NEC has said the spectral efficiency across the FASTER subsea cable system can be upgraded to 6 bits per second per hertz for a capacity of more than 26 terabits per second (Tbps) -- over two and a half times the capacity originally planned at no additional wet plant capex.
In joint research with Google, NEC said the tests made use of artificial intelligence (AI) and probabilistic shaping at a 64 Quadrature Amplitude Moderation (64 QAM) modulation.
"For the first time on a live cable, artificial intelligence was used to analyse data for the purpose of nonlinearity compensation (NLC). NEC developed an NLC algorithm based on data-driven deep neural networks to accurately and efficiently estimate the signal nonlinearity," NEC said.
"In doing so, the authors set a spectral efficiency-distance product record of 66,102b/s/Hz in a field trial performed together with live traffic neighbouring channels."
According to NEC's Submarine Network Division GM Toru Kawauchi, this approach utilises machine learning algorithms that can be used on any subsea cable system.
"The results demonstrate both an improvement in transmission performance and a reduction in implementation complexity," Kawauchi explained.
NEC said it would continue its AI-based research after achieving a capacity increase of around 15Gbps in every 100GHz of fibre bandwidth.
The 10,000km FASTER subsea cable system will also connect the west coast of the United States with Asia, landing in Japan and consisting of six fibre pairs and making use of 10Gbps wave technology.
The announcement followed NEC last year demonstrating speeds of 50.9Tbps[1] across subsea cables of up to 11,000km on a single optical fibre through the use of C+L-band erbium-doped optical fibre amplifiers, amounting to speeds of 570 petabits per second-kilometre.