Deep Learning-Based Dynamic Bandwidth Allocation for Future Optical Access Networks

John Abied Hatem,Ahmad R Dhaini,Shady Elbassuoni

doi:10.1109/access.2019.2929480

Abstract

Over the last decade, Passive Optical Networks (PONs) have emerged as an ideal candidate for next-generation broadband access networks. Meanwhile, machine learning and more specifically deep learning has been regarded as a star technology for solving complex classification and prediction problems. Recent advances in hardware and cloud technologies offer all the necessary capabilities for employing deep learning to enhance Next-Generation Ethernet PON’s (NG-EPON) performance. In NG-EPON systems, control messages are exchanged in every cycle between the optical line terminal and optical network units to enable dynamic bandwidth allocation (DBA) in the upstream direction. In this paper, we propose a novel DBA approach that employs deep learning to predict the bandwidth demand of end-users so that the control overhead due to the request-grant mechanism in NG-EPON is reduced, thereby increasing the bandwidth utilization. The extensive simulations highlight the merits of the new DBA approach and offer insights for this new line of research.

Highlights

According to Cisco’s Visual Networking Index forecast, the global Internet traffic, which amounted to approximately 27 Tbps in year 2016, will reach a whopping 106 Tbps by year 2021 [1]
RELATED WORK we review the state-of-the-art works that employ machine learning to enhance the operation and performance of bandwidth allocation in Passive Optical Networks (PONs)
The authors of [14] proposed a machine learning based dynamic bandwidth allocation (DBA) (MLP-DBA), where an artificial neural network (ANN) model is deployed at the Optical Line Terminal (OLT) to identify the On and Off periods of bursty Internet traffic for the polling cycle of every Optical Network Units (ONUs)

Summary

INTRODUCTION

According to Cisco’s Visual Networking Index forecast, the global Internet traffic, which amounted to approximately 27 Tbps in year 2016, will reach a whopping 106 Tbps by year 2021 [1]. Ensuring fairness among ONUs and supporting QoS is not attainable as the OLT would lack a holistic view of all the ONU demands This problem is resolved using offline schedulers, where the OLT waits until all the REPORT messages are received, and preforms DBA and schedules grants . This enables the OLT to support QoS and enables fairness among ONUs, at the expense of decreased channel utilization due to the control overhead between transmission cycles [18], [19].

RELATED WORK

PERFORMANCE EVALUATION

SETTING P-TO-Q

Findings

CONCLUSION