Weather-Adaptive Multi-Step Forecasting of State of Polarization Changes in Aerial Fibers Using Wavelet Neural Networks
arXiv:2409.03663v11 citationsh-index: 17
Originality Incremental advance
AI Analysis
This addresses forecasting accuracy for aerial fiber communication systems, but it appears incremental as it builds on existing methods with weather data integration.
The paper tackled the problem of forecasting state of polarization changes in aerial fibers by introducing a weather-adaptive approach using wavelet neural networks, resulting in improvements of over 65% in RMSE and 63% in MAPE compared to baselines.
We introduce a novel weather-adaptive approach for multi-step forecasting of multi-scale SOP changes in aerial fiber links. By harnessing the discrete wavelet transform and incorporating weather data, our approach improves forecasting accuracy by over 65% in RMSE and 63% in MAPE compared to baselines.