Faulty branch identification in passive optical networks using machine learning

Abstract

Passive optical networks (PONs) have become a promising broadband access network solution thanks to their wide bandwidth, low-cost deployment and maintenance, and scalability. To ensure a reliable transmission, and to meet service level agreements, PON systems have to be monitored constantly in order to quickly identify and localize network faults and thus reduce maintenance costs, minimize downtime, and enhance quality of service. Typically, a service disruption in a PON system is mainly due to fiber cuts and optical network unit (ONU) transmitter/receiver failures. When the ONUs are located at different distances from the optical line terminal, the faulty ONU or branch can be identified by analyzing the recorded optical time domain reflectometry (OTDR) traces. OTDR is a technique commonly used for monitoring of fiber optic links. However, faulty branch isolation becomes very challenging when the reflections originate from two or more branches with similar length overlap, which makes it very hard to discriminate the faulty branches given the global backscattered signal. Recently, machine learning (ML)-based approaches have shown great potential for managing optical faults in PON systems. Such techniques perform well when trained and tested with data derived from the same PON system. But their performance may severely degrade if the PON system (adopted for the generation of the training data) has changed, e.g., by adding more branches or varying the length difference between two neighboring branches, etc. A re-training of the ML models has to be conducted for each network change, which can be time consuming. In this paper, to overcome the aforementioned issues, we propose a generic ML approach trained independently of the network architecture for identifying the faulty branch in PON systems given OTDR signals for the cases of branches with close lengths. Such an approach can be applied to an arbitrary PON system without requiring to be re-trained for each change of the network. The proposed approach is validated using experimental data derived from the PON system.

Key Technologies for a Beyond-100G Next-Generation Passive Optical Network

“…Application, network, and element hierarchies can be managed based on abstraction and management domains. Currently, artificial intelligence (AI) and ML [152][153][154][155][156][157][158][159][160][161][162] are showing great capabilities in solving tasks in optical network fault management, resource allocation, and optical path quality of transmission (QoT) estimation. However, the focus of the research community has been on the predictive power of ML models, neglecting aspects related to model understanding, that is, explaining how to make predictions.…”

Key Technologies for Beyond 100G Next Generation Passive Optical Network

“…Business, network, and element hierarchies can be managed based on abstraction and management domains. Currently, artificial intelligence (AI) and ML [148][149][150][151][152][153][154][155][156][157][158] are showing great capabilities in solving tasks in optical network fault management, resource allocation, and quality of transmission optical path (QoT) estimation. However, the focus of the research community has been on the predictive power of ML models, neglecting aspects related to model understanding.…”

Technical–economic analysis to identify the acceptable maximum attenuation on PON FTTH lines for wholesale network operators

“…The parameters that are returned to the retail operator include the operational status of the ONT, the attenuation, the date/time of the last connection, etc. 32 .…”