Centralized and Distributed Machine Learning-Based QoT Estimation for Sliceable Optical Networks
This work addresses efficient control for 5G optical network slicing, but it appears incremental as it compares existing ML frameworks without introducing a new method.
The paper tackled the problem of estimating Quality-of-Transmission (QoT) for dynamic network slicing in 5G optical networks using machine learning, comparing centralized and distributed frameworks; it found that distributed models outperformed centralized ones in accuracy and training time, especially with more diverse QoT requirements.
Dynamic network slicing has emerged as a promising and fundamental framework for meeting 5G's diverse use cases. As machine learning (ML) is expected to play a pivotal role in the efficient control and management of these networks, in this work we examine the ML-based Quality-of-Transmission (QoT) estimation problem under the dynamic network slicing context, where each slice has to meet a different QoT requirement. We examine ML-based QoT frameworks with the aim of finding QoT model/s that are fine-tuned according to the diverse QoT requirements. Centralized and distributed frameworks are examined and compared according to their accuracy and training time. We show that the distributed QoT models outperform the centralized QoT model, especially as the number of diverse QoT requirements increases.