Page 39: of Marine Technology Magazine (November 2024)

help optimize the available spectrum. sponders, and at least two different features have seen active

Finally, optical power planning is an ongoing aspect of ? ber development.

pair operation, and it’s essential that this is carefully designed in order to ensure stable service levels. Threat Monitoring and Proactive Protection

For several years, In? nera has been involved in the devel-

Enhanced Network Monitoring opment of techniques for seismic anomaly detection – basi-

Coherent transponders and, to a lesser extent, the transport cally using existing submarine cables to enhance tsunami platforms they are housed in offer a veritable ? re hydrant ? ow warning systems. Cable operators have shown interest in of telemetry, with the latest transponders having hundreds of this capability, but they have also thrown down the chal- information points in their published data models. Dealing lenge of enhancing sensitivity in order to detect threats with this ? ood of information over the data communication such as seabed trawling or dragging anchors in the vicinity network has always been a challenge, but this is exactly the of the cable.

kind of problem that AI can help with by extracting correla- tions and patterns that the human eye alone cannot recognize. Advanced Nonlinear Compensation

The limiting impairments for modern coherent transpon-

Predictive Maintenance ders are nonlinear effects caused by high optical power lev-

Hand in hand with enhanced monitoring is the ability to els in the ? ber. Using fully effective, algorithmic nonlinear use the processed telemetry from the transponder, transport compensation (NLC) techniques is extremely computation- platform, SLTE terminal, and repeater chain to detect po- ally intensive – well beyond the immediate roadmap for tential operational issues and to deal with them before they ASIC processing power. Limited NLC does deliver useful become a problem. additional performance, but one direction of research is looking at the use of a neural network approach for NLC

Network-based Use of AI that uses far less processing power yet delivers a signi? cant

Network-based features generally run in AI-enhanced tran- performance improvement.

FIGURE 3:

The operational and network-based impact of AI in SLTE technology www.marinetechnologynews.com 39

MTR #8 (34-47).indd 39 11/20/2024 10:41:03 AM