Branch Identification in Passive Optical Networks using Machine Learning

PON systems are primarily deployed in fiber-to-thehome (FTTH) networks to deliver a wide range of communication and multimedia services [1]. Due to the omission of active electronic components, OPEX is reduced, and this also makes them less failure-prone in the outside plant. Implementing and deploying effective monitoring schemes in these systems can result in significant additional OPEX savings. Optical time domain reflectometry (OTDR), a technique based on Rayleigh backscattering, has primarily been used to monitor individual optical fiber spans. However, applying OTDR to monitor PON systems can be challenging because the backscattered signals from each branch are added together, making it difficult to distinguish between the backward signals of the individual branches [2]. In the case of (almost) equidistant branch terminations, event analysis becomes most difficult as the reflected signals from the branches with the same length overlap and add up.