Applying cognitive dynamic learning strategies for margins reduction in operational optical networks

Today's optical transport networks are complex already and the support of the new arising services will further increase such complexity. Traditional deterministic network procedures will need to be revisited, especially their operations. Network Operators will require more dynamic approaches to get the best out of their infrastructure. In this context, cognition and machine learning techniques can provide innovative management solutions for traditional telecom operators. In this paper, we explore a dynamic cognitive approach to improve the adaption of Network Operators' operational processes to the new digital age. We propose a dynamic strategy considering the Case-Base Reasoning (CBR) technique for helping to reduce overall costs by optimizing operation margins. In this way, highly competitive exploitation methods to support new services can be deployed. The proposed dynamic algorithms can achieve higher transmitted power efficiency, up to 20% versus previously proposed static solutions, prolonging the transceivers' lifetime and thus addressing telco operator costs reduction.