ANN-Based Optical Link Parameter Identification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In optical communications systems, accurately identifying the fiber types in links is challenging due to misidentification or unknown fiber types, leading to suboptimal launch power settings, reduced signal-to-noise ratio, and increased uncertainty in network planning, which complicates dispersion compensation and affects network capacity.
Innovation Solution
The use of trained artificial neural networks (ANNs) to analyze nonlinear noise and known link parameters, such as chromatic dispersion and launch power, to estimate fiber types, optical nonlinear coefficients, and other link parameters, enabling remote identification of fiber types and optimizing transmission settings.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional methods are used to identify fiber types in optical links, then direct physical access to all link spans is required, but this increases device complexity and reduces ease of operation
Solution Approach 1:
The patent uses trained artificial neural networks as intermediaries to identify fiber types. Instead of requiring direct physical access to fiber spans, the system processes received signal data through trained ANNs that have learned fiber type characteristics during training. The trained ANNs act as mediators between the received signals and the fiber type identification, eliminating the need for physical access while maintaining high identification accuracy.
2Measurement precision
If traditional methods are used to identify fiber types, then physical access to all link spans is required, but this reduces ease of operation
Solution Approach 1:
The system performs self-service by using the received signals themselves to identify fiber types. The trained ANNs process the signal data already present in the system to automatically determine fiber types without requiring external physical access or manual intervention. This self-service approach significantly improves operational convenience while maintaining identification accuracy.
3Productivity
If misidentification or unknown fiber types occur, then launch power settings become suboptimal, but adjusting launch power requires accurate fiber type knowledge
Solution Approach 1:
The system performs preliminary action by training multiple ANNs in advance, with each ANN specialized for identifying a specific fiber type. During operation, the system uses these pre-trained ANNs to quickly and accurately identify the fiber type, which then enables optimal launch power settings to be applied. This preliminary training phase ensures that when identification is needed, the system can rapidly determine fiber type and adjust parameters accordingly, maximizing network capacity.
Data Source
AI summary
Technology for link parameter identification in an optical communications network is described. A first trained artificial neural network (ANN) may be applied to first input values representative of nonlinear noise in a signal received at a receiver from a transmitter over a link in the optical communications system, thereby generating first output values. A second trained ANN may be applied to second input values comprising the first output values and one or more known parameters of the link, thereby generating second output values. One or more link parameter estimates may be identified based on the second output values. In some examples, the first trained ANN has an architecture specialized for two-dimensional image recognition and therefore suitable for the image-like properties of the first input values. For example, the first trained ANN may comprise a deep residual learning network (ResNet) or a Convolution Neural Network (CNN).