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 distorti...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 hybrid neural 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.展开更多
基金Supported by the National Natural Science Foundation of China under Grant No 60502001.
文摘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 hybrid neural 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.
