GPON PLOAMd Message Analysis Using Supervised Neural Networks

Abstract

This paper discusses the possibility of analyzing the orchestration protocol used in gigabit-capable passive optical networks (GPONs). Considering the fact that a GPON is defined by the International Telecommunication Union Telecommunication sector (ITU-T) as a set of recommendations, implementation across device vendors might exhibit few differences, which complicates analysis of such protocols. Therefore, machine learning techniques are used (e.g., neural networks) to evaluate differences in GPONs among various device vendors. As a result, this paper compares three neural network models based on different types of recurrent cells and discusses their suitability for such analysis.

Security Incident Response Automation for xPON Networks

“…The SIRAP defines five basic report types so far, but we are continuously working on its extension. These message definitions are definitions of problems (incidents) that the data analysis module can identify in the PON network based on PON frame analysis and machine learning, which is presented in [6], [27], [29]. The basic report types are: The report template can be easily extended because of the defined empty report, and new report types can be added.…”

A Novel Temporal Dynamic Wavelength Bandwidth Allocation Based on Long-Short-Term-Memory in NG-EPON

“…Notably, a number of cutting-edge studies employing ML/DL in DBA have been conducted (as shown in Table 1) [17], [18], [19], [20], [21], [22], [23], [24]. For example, [21], uses the k-Nearest Neighbors (k-NN) method to adaptively tune neighbors dynamically, which is essential in dynamic environments with frequent changes that affect accuracy.…”

“…Several recent studies have explored the use of machine learning techniques such as LSTM models to predict access network traffic, without implementing DBA or considering DiffServ [21], [22], [23], [24]. Another study proposed a DWBA algorithm for WDM/TDM-PONs that leverages neural networks to predict network traffic and reduce RTT delay, while improving bandwidth efficiency [20].…”