Cross-Train: Machine Learning Assisted QoT-Estimation in Un-used Optical Networks

The quality of transmission (QoT) estimation of lightpaths (LPs) has both technological and economic significance from the operator’s perspective. Typically, the network administrator configures the network element (NE) working point according to the specified nominal values given by vendors. These operational NEs experienced some variation from the given nominal working point and thus put up uncertainty during their operation, resulting in the introduction of uncertainty in estimating LP QoT. Consequently, a substantial margin is required to avoid any network outage. In this context, to reduce the required margin provisioning, a machine learning (ML) based framework is proposed which is cross-trained using the information retrieved from the fully operational network and utilized to support the QoT estimation unit of an un-used sister network.