Compensation for Radio-over-Fibre Uplink Based on Hybrid Neural Networks |
| |
Authors: | WANG Jian-Ping ZHOU Xian-Wei SONG Ya-Li GUO Wen-Zhe |
| |
Institution: | Department of Communication Engineering, School of Information Engineering, University of Science and Technology Beijing, Beijing 100083 |
| |
Abstract: | The radio-over-fibre (ROF) uplink, which combines the merit of optical fibre with that of microwave technology, can supply the high capacity of communication. However, there are two major issues: nonlinear distortion of the optical link and the multipath dispersion of the wireless channel, affecting the performance of the system. We propose an equalizer based on hybridneural networks. The compensation needs no estimation of the channel. The simulated result shows that the ROF uplink can be adequately compensated and the performance of the equalizer depends on the channel noise. |
| |
Keywords: | 42 25 Bs 42 15 Eq |
本文献已被 维普 等数据库收录! |
| 点击此处可从《中国物理快报》浏览原始摘要信息 |
| 点击此处可从《中国物理快报》下载免费的PDF全文 |
|