A CNN-LSTM Phase Compensation Method for Unidirectional Two-way Radio Frequency Transmission System
A convolutional neural network combined with long short-term memory (CNN-LSTM) phase compensation method (PCM) is proposed and demonstrated, where CNN is employed to extract spatial features, and LSTM is used to capture temporal features and realize the long-term predictions of residual phase fluctu...
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Photonics Journal |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10517367/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832590435686547456 |
|---|---|
| author | Jiahui Cheng Zhengkang Wang Yaojun Qiao Hao Gao Chenxia Liu Zhuoze Zhao Jie Zhang Baodong Zhao Bin Luo Song Yu |
| author_facet | Jiahui Cheng Zhengkang Wang Yaojun Qiao Hao Gao Chenxia Liu Zhuoze Zhao Jie Zhang Baodong Zhao Bin Luo Song Yu |
| author_sort | Jiahui Cheng |
| collection | DOAJ |
| description | A convolutional neural network combined with long short-term memory (CNN-LSTM) phase compensation method (PCM) is proposed and demonstrated, where CNN is employed to extract spatial features, and LSTM is used to capture temporal features and realize the long-term predictions of residual phase fluctuations. This is the first-time machine learning (ML) has been used to mitigate the effects of optical path asymmetry caused by temperature variations on radio frequency (RF) transmission systems. The performance is verified by experiments on a unidirectional two-way RF transmission system, in which both the two 259-km-long separate fibers are coupled into one optical cable. The results demonstrate the CNN-LSTM model presents better prediction performance than the other eight previously proposed ML models. When the prediction duration is 40,000 s and the ambient temperature variation range is 14.38 °C, the coefficient of determination (R Squared, R2) between the predicted value and the actual value is higher than 0.99. In addition, compared to the phase locked loop (PLL) PCM, the proposed CNN-LSTM PCM can reduce the root-mean-square (RMS) phase jitter of the received signal from 219 ps to 19.72 ps, and improve the frequency stability of the system at 10,000 s by 84.5%. Overall, the proposed CNN-LSTM PCM can effectively compensate for residual phase fluctuations generated by the optical path asymmetry, providing a potential option for achieving stable RF transmission in telecommunication networks. |
| format | Article |
| id | doaj-art-eebe60e7972645978c0c078f15ba0e71 |
| institution | Kabale University |
| issn | 1943-0655 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Photonics Journal |
| spelling | doaj-art-eebe60e7972645978c0c078f15ba0e712025-01-24T00:00:32ZengIEEEIEEE Photonics Journal1943-06552024-01-011631810.1109/JPHOT.2024.339583410517367A CNN-LSTM Phase Compensation Method for Unidirectional Two-way Radio Frequency Transmission SystemJiahui Cheng0https://orcid.org/0000-0001-8801-3399Zhengkang Wang1https://orcid.org/0000-0002-1021-6513Yaojun Qiao2https://orcid.org/0000-0001-7253-9839Hao Gao3https://orcid.org/0000-0002-9304-6854Chenxia Liu4https://orcid.org/0000-0002-2631-322XZhuoze Zhao5https://orcid.org/0000-0003-3839-7157Jie Zhang6https://orcid.org/0009-0002-2212-0399Baodong Zhao7https://orcid.org/0009-0001-3798-6358Bin Luo8https://orcid.org/0000-0001-9231-0273Song Yu9https://orcid.org/0000-0003-1489-9021State Key Laboratory of Information Photonics and Optical Communications, Beijing University of Posts and Telecommunications, Beijing, ChinaLaboratory of Space-Ground Interconnection and Convergence, School of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing, ChinaState Key Laboratory of Information Photonics and Optical Communications, Beijing University of Posts and Telecommunications, Beijing, ChinaState Key Laboratory of Information Photonics and Optical Communications, Beijing University of Posts and Telecommunications, Beijing, ChinaDepartment of Electronic and Communication Engineering, North China Electric Power University, Baoding, ChinaState Key Laboratory of Information Photonics and Optical Communications, Beijing University of Posts and Telecommunications, Beijing, ChinaState Key Laboratory of Information Photonics and Optical Communications, Beijing University of Posts and Telecommunications, Beijing, ChinaState Key Laboratory of Information Photonics and Optical Communications, Beijing University of Posts and Telecommunications, Beijing, ChinaState Key Laboratory of Information Photonics and Optical Communications, Beijing University of Posts and Telecommunications, Beijing, ChinaState Key Laboratory of Information Photonics and Optical Communications, Beijing University of Posts and Telecommunications, Beijing, ChinaA convolutional neural network combined with long short-term memory (CNN-LSTM) phase compensation method (PCM) is proposed and demonstrated, where CNN is employed to extract spatial features, and LSTM is used to capture temporal features and realize the long-term predictions of residual phase fluctuations. This is the first-time machine learning (ML) has been used to mitigate the effects of optical path asymmetry caused by temperature variations on radio frequency (RF) transmission systems. The performance is verified by experiments on a unidirectional two-way RF transmission system, in which both the two 259-km-long separate fibers are coupled into one optical cable. The results demonstrate the CNN-LSTM model presents better prediction performance than the other eight previously proposed ML models. When the prediction duration is 40,000 s and the ambient temperature variation range is 14.38 °C, the coefficient of determination (R Squared, R2) between the predicted value and the actual value is higher than 0.99. In addition, compared to the phase locked loop (PLL) PCM, the proposed CNN-LSTM PCM can reduce the root-mean-square (RMS) phase jitter of the received signal from 219 ps to 19.72 ps, and improve the frequency stability of the system at 10,000 s by 84.5%. Overall, the proposed CNN-LSTM PCM can effectively compensate for residual phase fluctuations generated by the optical path asymmetry, providing a potential option for achieving stable RF transmission in telecommunication networks.https://ieeexplore.ieee.org/document/10517367/Convolutional neural networkfrequency transmissionlong short-term memory networkunidirectional two-wayfrequency stability |
| spellingShingle | Jiahui Cheng Zhengkang Wang Yaojun Qiao Hao Gao Chenxia Liu Zhuoze Zhao Jie Zhang Baodong Zhao Bin Luo Song Yu A CNN-LSTM Phase Compensation Method for Unidirectional Two-way Radio Frequency Transmission System IEEE Photonics Journal Convolutional neural network frequency transmission long short-term memory network unidirectional two-way frequency stability |
| title | A CNN-LSTM Phase Compensation Method for Unidirectional Two-way Radio Frequency Transmission System |
| title_full | A CNN-LSTM Phase Compensation Method for Unidirectional Two-way Radio Frequency Transmission System |
| title_fullStr | A CNN-LSTM Phase Compensation Method for Unidirectional Two-way Radio Frequency Transmission System |
| title_full_unstemmed | A CNN-LSTM Phase Compensation Method for Unidirectional Two-way Radio Frequency Transmission System |
| title_short | A CNN-LSTM Phase Compensation Method for Unidirectional Two-way Radio Frequency Transmission System |
| title_sort | cnn lstm phase compensation method for unidirectional two way radio frequency transmission system |
| topic | Convolutional neural network frequency transmission long short-term memory network unidirectional two-way frequency stability |
| url | https://ieeexplore.ieee.org/document/10517367/ |
| work_keys_str_mv | AT jiahuicheng acnnlstmphasecompensationmethodforunidirectionaltwowayradiofrequencytransmissionsystem AT zhengkangwang acnnlstmphasecompensationmethodforunidirectionaltwowayradiofrequencytransmissionsystem AT yaojunqiao acnnlstmphasecompensationmethodforunidirectionaltwowayradiofrequencytransmissionsystem AT haogao acnnlstmphasecompensationmethodforunidirectionaltwowayradiofrequencytransmissionsystem AT chenxialiu acnnlstmphasecompensationmethodforunidirectionaltwowayradiofrequencytransmissionsystem AT zhuozezhao acnnlstmphasecompensationmethodforunidirectionaltwowayradiofrequencytransmissionsystem AT jiezhang acnnlstmphasecompensationmethodforunidirectionaltwowayradiofrequencytransmissionsystem AT baodongzhao acnnlstmphasecompensationmethodforunidirectionaltwowayradiofrequencytransmissionsystem AT binluo acnnlstmphasecompensationmethodforunidirectionaltwowayradiofrequencytransmissionsystem AT songyu acnnlstmphasecompensationmethodforunidirectionaltwowayradiofrequencytransmissionsystem AT jiahuicheng cnnlstmphasecompensationmethodforunidirectionaltwowayradiofrequencytransmissionsystem AT zhengkangwang cnnlstmphasecompensationmethodforunidirectionaltwowayradiofrequencytransmissionsystem AT yaojunqiao cnnlstmphasecompensationmethodforunidirectionaltwowayradiofrequencytransmissionsystem AT haogao cnnlstmphasecompensationmethodforunidirectionaltwowayradiofrequencytransmissionsystem AT chenxialiu cnnlstmphasecompensationmethodforunidirectionaltwowayradiofrequencytransmissionsystem AT zhuozezhao cnnlstmphasecompensationmethodforunidirectionaltwowayradiofrequencytransmissionsystem AT jiezhang cnnlstmphasecompensationmethodforunidirectionaltwowayradiofrequencytransmissionsystem AT baodongzhao cnnlstmphasecompensationmethodforunidirectionaltwowayradiofrequencytransmissionsystem AT binluo cnnlstmphasecompensationmethodforunidirectionaltwowayradiofrequencytransmissionsystem AT songyu cnnlstmphasecompensationmethodforunidirectionaltwowayradiofrequencytransmissionsystem |