Accuracy vs. Cost Trade-off for Machine Learning Based QoE Estimation in 5G Networks

Abstract

Since their first release, 5G systems have been enhanced with Network Data Analytics Functionalities (NWDAF) as well as with the ability to interact with 3rd parties' Application Functions (AFs). Such capabilities enable a variety of potentials, unimaginable for earlier generation networks, notable examples being 5G built-in Machine Learning (ML) mechanisms for QoE estimation, subject of this paper. In this work, an ML-based mechanism for video streaming QoE estimation in 5G networks is presented and evaluated. The mechanism relies on an ML algorithm embedded in NWDAF, the collection of 5G network KPIs, and the collection of QoE information from video streaming service provider, i.e., the 3rd party AF. The mechanism has been evaluated in terms of QoE estimation accuracy against the cost in terms of required input sources and data for the estimation, and its performance has been compared to alternative methodologies not making use of ML. The evaluation, via simulation activity, clearly highlights the benefits of the proposed mechanism. Based on the derived results, the required input sources are ranked with respect to their importance.

ML-Based QoE Estimation in 5G Networks Using Different Regression Techniques

“…The number of zero weights can be tuned by the regularization parameter λ, which controls the strength of shrinkage and sparsity. By doing so, LASSO does not only help to reduce over-fitting, but can also be used for feature selection, as done in our previous work [5]. This can also help to make the model less complex and thus easier to understand by humans.…”

“…Thereby, the authors distinguish moving and static users and find that predictions are harder to perform for those users, who are moving during streaming. The movement of users for estimating the QoE is also addressed in our previous work [5], which shows that the relevance of features differs for moving and static user equipments (UEs). For moving ones, features expressing variability gain importance and as obtaining those features requires to monitor the network with finer granularity, the costs for QoE estimation could increase with user movement.…”

Керування Телекомунікаційними Мережами З Використанням Технологій Ai/Ml

“…Виявлення мережних аномалій є яскравим прикладом, у якому застосовуються методи ML для їхньої здатності автоматично навчатися з даних і «витягувати» шаблони, які можна використовувати для своєчасної ідентифікації мережних аномалій [11]. Для цього застосовуються підходи часової кореляції [12], вейвлет-аналізу [13] та традиційного виявлення точки зміни [14] для створення моделей нормального/зловмисного трафіку, де послідовність дій у часовому вікні використовується для створення профілів за допомогою таких методів кластеризації, як самоорганізовувальні карти [15], K-середні [16] і моделі змішування Гауса [17]. Крім того, методи AI/ML були застосовані для виявлення мережних вторгнень, охоплюючи, але не обмежуючись цим, дерева рішень, еволюційні обчислення, байєсовські мережі, опорні векторні машини та віднедавна глибоке навчання та навчання з підкріпленням [18].…”

Measuring, Modeling and Integrating Time-Varying Video Quality in End-to-End Multimedia Service Delivery: A Review and Open Challenges

“…Future research in the direction of ultra compressed data representation formats can decrease the volume of control data [241], [256]. The QoE monitoring frequency depends on the time interval of optimization, accuracy/data requirements of optimization algorithm(s), and time-period for the optimization [257]. For example, if the optimization is being performed at O-RAN near-real-time RIC then extremely low latency is required which needs secure fast information retrieval as compared to the optimization being performed at O-RAN non-real-time RIC [258], [259].…”