NEC has announced it has applied AI to subsea cable networks to push the capacity limits of the transmission networks.
During joint research with Google, NEC applied AI and probabilistic shaping using 64 quadrature amplitude modulation (64QAM) to the FASTER subsea cable linking Taiwan, Japan and the US west coast.
The study demonstrated that the 11,000km FASTER cable can be upgraded to a spectral efficiency of 6 bits per second per hertz. This would represent a capacity of more than 26Tbps, over two and a half times the capacity originally planned for the cable.
According to NEC, the team used probabilistic shaping techniques that near the Shannon limit, the theoretical maximum transmission speed over a telecoms network before the signal is drowned out by noise, at a modulation of 64QAM.
For the first time on a live cable, AI was used to analyze data for the purposed of nonlinearity compensation (NLC). The trial used an NEC developed compensation algorithm based on deep neural networks to accurately estimate signal nonlinearity.
"Other approaches to NLC have attempted to solve the nonlinear Schrodinger equation, which requires the use of very complex algorithms," NEC GM of submarine networks Toru Kawauchi said.
“This approach sets aside those deterministic models of nonlinear propagation, in favor of a low-complexity black-box model of the fiber, generated by machine learning algorithms. The results demonstrate both an improvement in transmission performance and a reduction in implementation complexity.”