Mechanisms for QoE optimisation of Video Traffic: A review paper

qadir, qahhar muhammad; Kist, Alexander A.; Zhang, Zhongwei

doi:10.17972/ajicta2015117

Cited by 11 publications

(5 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Numerous QoE studies have been conducted to investigate the impact of technical parameters of systems and networks on the experience of end users. The results of these studies can be considered by network operators for network management to avoid QoE degradation and improve the experience of end users with networked applications [11], [12].…”

Section: Background and Related Workmentioning

confidence: 99%

On Machine Learning Based Video QoE Estimation Across Different Networks

Oršolić

Seufert

2021

2021 16th International Conference on Telecommunications (ConTEL)

View full text Add to dashboard Cite

With Over-The-Top traffic being extensively encrypted end-to-end, network operators typically lack insight into the performance of these services, as perceived by the end users. Yet, such an insight is essential for employing QoE-aware network management and potential alleviation of problems that may originate in the network. There is a clear interest from network operators to find ways to estimate service performance in terms of Key Performance Indicators (KPIs) and Quality of Experience (QoE). Over the last years, machine-learning-based (ML) models have proven to be capable of inferring QoE/KPIs from patterns in encrypted network traffic. The particular focus has mostly been on adaptive video streaming services, considering their share of the global network traffic. Those ML-based models have typically been trained and tested on a single dataset collected under specific conditions only. Going beyond related work on the topic of QoE/KPI estimation, we collected two large datasets related to YouTube streaming using the same setup at two different locations in Europe and analyzed the extent to which the differences in network characteristics and location specifics influence the performance of such models. This is of interest, as applicability of the models across diverse networks would significantly reduce the needed extensiveness of data collection typically required for ML-based approaches. In this paper, we compare models trained and tested on a single dataset/location (network-specific), models trained on the merged dataset (general), and models trained on one dataset and tested on the other dataset (cross-tested). The results show that the performance of general models is comparable to that of networkspecific models, but cross-tests exhibit a considerable reduction in performance. With the aim to understand and improve crossnetwork applicability of the models in the future, the paper also provides an investigation of underlying reasons for the performance degradation.

show abstract

Section: Background and Related Workmentioning

confidence: 99%

On Machine Learning Based Video QoE Estimation Across Different Networks

Oršolić

Seufert

2021

2021 16th International Conference on Telecommunications (ConTEL)

View full text Add to dashboard Cite

show abstract

“…Different approaches for QoE-aware traffic management approaches in wireless networks were surveyed in [6]. In contrast, [7] only focused on mechanisms for improving the QoE of video streaming. Also [8] surveyed mechanisms for video streaming, but additionally differentiated between pure network traffic management solutions, and cross-layer and collaborative mechanisms.…”

Section: Quality-of-experience-aware Traffic Managementmentioning

confidence: 99%

Considering User Behavior in the Quality of Experience Cycle: Towards Proactive QoE-Aware Traffic Management

2019

View full text Add to dashboard Cite

The concept of Quality of Experience (QoE) of Internet services is widely recognized by service providers and network operators. They strive to deliver the best experience to their customers in order to increase revenues and avoid churn. Therefore, QoE is increasingly considered as an integral part of the reactive traffic management cycle of network operators. Additionally, QoE also constitutes a cycle of its own, which includes the user behavior and the service requirements. This work describes this QoE cycle, which is not widely taken into account yet, discusses the interactions of the two cycles, and derives implications towards an improved and proactive QoE-aware traffic management. A showcase on how network operators can obtain hints on the change of network requirements from detecting user behavior in encrypted video traffic is also presented in this paper.

show abstract

“…QoE monitoring Surveys [162][163][164][165][166][167] Monitoring in the network QoE estimation [168][169][170][171][172][173] QoE factor estimation [16,27,63,[174][175][176][177][178][179][180][181][182] Machine learning [183][184][185][186][187][188][189] Monitoring in the application QoE factors [176,[190][191][192][193][194][195][196] QoE models [132,148,[197][198][199] QoE-aware tra c management mechanisms Surveys [200,201] Network tra c management [202][203]…”

Section: Background and Related Workmentioning

confidence: 99%

“…The goals of QoE-aware tra c management are to e ciently utilize the available network resources and to improve the QoE of end users, which typically includes to establish QoE fairness [242] between di erent applications and users. Reference [200] surveyed various approaches to QoE-aware tra c management approaches in wireless networks, whereas [201] only focused on mechanisms for improving the QoE of video streaming. Selected tra c management approaches are presented in chronological order and separated into pure network tra c management solutions, and mechanisms, which use information from applications and/or signal applications to change their network demands.…”

Section: Qoe-aware Tra Ic Management Mechanisms For Video Streamingmentioning

confidence: 99%