Cognitive algorithm using fuzzy reasoning for software-defined optical network

摘要

We propose a cognitive algorithm based on Fuzzy C-Means (FCM) technique for the learning and decision-making functionalities of software-defined optical networks (SDONs). SDON is a new optical network paradigm where the control plane is decoupled from the data plane, thus providing a degree of software programmability to the network. Our proposal is to add the FCM algorithm to the SDON control plane in order to achieve a better network performance, when compared with a non-cognitive control plane. In this context, we illustrate the use of the FCM algorithm for determining, in real time and autonomously, the modulation format of high-speed flexible rate transponders in accordance with the quality of transmission of optical channels. The performance of this FCM algorithm is evaluated via computational simulations for a long-haul network and compared to the case-based reasoning (CBR) algorithm, which is commonly used in optical cognitive networks. We demonstrate that FCM outperforms CBR in both fastness and error avoidance, achieving 100 % of successful classifications, being two orders of magnitude faster. Additionally, we propose a definition of cognitive optical networking and an architecture for the SDON control plane including the FCM engine.