).
    [Crossref]
  26. A. Ardakani, F. L. -Primeau, N. Onizawa, T. Hanyu, and W. J. Gross, “VLSI implementation of deep neural network using integral stochastic computing,” IEEE Transactions on very large scale integration (VLSI) systems (to be published).
  27. F. O. -Zamorano, J. M. Jerez, I. Gómez, and L. Franco, “Deep neural network architecture implementation on FPGAs using a layer multiplexing scheme,” in Proc. International Conference on Distributed Computing and Artificial Intelligence (DCAI, 2016), pp. 79−86.
  28. A. Ardakani, C. Condo, and W. J. Gross, “Sparsely-connected neural networks: towards efficient VLSI implementation of deep neural networks,” in Proc. International Conference on Learning Representations (ICLR, 2017).

2016 (3)

Z. Dong, F. N. Khan, Q. Sui, K. Zhong, C. Lu, and A. P. T. Lau, “Optical performance monitoring: a review of current and future technologies,” IEEE/OSA J. Lightwave Technol. 34(2), 525–543 (2016).
[Crossref]

F. N. Khan, C. Lu, and A. P. T. Lau, “Joint modulation format/bit-rate classification and signal-to-noise ratio estimation in multipath fading channels using deep machine learning,” IET Electron. Lett. 52(14), 1272–1274 (2016).
[Crossref]

F. N. Khan, K. Zhong, W. H. Al-Arashi, C. Yu, C. Lu, and A. P. T. Lau, “Modulation format identification in coherent receivers using deep machine learning,” IEEE Photonics Technol. Lett. 28(17), 1886–1889 (2016).
[Crossref]

2015 (2)

S. M. Bilal, G. Bosco, Z. Dong, A. P. T. Lau, and C. Lu, “Blind modulation format identification for digital coherent receivers,” Opt. Express 23(20), 26769–26778 (2015).
[Crossref] [PubMed]

P. Isautier, K. Mehta, A. J. Stark, and S. E. Ralph, “Robust architecture for autonomous coherent optical receivers,” IEEE J. Opt. Commun. Netw. 7(9), 864–874 (2015).
[Crossref]

2014 (3)

I. Tomkos, S. Azodolmolky, J. Sole-Pareta, D. Careglio, and E. Palkopoulou, “A tutorial on the flexible optical networking paradigm: state of the art, trends, and research challenges,” Proc. IEEE 102(9), 1317–1337 (2014).
[Crossref]

M. S. Faruk, Y. Mori, and K. Kikuchi, “In-band estimation of optical signal-to-noise ratio from equalized signals in digital coherent receivers,” IEEE Photonics J. 6(1), 7800109 (2014).
[Crossref]

M. R. Chitgarha, S. Khaleghi, W. Daab, A. Almaiman, M. Ziyadi, A. Mohajerin-Ariaei, D. Rogawski, M. Tur, J. D. Touch, V. Vusirikala, W. Zhao, and A. E. Willner, “Demonstration of in-service wavelength division multiplexing optical-signal-to-noise ratio performance monitoring and operating guidelines for coherent data channels with different modulation formats and various baud rates,” Opt. Lett. 39(6), 1605–1608 (2014).
[Crossref] [PubMed]

2013 (3)

C. Do, A. V. Tran, C. Zhu, D. Hewitt, and E. Skafidas, “Data-aided OSNR estimation for QPSK and 16-QAM coherent optical system,” IEEE Photonics J. 5(5), 6601609 (2013).
[Crossref]

R. Borkowski, D. Zibar, A. Caballero, V. Arlunno, and I. T. Monroy, “Stokes space-based optical modulation format recognition in digital coherent receivers,” IEEE Photonics Technol. Lett. 25(21), 2129–2132 (2013).
[Crossref]

Y. Bengio, A. Courville, and P. Vincent, “Representation learning: a review and new perspectives,” IEEE Trans. Pattern Anal. Mach. Intell. 35(8), 1798–1828 (2013).
[Crossref] [PubMed]

2012 (5)

F. N. Khan, Y. Zhou, A. P. T. Lau, and C. Lu, “Modulation format identification in heterogeneous fiber-optic networks using artificial neural networks,” Opt. Express 20(11), 12422–12431 (2012).
[Crossref] [PubMed]

T. S. R. Shen, Q. Sui, and A. P. T. Lau, “OSNR monitoring for PM-QPSK systems with large inline chromatic dispersion using artificial neural network technique,” IEEE Photonics Technol. Lett. 26(13), 1291–1294 (2012).

Z. Dong, A. P. T. Lau, and C. Lu, “OSNR monitoring for QPSK and 16-QAM systems in presence of fiber nonlinearities for digital coherent receivers,” Opt. Express 20(17), 19520–19534 (2012).
[Crossref] [PubMed]

R. Schmogrow, B. Nebendahl, M. Winter, A. Josten, D. Hillerkuss, S. Koenig, J. Meyer, M. Dreschmann, M. Huebner, C. Koos, J. Becker, W. Freude, and J. Leuthold, “Error vector magnitude as a performance measure for advanced modulation formats,” IEEE Photonics Technol. Lett. 24(1), 61–63 (2012).
[Crossref]

F. N. Khan, A. P. T. Lau, T. B. Anderson, J. C. Li, C. Lu, and P. K. A. Wai, “Simultaneous and independent OSNR and chromatic dispersion monitoring using empirical moments of asynchronously sampled signal amplitudes,” IEEE Photonics J. 4(5), 1340–1350 (2012).
[Crossref]

2010 (1)

S. J. Savory, “Digital coherent optical receivers: algorithms and subsystems,” IEEE J. Sel. Top. Quantum Electron. 16(5), 1164–1178 (2010).
[Crossref]

2009 (1)

Y. Bengio, “Learning deep architectures for AI,” Found. Trends Mach. Learn. 2(1), 1–127 (2009).
[Crossref]

Al-Arashi, W. H.

F. N. Khan, K. Zhong, W. H. Al-Arashi, C. Yu, C. Lu, and A. P. T. Lau, “Modulation format identification in coherent receivers using deep machine learning,” IEEE Photonics Technol. Lett. 28(17), 1886–1889 (2016).
[Crossref]

Almaiman, A.

Anderson, T. B.

F. N. Khan, A. P. T. Lau, T. B. Anderson, J. C. Li, C. Lu, and P. K. A. Wai, “Simultaneous and independent OSNR and chromatic dispersion monitoring using empirical moments of asynchronously sampled signal amplitudes,” IEEE Photonics J. 4(5), 1340–1350 (2012).
[Crossref]

Ardakani, A.

A. Ardakani, C. Condo, and W. J. Gross, “Sparsely-connected neural networks: towards efficient VLSI implementation of deep neural networks,” in Proc. International Conference on Learning Representations (ICLR, 2017).

Arlunno, V.

R. Borkowski, D. Zibar, A. Caballero, V. Arlunno, and I. T. Monroy, “Stokes space-based optical modulation format recognition in digital coherent receivers,” IEEE Photonics Technol. Lett. 25(21), 2129–2132 (2013).
[Crossref]

Azodolmolky, S.

I. Tomkos, S. Azodolmolky, J. Sole-Pareta, D. Careglio, and E. Palkopoulou, “A tutorial on the flexible optical networking paradigm: state of the art, trends, and research challenges,” Proc. IEEE 102(9), 1317–1337 (2014).
[Crossref]

Becker, J.

R. Schmogrow, B. Nebendahl, M. Winter, A. Josten, D. Hillerkuss, S. Koenig, J. Meyer, M. Dreschmann, M. Huebner, C. Koos, J. Becker, W. Freude, and J. Leuthold, “Error vector magnitude as a performance measure for advanced modulation formats,” IEEE Photonics Technol. Lett. 24(1), 61–63 (2012).
[Crossref]

Bengio, Y.

Y. Bengio, A. Courville, and P. Vincent, “Representation learning: a review and new perspectives,” IEEE Trans. Pattern Anal. Mach. Intell. 35(8), 1798–1828 (2013).
[Crossref] [PubMed]

Y. Bengio, “Learning deep architectures for AI,” Found. Trends Mach. Learn. 2(1), 1–127 (2009).
[Crossref]

Bilal, S. M.

Borkowski, R.

R. Borkowski, D. Zibar, A. Caballero, V. Arlunno, and I. T. Monroy, “Stokes space-based optical modulation format recognition in digital coherent receivers,” IEEE Photonics Technol. Lett. 25(21), 2129–2132 (2013).
[Crossref]

Bosco, G.

Caballero, A.

R. Borkowski, D. Zibar, A. Caballero, V. Arlunno, and I. T. Monroy, “Stokes space-based optical modulation format recognition in digital coherent receivers,” IEEE Photonics Technol. Lett. 25(21), 2129–2132 (2013).
[Crossref]

Careglio, D.

I. Tomkos, S. Azodolmolky, J. Sole-Pareta, D. Careglio, and E. Palkopoulou, “A tutorial on the flexible optical networking paradigm: state of the art, trends, and research challenges,” Proc. IEEE 102(9), 1317–1337 (2014).
[Crossref]

Chitgarha, M. R.

Condo, C.

A. Ardakani, C. Condo, and W. J. Gross, “Sparsely-connected neural networks: towards efficient VLSI implementation of deep neural networks,” in Proc. International Conference on Learning Representations (ICLR, 2017).

Courville, A.

Y. Bengio, A. Courville, and P. Vincent, “Representation learning: a review and new perspectives,” IEEE Trans. Pattern Anal. Mach. Intell. 35(8), 1798–1828 (2013).
[Crossref] [PubMed]

Daab, W.

Do, C.

C. Do, A. V. Tran, C. Zhu, D. Hewitt, and E. Skafidas, “Data-aided OSNR estimation for QPSK and 16-QAM coherent optical system,” IEEE Photonics J. 5(5), 6601609 (2013).
[Crossref]

Dong, Z.

Dreschmann, M.

R. Schmogrow, B. Nebendahl, M. Winter, A. Josten, D. Hillerkuss, S. Koenig, J. Meyer, M. Dreschmann, M. Huebner, C. Koos, J. Becker, W. Freude, and J. Leuthold, “Error vector magnitude as a performance measure for advanced modulation formats,” IEEE Photonics Technol. Lett. 24(1), 61–63 (2012).
[Crossref]

Faruk, M. S.

M. S. Faruk, Y. Mori, and K. Kikuchi, “In-band estimation of optical signal-to-noise ratio from equalized signals in digital coherent receivers,” IEEE Photonics J. 6(1), 7800109 (2014).
[Crossref]

Freude, W.

R. Schmogrow, B. Nebendahl, M. Winter, A. Josten, D. Hillerkuss, S. Koenig, J. Meyer, M. Dreschmann, M. Huebner, C. Koos, J. Becker, W. Freude, and J. Leuthold, “Error vector magnitude as a performance measure for advanced modulation formats,” IEEE Photonics Technol. Lett. 24(1), 61–63 (2012).
[Crossref]

Gross, W. J.

A. Ardakani, C. Condo, and W. J. Gross, “Sparsely-connected neural networks: towards efficient VLSI implementation of deep neural networks,” in Proc. International Conference on Learning Representations (ICLR, 2017).

Hewitt, D.

C. Do, A. V. Tran, C. Zhu, D. Hewitt, and E. Skafidas, “Data-aided OSNR estimation for QPSK and 16-QAM coherent optical system,” IEEE Photonics J. 5(5), 6601609 (2013).
[Crossref]

Hillerkuss, D.

R. Schmogrow, B. Nebendahl, M. Winter, A. Josten, D. Hillerkuss, S. Koenig, J. Meyer, M. Dreschmann, M. Huebner, C. Koos, J. Becker, W. Freude, and J. Leuthold, “Error vector magnitude as a performance measure for advanced modulation formats,” IEEE Photonics Technol. Lett. 24(1), 61–63 (2012).
[Crossref]

Huebner, M.

R. Schmogrow, B. Nebendahl, M. Winter, A. Josten, D. Hillerkuss, S. Koenig, J. Meyer, M. Dreschmann, M. Huebner, C. Koos, J. Becker, W. Freude, and J. Leuthold, “Error vector magnitude as a performance measure for advanced modulation formats,” IEEE Photonics Technol. Lett. 24(1), 61–63 (2012).
[Crossref]

Isautier, P.

P. Isautier, K. Mehta, A. J. Stark, and S. E. Ralph, “Robust architecture for autonomous coherent optical receivers,” IEEE J. Opt. Commun. Netw. 7(9), 864–874 (2015).
[Crossref]

Josten, A.

R. Schmogrow, B. Nebendahl, M. Winter, A. Josten, D. Hillerkuss, S. Koenig, J. Meyer, M. Dreschmann, M. Huebner, C. Koos, J. Becker, W. Freude, and J. Leuthold, “Error vector magnitude as a performance measure for advanced modulation formats,” IEEE Photonics Technol. Lett. 24(1), 61–63 (2012).
[Crossref]

Khaleghi, S.

Khan, F. N.

Z. Dong, F. N. Khan, Q. Sui, K. Zhong, C. Lu, and A. P. T. Lau, “Optical performance monitoring: a review of current and future technologies,” IEEE/OSA J. Lightwave Technol. 34(2), 525–543 (2016).
[Crossref]

F. N. Khan, C. Lu, and A. P. T. Lau, “Joint modulation format/bit-rate classification and signal-to-noise ratio estimation in multipath fading channels using deep machine learning,” IET Electron. Lett. 52(14), 1272–1274 (2016).
[Crossref]

F. N. Khan, K. Zhong, W. H. Al-Arashi, C. Yu, C. Lu, and A. P. T. Lau, “Modulation format identification in coherent receivers using deep machine learning,” IEEE Photonics Technol. Lett. 28(17), 1886–1889 (2016).
[Crossref]

F. N. Khan, A. P. T. Lau, T. B. Anderson, J. C. Li, C. Lu, and P. K. A. Wai, “Simultaneous and independent OSNR and chromatic dispersion monitoring using empirical moments of asynchronously sampled signal amplitudes,” IEEE Photonics J. 4(5), 1340–1350 (2012).
[Crossref]

F. N. Khan, Y. Zhou, A. P. T. Lau, and C. Lu, “Modulation format identification in heterogeneous fiber-optic networks using artificial neural networks,” Opt. Express 20(11), 12422–12431 (2012).
[Crossref] [PubMed]

C. Lu, A. P. T. Lau, F. N. Khan, Q. Sui, J. Zhao, Z. Li, H.-Y. Tam, and P. K. A. Wai, “Optical performance monitoring techniques for high capacity optical networks,” in Proc. International Symposium on Communication Systems, Networks and Digital Signal Processing (CSNDSP, 2010), pp. 678−681.

Kikuchi, K.

M. S. Faruk, Y. Mori, and K. Kikuchi, “In-band estimation of optical signal-to-noise ratio from equalized signals in digital coherent receivers,” IEEE Photonics J. 6(1), 7800109 (2014).
[Crossref]

Koenig, S.

R. Schmogrow, B. Nebendahl, M. Winter, A. Josten, D. Hillerkuss, S. Koenig, J. Meyer, M. Dreschmann, M. Huebner, C. Koos, J. Becker, W. Freude, and J. Leuthold, “Error vector magnitude as a performance measure for advanced modulation formats,” IEEE Photonics Technol. Lett. 24(1), 61–63 (2012).
[Crossref]

Koos, C.

R. Schmogrow, B. Nebendahl, M. Winter, A. Josten, D. Hillerkuss, S. Koenig, J. Meyer, M. Dreschmann, M. Huebner, C. Koos, J. Becker, W. Freude, and J. Leuthold, “Error vector magnitude as a performance measure for advanced modulation formats,” IEEE Photonics Technol. Lett. 24(1), 61–63 (2012).
[Crossref]

Lau, A. P. T.

Z. Dong, F. N. Khan, Q. Sui, K. Zhong, C. Lu, and A. P. T. Lau, “Optical performance monitoring: a review of current and future technologies,” IEEE/OSA J. Lightwave Technol. 34(2), 525–543 (2016).
[Crossref]

F. N. Khan, C. Lu, and A. P. T. Lau, “Joint modulation format/bit-rate classification and signal-to-noise ratio estimation in multipath fading channels using deep machine learning,” IET Electron. Lett. 52(14), 1272–1274 (2016).
[Crossref]

F. N. Khan, K. Zhong, W. H. Al-Arashi, C. Yu, C. Lu, and A. P. T. Lau, “Modulation format identification in coherent receivers using deep machine learning,” IEEE Photonics Technol. Lett. 28(17), 1886–1889 (2016).
[Crossref]

S. M. Bilal, G. Bosco, Z. Dong, A. P. T. Lau, and C. Lu, “Blind modulation format identification for digital coherent receivers,” Opt. Express 23(20), 26769–26778 (2015).
[Crossref] [PubMed]

T. S. R. Shen, Q. Sui, and A. P. T. Lau, “OSNR monitoring for PM-QPSK systems with large inline chromatic dispersion using artificial neural network technique,” IEEE Photonics Technol. Lett. 26(13), 1291–1294 (2012).

F. N. Khan, Y. Zhou, A. P. T. Lau, and C. Lu, “Modulation format identification in heterogeneous fiber-optic networks using artificial neural networks,” Opt. Express 20(11), 12422–12431 (2012).
[Crossref] [PubMed]

Z. Dong, A. P. T. Lau, and C. Lu, “OSNR monitoring for QPSK and 16-QAM systems in presence of fiber nonlinearities for digital coherent receivers,” Opt. Express 20(17), 19520–19534 (2012).
[Crossref] [PubMed]

F. N. Khan, A. P. T. Lau, T. B. Anderson, J. C. Li, C. Lu, and P. K. A. Wai, “Simultaneous and independent OSNR and chromatic dispersion monitoring using empirical moments of asynchronously sampled signal amplitudes,” IEEE Photonics J. 4(5), 1340–1350 (2012).
[Crossref]

C. Lu, A. P. T. Lau, F. N. Khan, Q. Sui, J. Zhao, Z. Li, H.-Y. Tam, and P. K. A. Wai, “Optical performance monitoring techniques for high capacity optical networks,” in Proc. International Symposium on Communication Systems, Networks and Digital Signal Processing (CSNDSP, 2010), pp. 678−681.

Leuthold, J.

R. Schmogrow, B. Nebendahl, M. Winter, A. Josten, D. Hillerkuss, S. Koenig, J. Meyer, M. Dreschmann, M. Huebner, C. Koos, J. Becker, W. Freude, and J. Leuthold, “Error vector magnitude as a performance measure for advanced modulation formats,” IEEE Photonics Technol. Lett. 24(1), 61–63 (2012).
[Crossref]

Li, J. C.

F. N. Khan, A. P. T. Lau, T. B. Anderson, J. C. Li, C. Lu, and P. K. A. Wai, “Simultaneous and independent OSNR and chromatic dispersion monitoring using empirical moments of asynchronously sampled signal amplitudes,” IEEE Photonics J. 4(5), 1340–1350 (2012).
[Crossref]

Li, Z.

C. Lu, A. P. T. Lau, F. N. Khan, Q. Sui, J. Zhao, Z. Li, H.-Y. Tam, and P. K. A. Wai, “Optical performance monitoring techniques for high capacity optical networks,” in Proc. International Symposium on Communication Systems, Networks and Digital Signal Processing (CSNDSP, 2010), pp. 678−681.

Lu, C.

F. N. Khan, K. Zhong, W. H. Al-Arashi, C. Yu, C. Lu, and A. P. T. Lau, “Modulation format identification in coherent receivers using deep machine learning,” IEEE Photonics Technol. Lett. 28(17), 1886–1889 (2016).
[Crossref]

Z. Dong, F. N. Khan, Q. Sui, K. Zhong, C. Lu, and A. P. T. Lau, “Optical performance monitoring: a review of current and future technologies,” IEEE/OSA J. Lightwave Technol. 34(2), 525–543 (2016).
[Crossref]

F. N. Khan, C. Lu, and A. P. T. Lau, “Joint modulation format/bit-rate classification and signal-to-noise ratio estimation in multipath fading channels using deep machine learning,” IET Electron. Lett. 52(14), 1272–1274 (2016).
[Crossref]

S. M. Bilal, G. Bosco, Z. Dong, A. P. T. Lau, and C. Lu, “Blind modulation format identification for digital coherent receivers,” Opt. Express 23(20), 26769–26778 (2015).
[Crossref] [PubMed]

Z. Dong, A. P. T. Lau, and C. Lu, “OSNR monitoring for QPSK and 16-QAM systems in presence of fiber nonlinearities for digital coherent receivers,” Opt. Express 20(17), 19520–19534 (2012).
[Crossref] [PubMed]

F. N. Khan, Y. Zhou, A. P. T. Lau, and C. Lu, “Modulation format identification in heterogeneous fiber-optic networks using artificial neural networks,” Opt. Express 20(11), 12422–12431 (2012).
[Crossref] [PubMed]

F. N. Khan, A. P. T. Lau, T. B. Anderson, J. C. Li, C. Lu, and P. K. A. Wai, “Simultaneous and independent OSNR and chromatic dispersion monitoring using empirical moments of asynchronously sampled signal amplitudes,” IEEE Photonics J. 4(5), 1340–1350 (2012).
[Crossref]

C. Lu, A. P. T. Lau, F. N. Khan, Q. Sui, J. Zhao, Z. Li, H.-Y. Tam, and P. K. A. Wai, “Optical performance monitoring techniques for high capacity optical networks,” in Proc. International Symposium on Communication Systems, Networks and Digital Signal Processing (CSNDSP, 2010), pp. 678−681.

Mehta, K.

P. Isautier, K. Mehta, A. J. Stark, and S. E. Ralph, “Robust architecture for autonomous coherent optical receivers,” IEEE J. Opt. Commun. Netw. 7(9), 864–874 (2015).
[Crossref]

Meyer, J.

R. Schmogrow, B. Nebendahl, M. Winter, A. Josten, D. Hillerkuss, S. Koenig, J. Meyer, M. Dreschmann, M. Huebner, C. Koos, J. Becker, W. Freude, and J. Leuthold, “Error vector magnitude as a performance measure for advanced modulation formats,” IEEE Photonics Technol. Lett. 24(1), 61–63 (2012).
[Crossref]

Mohajerin-Ariaei, A.

Monroy, I. T.

R. Borkowski, D. Zibar, A. Caballero, V. Arlunno, and I. T. Monroy, “Stokes space-based optical modulation format recognition in digital coherent receivers,” IEEE Photonics Technol. Lett. 25(21), 2129–2132 (2013).
[Crossref]

Mori, Y.

M. S. Faruk, Y. Mori, and K. Kikuchi, “In-band estimation of optical signal-to-noise ratio from equalized signals in digital coherent receivers,” IEEE Photonics J. 6(1), 7800109 (2014).
[Crossref]

Nebendahl, B.

R. Schmogrow, B. Nebendahl, M. Winter, A. Josten, D. Hillerkuss, S. Koenig, J. Meyer, M. Dreschmann, M. Huebner, C. Koos, J. Becker, W. Freude, and J. Leuthold, “Error vector magnitude as a performance measure for advanced modulation formats,” IEEE Photonics Technol. Lett. 24(1), 61–63 (2012).
[Crossref]

Palkopoulou, E.

I. Tomkos, S. Azodolmolky, J. Sole-Pareta, D. Careglio, and E. Palkopoulou, “A tutorial on the flexible optical networking paradigm: state of the art, trends, and research challenges,” Proc. IEEE 102(9), 1317–1337 (2014).
[Crossref]

Ralph, S. E.

P. Isautier, K. Mehta, A. J. Stark, and S. E. Ralph, “Robust architecture for autonomous coherent optical receivers,” IEEE J. Opt. Commun. Netw. 7(9), 864–874 (2015).
[Crossref]

Rogawski, D.

Savory, S. J.

S. J. Savory, “Digital coherent optical receivers: algorithms and subsystems,” IEEE J. Sel. Top. Quantum Electron. 16(5), 1164–1178 (2010).
[Crossref]

Schmogrow, R.

R. Schmogrow, B. Nebendahl, M. Winter, A. Josten, D. Hillerkuss, S. Koenig, J. Meyer, M. Dreschmann, M. Huebner, C. Koos, J. Becker, W. Freude, and J. Leuthold, “Error vector magnitude as a performance measure for advanced modulation formats,” IEEE Photonics Technol. Lett. 24(1), 61–63 (2012).
[Crossref]

Shen, T. S. R.

T. S. R. Shen, Q. Sui, and A. P. T. Lau, “OSNR monitoring for PM-QPSK systems with large inline chromatic dispersion using artificial neural network technique,” IEEE Photonics Technol. Lett. 26(13), 1291–1294 (2012).

Skafidas, E.

C. Do, A. V. Tran, C. Zhu, D. Hewitt, and E. Skafidas, “Data-aided OSNR estimation for QPSK and 16-QAM coherent optical system,” IEEE Photonics J. 5(5), 6601609 (2013).
[Crossref]

Sole-Pareta, J.

I. Tomkos, S. Azodolmolky, J. Sole-Pareta, D. Careglio, and E. Palkopoulou, “A tutorial on the flexible optical networking paradigm: state of the art, trends, and research challenges,” Proc. IEEE 102(9), 1317–1337 (2014).
[Crossref]

Stark, A. J.

P. Isautier, K. Mehta, A. J. Stark, and S. E. Ralph, “Robust architecture for autonomous coherent optical receivers,” IEEE J. Opt. Commun. Netw. 7(9), 864–874 (2015).
[Crossref]

Sui, Q.

Z. Dong, F. N. Khan, Q. Sui, K. Zhong, C. Lu, and A. P. T. Lau, “Optical performance monitoring: a review of current and future technologies,” IEEE/OSA J. Lightwave Technol. 34(2), 525–543 (2016).
[Crossref]

T. S. R. Shen, Q. Sui, and A. P. T. Lau, “OSNR monitoring for PM-QPSK systems with large inline chromatic dispersion using artificial neural network technique,” IEEE Photonics Technol. Lett. 26(13), 1291–1294 (2012).

C. Lu, A. P. T. Lau, F. N. Khan, Q. Sui, J. Zhao, Z. Li, H.-Y. Tam, and P. K. A. Wai, “Optical performance monitoring techniques for high capacity optical networks,” in Proc. International Symposium on Communication Systems, Networks and Digital Signal Processing (CSNDSP, 2010), pp. 678−681.

Tam, H.-Y.

C. Lu, A. P. T. Lau, F. N. Khan, Q. Sui, J. Zhao, Z. Li, H.-Y. Tam, and P. K. A. Wai, “Optical performance monitoring techniques for high capacity optical networks,” in Proc. International Symposium on Communication Systems, Networks and Digital Signal Processing (CSNDSP, 2010), pp. 678−681.

Tomkos, I.

I. Tomkos, S. Azodolmolky, J. Sole-Pareta, D. Careglio, and E. Palkopoulou, “A tutorial on the flexible optical networking paradigm: state of the art, trends, and research challenges,” Proc. IEEE 102(9), 1317–1337 (2014).
[Crossref]

Touch, J. D.

Tran, A. V.

C. Do, A. V. Tran, C. Zhu, D. Hewitt, and E. Skafidas, “Data-aided OSNR estimation for QPSK and 16-QAM coherent optical system,” IEEE Photonics J. 5(5), 6601609 (2013).
[Crossref]

Tur, M.

Vincent, P.

Y. Bengio, A. Courville, and P. Vincent, “Representation learning: a review and new perspectives,” IEEE Trans. Pattern Anal. Mach. Intell. 35(8), 1798–1828 (2013).
[Crossref] [PubMed]

Vusirikala, V.

Wai, P. K. A.

F. N. Khan, A. P. T. Lau, T. B. Anderson, J. C. Li, C. Lu, and P. K. A. Wai, “Simultaneous and independent OSNR and chromatic dispersion monitoring using empirical moments of asynchronously sampled signal amplitudes,” IEEE Photonics J. 4(5), 1340–1350 (2012).
[Crossref]

C. Lu, A. P. T. Lau, F. N. Khan, Q. Sui, J. Zhao, Z. Li, H.-Y. Tam, and P. K. A. Wai, “Optical performance monitoring techniques for high capacity optical networks,” in Proc. International Symposium on Communication Systems, Networks and Digital Signal Processing (CSNDSP, 2010), pp. 678−681.

Willner, A. E.

Winter, M.

R. Schmogrow, B. Nebendahl, M. Winter, A. Josten, D. Hillerkuss, S. Koenig, J. Meyer, M. Dreschmann, M. Huebner, C. Koos, J. Becker, W. Freude, and J. Leuthold, “Error vector magnitude as a performance measure for advanced modulation formats,” IEEE Photonics Technol. Lett. 24(1), 61–63 (2012).
[Crossref]

Yu, C.

F. N. Khan, K. Zhong, W. H. Al-Arashi, C. Yu, C. Lu, and A. P. T. Lau, “Modulation format identification in coherent receivers using deep machine learning,” IEEE Photonics Technol. Lett. 28(17), 1886–1889 (2016).
[Crossref]

Zhao, J.

C. Lu, A. P. T. Lau, F. N. Khan, Q. Sui, J. Zhao, Z. Li, H.-Y. Tam, and P. K. A. Wai, “Optical performance monitoring techniques for high capacity optical networks,” in Proc. International Symposium on Communication Systems, Networks and Digital Signal Processing (CSNDSP, 2010), pp. 678−681.

Zhao, W.

Zhong, K.

Z. Dong, F. N. Khan, Q. Sui, K. Zhong, C. Lu, and A. P. T. Lau, “Optical performance monitoring: a review of current and future technologies,” IEEE/OSA J. Lightwave Technol. 34(2), 525–543 (2016).
[Crossref]

F. N. Khan, K. Zhong, W. H. Al-Arashi, C. Yu, C. Lu, and A. P. T. Lau, “Modulation format identification in coherent receivers using deep machine learning,” IEEE Photonics Technol. Lett. 28(17), 1886–1889 (2016).
[Crossref]

Zhou, Y.

Zhu, C.

C. Do, A. V. Tran, C. Zhu, D. Hewitt, and E. Skafidas, “Data-aided OSNR estimation for QPSK and 16-QAM coherent optical system,” IEEE Photonics J. 5(5), 6601609 (2013).
[Crossref]

Zibar, D.

R. Borkowski, D. Zibar, A. Caballero, V. Arlunno, and I. T. Monroy, “Stokes space-based optical modulation format recognition in digital coherent receivers,” IEEE Photonics Technol. Lett. 25(21), 2129–2132 (2013).
[Crossref]

Ziyadi, M.

Found. Trends Mach. Learn. (1)

Y. Bengio, “Learning deep architectures for AI,” Found. Trends Mach. Learn. 2(1), 1–127 (2009).
[Crossref]

IEEE J. Opt. Commun. Netw. (1)

P. Isautier, K. Mehta, A. J. Stark, and S. E. Ralph, “Robust architecture for autonomous coherent optical receivers,” IEEE J. Opt. Commun. Netw. 7(9), 864–874 (2015).
[Crossref]

IEEE J. Sel. Top. Quantum Electron. (1)

S. J. Savory, “Digital coherent optical receivers: algorithms and subsystems,” IEEE J. Sel. Top. Quantum Electron. 16(5), 1164–1178 (2010).
[Crossref]

IEEE Photonics J. (3)

M. S. Faruk, Y. Mori, and K. Kikuchi, “In-band estimation of optical signal-to-noise ratio from equalized signals in digital coherent receivers,” IEEE Photonics J. 6(1), 7800109 (2014).
[Crossref]

C. Do, A. V. Tran, C. Zhu, D. Hewitt, and E. Skafidas, “Data-aided OSNR estimation for QPSK and 16-QAM coherent optical system,” IEEE Photonics J. 5(5), 6601609 (2013).
[Crossref]

F. N. Khan, A. P. T. Lau, T. B. Anderson, J. C. Li, C. Lu, and P. K. A. Wai, “Simultaneous and independent OSNR and chromatic dispersion monitoring using empirical moments of asynchronously sampled signal amplitudes,” IEEE Photonics J. 4(5), 1340–1350 (2012).
[Crossref]

IEEE Photonics Technol. Lett. (4)

F. N. Khan, K. Zhong, W. H. Al-Arashi, C. Yu, C. Lu, and A. P. T. Lau, “Modulation format identification in coherent receivers using deep machine learning,” IEEE Photonics Technol. Lett. 28(17), 1886–1889 (2016).
[Crossref]

T. S. R. Shen, Q. Sui, and A. P. T. Lau, “OSNR monitoring for PM-QPSK systems with large inline chromatic dispersion using artificial neural network technique,” IEEE Photonics Technol. Lett. 26(13), 1291–1294 (2012).

R. Borkowski, D. Zibar, A. Caballero, V. Arlunno, and I. T. Monroy, “Stokes space-based optical modulation format recognition in digital coherent receivers,” IEEE Photonics Technol. Lett. 25(21), 2129–2132 (2013).
[Crossref]

R. Schmogrow, B. Nebendahl, M. Winter, A. Josten, D. Hillerkuss, S. Koenig, J. Meyer, M. Dreschmann, M. Huebner, C. Koos, J. Becker, W. Freude, and J. Leuthold, “Error vector magnitude as a performance measure for advanced modulation formats,” IEEE Photonics Technol. Lett. 24(1), 61–63 (2012).
[Crossref]

IEEE Trans. Pattern Anal. Mach. Intell. (1)

Y. Bengio, A. Courville, and P. Vincent, “Representation learning: a review and new perspectives,” IEEE Trans. Pattern Anal. Mach. Intell. 35(8), 1798–1828 (2013).
[Crossref] [PubMed]

IEEE/OSA J. Lightwave Technol. (1)

Z. Dong, F. N. Khan, Q. Sui, K. Zhong, C. Lu, and A. P. T. Lau, “Optical performance monitoring: a review of current and future technologies,” IEEE/OSA J. Lightwave Technol. 34(2), 525–543 (2016).
[Crossref]

IET Electron. Lett. (1)

F. N. Khan, C. Lu, and A. P. T. Lau, “Joint modulation format/bit-rate classification and signal-to-noise ratio estimation in multipath fading channels using deep machine learning,” IET Electron. Lett. 52(14), 1272–1274 (2016).
[Crossref]

Opt. Express (3)

Opt. Lett. (1)

Proc. IEEE (1)

I. Tomkos, S. Azodolmolky, J. Sole-Pareta, D. Careglio, and E. Palkopoulou, “A tutorial on the flexible optical networking paradigm: state of the art, trends, and research challenges,” Proc. IEEE 102(9), 1317–1337 (2014).
[Crossref]

Other (10)

S. Oda, J. Y. Yang, Y. Akasaka, K. Sone, Y. Aoki, M. Sekiya, and J. C. Rasmussen, “In-band OSNR monitor using an optical bandpass filter and optical power measurements for superchannel signals,” in Proc. European Conference and Exhibition on Optical Communication (ECOC, 2013), paper P.3.12.
[Crossref]

N. G. Gonzalez, D. Zibar, and I. T. Monroy, “Cognitive digital receiver for burst mode phase modulated radio over fiber links,” in Proc. European Conference and Exhibition on Optical Communication (ECOC, 2010), paper P6.11.
[Crossref]

A. S. Ahsan, M. S. Wang, M. R. Chitgarha, D. C. Kilper, A. E. Willner, and K. Bergman, “Autonomous OSNR monitoring and cross-Layer control in a mixed bit-rate and modulation format system using pilot tones,” in Proc. Advanced Photon. Comm. (APC, 2014), paper NT4C.3.

L. Lundberg, H. Sunnerud, and P. Johannisson, “In-band OSNR monitoring of PM-QPSK using the Stokes parameters,” in Proc. Optical Fiber Comm. Conf. (OFC, 2015), paper W4D. 5.
[Crossref]

F. N. Khan, Z. Dong, C. Lu, and A. P. T. Lau, “Optical performance monitoring for fiber-optic communication networks,” in Enabling Technologies for High Spectral-Efficiency Coherent Optical Communication Networks, X. Zhou and C. Xie, eds. (Wiley, 2016), Chap. 14.

C. K. Chan, Optical Performance Monitoring (Academic, 2010).

C. Lu, A. P. T. Lau, F. N. Khan, Q. Sui, J. Zhao, Z. Li, H.-Y. Tam, and P. K. A. Wai, “Optical performance monitoring techniques for high capacity optical networks,” in Proc. International Symposium on Communication Systems, Networks and Digital Signal Processing (CSNDSP, 2010), pp. 678−681.

A. Ardakani, F. L. -Primeau, N. Onizawa, T. Hanyu, and W. J. Gross, “VLSI implementation of deep neural network using integral stochastic computing,” IEEE Transactions on very large scale integration (VLSI) systems (to be published).

F. O. -Zamorano, J. M. Jerez, I. Gómez, and L. Franco, “Deep neural network architecture implementation on FPGAs using a layer multiplexing scheme,” in Proc. International Conference on Distributed Computing and Artificial Intelligence (DCAI, 2016), pp. 79−86.

A. Ardakani, C. Condo, and W. J. Gross, “Sparsely-connected neural networks: towards efficient VLSI implementation of deep neural networks,” in Proc. International Conference on Learning Representations (ICLR, 2017).

Cited By

OSA participates in Crossref's Cited-By Linking service. Citing articles from OSA journals and other participating publishers are listed here.

Alert me when this article is cited.


Figures (6)

Fig. 1
Fig. 1 DSP configuraion used in the receiver with the proposed OSNR monitoring and MFI stage highlighted in red colour.
Fig. 2
Fig. 2 AHs for three different OSNRs for QPSK (first row), 16-QAM (second row), and 64-QAM (third row) signals after CMA equalization.
Fig. 3
Fig. 3 DNNs with bin-count vectors x as inputs and estimated modulation formats/OSNRs as outputs. During testing, a suitable DNN-OSNR is chosen based on identified modulation format for the given input vector x.
Fig. 4
Fig. 4 Experimental setup for joint OSNR monitroing and MFI in coherent receivers using DNNs.
Fig. 5
Fig. 5 Elements of output vectors v1 for (a) QPSK, (b) 16-QAM, and (c) 64-QAM modulation formats when 57 vectors x belonging to testing data set are applied at DNN-MFI’s input.
Fig. 6
Fig. 6 True versus estimated OSNRs for (a) QPSK, (b) 16-QAM, and (c) 64-QAM signals using the proposed technique.

Tables (1)

Tables Icon

Table 1 Identification accuracies for different modulation formats using the proposed technique.

Metrics