Page 164 - Proceedings of the 2018 ITU Kaleidoscope

1
Session 1: Machine Learning in Telecommunication Networks - I
Invited Paper - A Machine Learning Management Model for QoE Enhancement in Next
S1.1
Generation Wireless Ecosystems
Eva Ibarrola (University of the Basque Country (UPV/EHU), Spain); Mark Davis (Dublin
Institute of Technology (DIT), Ireland); Camille Voisin and Ciara Close (OptiWi-fi, Ireland);
Leire Cristobo (University of the Basque Country (UPV/EHU), Spain)

Next-generation wireless ecosystems are expected to comprise heterogeneous technologies and
diverse deployment scenarios. Ensuring a good quality of service (QoS) will be one of the major
challenges of next-generation wireless systems on account of a variety of factors that are beyond
the control of network and service providers. In this context, ITU-T is working on updating the
various Recommendations related to QoS and users' quality of experience (QoE). Considering
the ITU-T QoS framework, we propose a methodology to develop a global QoS management
model for next-generation wireless ecosystems taking advantage of big data and machine
learning. The results from a case study conducted to validate the model in real-world Wi-Fi
deployment scenarios are also presented.

S1.2 Unsupervised Learning for Detection of Leakage from the HFC Network

Emilia Gibellini and Claudio E. Righetti (Telecom Argentina, Argentina)

In the context of proactive maintenance of the HFC networks, cable operators count on Full-
Band Capture (FBC) to analyze the downstream spectrum and look for impairments. There exists
one particular type of impairment, which is ingress, likely to happen along with leakage.
Therefore, the detection of the former leads to the identification of the latter. We collect data

from FBC tool, and use unsupervised machine learning to group cable modems such that the
signal they receive show common patterns. This allows a characterization of all cable modems
in a service group. Then, we use the modems' locations to determine whether the root cause of
the flaw is inside the homes or not.
Double Sarsa Based Machine Learning to Improve Quality of Video Streaming over HTTP
S1.3 Through Wireless Networks
Dhananjay Kumar and Narmathaa Logganathan (Anna University, India); Ved P. Kafle
(National Institute of Information and Communications Technology, Japan)

The adaptive streaming over HTTP is widely advocated to enhance the Quality of Experience
(QoE) in a bitrate constrained IP network. However, most previous approaches based on
estimation of available link bandwidth or fullness of media buffer tend to become ineffective due
to the variability of IP traffic patterns. In this paper, we propose a Double State-Action-Reward-
State-Action (Sarsa) based machine learning method to improve user QoE in IP network. The Pv
video quality estimation model specified in ITU-T P.1203.1 recommendation is embedded in the

learning process for the estimation of QoE. We have implemented the proposed Double Sarsa
based adaptation method on the top of HTTP in a 4G wireless network and assessed the resulting
quality improvement by using full reference video quality metrics. The results show that the
proposed method outperforms an existing approach and can be recommended in standardization
of future audio-visual streaming services over wireless IP network. We observed the average
improvement of 7% in PSNR and 25% in VQM during the live streaming of video.

1 Papers marked with an “*” were nominated for the three best paper awards.

– 148 –