Two-Lane DNN Equalizer Using Balanced Random-Oversampling for W-Band PS-16QAM RoF Delivery over 4.6 km
For W-band long-range mm-wave wireless transmission systems, nonlinearity issues resulting from photoelectric devices, optical fibers, and wireless power amplifiers can be handled by deep learning equalization algorithms. In addition, the PS technique is considered an effective measure to further in...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-05-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/10/4618 |
| _version_ | 1797598412772737024 |
|---|---|
| author | Sicong Xu Bohan Sang Lingchuan Zeng Li Zhao |
| author_facet | Sicong Xu Bohan Sang Lingchuan Zeng Li Zhao |
| author_sort | Sicong Xu |
| collection | DOAJ |
| description | For W-band long-range mm-wave wireless transmission systems, nonlinearity issues resulting from photoelectric devices, optical fibers, and wireless power amplifiers can be handled by deep learning equalization algorithms. In addition, the PS technique is considered an effective measure to further increase the capacity of the modulation-constraint channel. However, since the probabilistic distribution of m-QAM varies with the amplitude, there have been difficulties in learning valuable information from the minority class. This limits the benefit of nonlinear equalization. To overcome the imbalanced machine learning problem, we propose a novel two-lane DNN (TLD) equalizer using the random oversampling (ROS) technique in this paper. The combination of PS at the transmitter and ROS at the receiver improved the overall performance of the W-band wireless transmission system, and our 4.6-km ROF delivery experiment verified its effectiveness for the W-band mm-wave PS-16QAM system. Based on our proposed equalization scheme, we achieved single-channel 10-Gbaud W-band PS-16QAM wireless transmission over a 100 m optical fiber link and a 4.6 km wireless air-free distance. The results show that compared with the typical TLD without ROS, the TLD-ROS can improve the receiver‘s sensitivity by 1 dB. Furthermore, a reduction of 45.6% in complexity was achieved, and we were able to reduce training samples by 15.5%. Considering the actual wireless physical layer and its requirements, there is much to be gained from the joint use of deep learning and balanced data pre-processing techniques. |
| first_indexed | 2024-03-11T03:21:50Z |
| format | Article |
| id | doaj.art-dca26c0e1cad4e3981ff66c026604717 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-11T03:21:50Z |
| publishDate | 2023-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-dca26c0e1cad4e3981ff66c0266047172023-11-18T03:09:58ZengMDPI AGSensors1424-82202023-05-012310461810.3390/s23104618Two-Lane DNN Equalizer Using Balanced Random-Oversampling for W-Band PS-16QAM RoF Delivery over 4.6 kmSicong Xu0Bohan Sang1Lingchuan Zeng2Li Zhao3Shanghai Institute for Advanced Communication and Data Science, Key Laboratory for Information Science of Electromagnetic Waves (MoE), Fudan University, Shanghai 200433, ChinaShanghai Institute for Advanced Communication and Data Science, Key Laboratory for Information Science of Electromagnetic Waves (MoE), Fudan University, Shanghai 200433, ChinaAerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, ChinaShanghai Institute for Advanced Communication and Data Science, Key Laboratory for Information Science of Electromagnetic Waves (MoE), Fudan University, Shanghai 200433, ChinaFor W-band long-range mm-wave wireless transmission systems, nonlinearity issues resulting from photoelectric devices, optical fibers, and wireless power amplifiers can be handled by deep learning equalization algorithms. In addition, the PS technique is considered an effective measure to further increase the capacity of the modulation-constraint channel. However, since the probabilistic distribution of m-QAM varies with the amplitude, there have been difficulties in learning valuable information from the minority class. This limits the benefit of nonlinear equalization. To overcome the imbalanced machine learning problem, we propose a novel two-lane DNN (TLD) equalizer using the random oversampling (ROS) technique in this paper. The combination of PS at the transmitter and ROS at the receiver improved the overall performance of the W-band wireless transmission system, and our 4.6-km ROF delivery experiment verified its effectiveness for the W-band mm-wave PS-16QAM system. Based on our proposed equalization scheme, we achieved single-channel 10-Gbaud W-band PS-16QAM wireless transmission over a 100 m optical fiber link and a 4.6 km wireless air-free distance. The results show that compared with the typical TLD without ROS, the TLD-ROS can improve the receiver‘s sensitivity by 1 dB. Furthermore, a reduction of 45.6% in complexity was achieved, and we were able to reduce training samples by 15.5%. Considering the actual wireless physical layer and its requirements, there is much to be gained from the joint use of deep learning and balanced data pre-processing techniques.https://www.mdpi.com/1424-8220/23/10/4618deep neural networkphotonic-aided mm-wave systemcoherent detection DSP |
| spellingShingle | Sicong Xu Bohan Sang Lingchuan Zeng Li Zhao Two-Lane DNN Equalizer Using Balanced Random-Oversampling for W-Band PS-16QAM RoF Delivery over 4.6 km Sensors deep neural network photonic-aided mm-wave system coherent detection DSP |
| title | Two-Lane DNN Equalizer Using Balanced Random-Oversampling for W-Band PS-16QAM RoF Delivery over 4.6 km |
| title_full | Two-Lane DNN Equalizer Using Balanced Random-Oversampling for W-Band PS-16QAM RoF Delivery over 4.6 km |
| title_fullStr | Two-Lane DNN Equalizer Using Balanced Random-Oversampling for W-Band PS-16QAM RoF Delivery over 4.6 km |
| title_full_unstemmed | Two-Lane DNN Equalizer Using Balanced Random-Oversampling for W-Band PS-16QAM RoF Delivery over 4.6 km |
| title_short | Two-Lane DNN Equalizer Using Balanced Random-Oversampling for W-Band PS-16QAM RoF Delivery over 4.6 km |
| title_sort | two lane dnn equalizer using balanced random oversampling for w band ps 16qam rof delivery over 4 6 km |
| topic | deep neural network photonic-aided mm-wave system coherent detection DSP |
| url | https://www.mdpi.com/1424-8220/23/10/4618 |
| work_keys_str_mv | AT sicongxu twolanednnequalizerusingbalancedrandomoversamplingforwbandps16qamrofdeliveryover46km AT bohansang twolanednnequalizerusingbalancedrandomoversamplingforwbandps16qamrofdeliveryover46km AT lingchuanzeng twolanednnequalizerusingbalancedrandomoversamplingforwbandps16qamrofdeliveryover46km AT lizhao twolanednnequalizerusingbalancedrandomoversamplingforwbandps16qamrofdeliveryover46km |