Traffic estimation based on long short-term memory neural network for mobile front-haul with XG-PON

A novel predictive dynamic bandwidth allocation(DBA) method based on the long short-term memory(LSTM)neural network is proposed for a 10-gigabit-capable passive optical network in mobile front-haul(MFH) links. By predicting the number of packets that arrive at the optical network unit buffer based on LSTM, the round-trip time delay in traditional DBAs can be eliminated to meet the strict latency requirement for MFH links. Our study shows that the LSTM neural network has better performance than feed-forward neural networks. Based on extensive simulations, the proposed scheme is found to be able to achieve the latency requirement for MFH and outperforms the traditional DBAs in terms of delay, jitter, and packet loss ratio.     

直接探测系统中两种单边带光信号调制与恢复方法的研究

从理论上阐释了基于独立双驱动马赫-曾德尔调制器(DDMZM)和同相正交调制器的两种单边带光信号调制原理。通过研究100 Gbit/s速率75 km标准单模光纤传输系统中的16-正交幅度调制单边带信号,分析了两种方法的参数调优原理。接收端使用Kramers-Kronig(KK)算法恢复单边带信号并消除信号与信号间的拍频串扰。结果表明,由于调制器的非线性以及单边带信号的载波信号功率比的影响,在误比特率为3.8×10~(-3)的7%硬判决前向纠错门限上,使用基于KK算法的接收机的虚载波方法与DDMZM方法相比,能够降低接收光功率约2.3 dB。     

Application of Kramers–Kronig receiver in SSB-OFDM-RoF link

We propose and investigate the use of a Kramers–Kronig(KK) receiver in a single sideband orthogonal frequency division multiplexing radio over fiber(SSB-OFDM-RoF) link based on an optical remote heterodyne solution. This scheme is effective in eliminating the signal-to-signal beating interference introduced by square-law detection of a photo-detector in an SSB-OFDM-RoF link. We extensively study the influences of different carrier-to-signal power ratios(CSPRs), laser linewidths, and transmission distances on our proposed scheme. It is proved that the KK-based receiver can reduce optimal CSPR by more than 5 dB and provide about 1.1 dB gain over the conventional mixer-based receiver scheme with CSPR of 11 dB after 75 km fiber transmission.