-
Categories
-
Pharmaceutical Intermediates
-
Active Pharmaceutical Ingredients
-
Food Additives
- Industrial Coatings
- Agrochemicals
- Dyes and Pigments
- Surfactant
- Flavors and Fragrances
- Chemical Reagents
- Catalyst and Auxiliary
- Natural Products
- Inorganic Chemistry
-
Organic Chemistry
-
Biochemical Engineering
- Analytical Chemistry
-
Cosmetic Ingredient
- Water Treatment Chemical
-
Pharmaceutical Intermediates
Promotion
ECHEMI Mall
Wholesale
Weekly Price
Exhibition
News
-
Trade Service
Recently, NEC Japan has completed transmission tests
of commercial submarine cables through the use of AI technology (artificial intelligence) and probability molding.
The tests were carried out on more than 10,000 kilometers of submarine
cables.
NEC uses AI technology to complete transmission tests of submarine cables
A study published by NEC in collaboration with Google is the first to demonstrate that the FASTER open submarine cable can be upgraded to a spectral efficiency
of 6b/s/Hz over a length of 11,000 kilometers.
NEC explained that this means that the capacity of the C band exceeds 26Tb/s, more than 2.
5 times the original planned capacity of the submarine cable, and there is no additional capital expenditure
.
When modulating 64 quadrature amplitude modulation, the team achieved this result using approximate Shannon probability shaping and, for the first time, used AI technology on field cables to analyze nonlinear compensation data
.
"Other methods for implementing nonlinear compensation attempt to solve the nonlinear Schrödinger equation, which requires the use of very complex algorithms
.
" Toru Kawauchi, general manager of NEC's submarine network division, said, "This approach sets aside deterministic models that are non-linear propagation to support low-complexity fiber black-box models
generated by machine learning algorithms.
The results show that the transmission performance is improved and the complexity is reduced
.
”
In addition, since the black-box model is constructed of transmitting data in real time, there is no need to know the cable parameters
in advance.
This allows the model to be used on any cable without prior modeling or characterization
.
This shows the potential application of AI technology in opening submarine cable systems so that end equipment
from multiple suppliers can be easily installed.
，
Recently, NEC Japan has completed transmission tests
of commercial submarine cables through the use of AI technology (artificial intelligence) and probability molding.
The tests were carried out on more than 10,000 kilometers of submarine
cables.
NEC uses AI technology to complete transmission tests of submarine cables
NEC uses AI technology to complete transmission tests of submarine cablesA study published by NEC in collaboration with Google is the first to demonstrate that the FASTER open submarine cable can be upgraded to a spectral efficiency
of 6b/s/Hz over a length of 11,000 kilometers.
NEC explained that this means that the capacity of the C band exceeds 26Tb/s, more than 2.
5 times the original planned capacity of the submarine cable, and there is no additional capital expenditure
.
When modulating 64 quadrature amplitude modulation, the team achieved this result using approximate Shannon probability shaping and, for the first time, used AI technology on field cables to analyze nonlinear compensation data
.
"Other methods for implementing nonlinear compensation attempt to solve the nonlinear Schrödinger equation, which requires the use of very complex algorithms
.
" Toru Kawauchi, general manager of NEC's submarine network division, said, "This approach sets aside deterministic models that are non-linear propagation to support low-complexity fiber black-box models
generated by machine learning algorithms.
The results show that the transmission performance is improved and the complexity is reduced
.
”
In addition, since the black-box model is constructed of transmitting data in real time, there is no need to know the cable parameters
in advance.
This allows the model to be used on any cable without prior modeling or characterization
.
This shows the potential application of AI technology in opening submarine cable systems so that end equipment
from multiple suppliers can be easily installed.
，
