Multi-Span Optical Power Spectrum Evolution Modeling using ML-based Multi-Decoder Attention Framework
This work addresses the challenge of efficient optical network modeling for brown-field scenarios, though it appears incremental as it builds on existing ML and attention methods.
The paper tackled the problem of predicting optical power spectrum evolution in multi-span networks by implementing a machine learning-based attention framework with component-specific decoders, resulting in improved prediction accuracy and scalability with minimal data collection.
We implement a ML-based attention framework with component-specific decoders, improving optical power spectrum prediction in multi-span networks. By reducing the need for in-depth training on each component, the framework can be scaled to multi-span topologies with minimal data collection, making it suitable for brown-field scenarios.