QoE Enhancement in Next Generation Wireless Ecosystems: A Machine Learning Approach

A Centralized Win‐Win Cooperative Framework for Wi‐Fi and 5G Radio Access Networks

“…Other solutions can be found that try to solve these problems of access node allocation inefficiency through enhanced coexistence of Wi-Fi and cellular mobile networks [1,12,[17][18][19][20][21]. Specifically, in [1], the authors studied the 3 Wireless Communications and Mobile Computing coexistence of LTE-U and Wi-Fi networks in a multichannel unlicensed spectrum scenario and proposed an algorithm based on Q-learning.…”

“…In [17,18], the authors propose strategies for mobile networks and Wi-Fi in heterogeneous networks to maximize the throughput. Other papers also address Quality of Service (QoS) requirements in terms of data bit rates of wireless users and Quality of Experience (QoE) defined through users surveys' results such as the works proposed in [19,20], respectively. Finally, in [21], the authors presented 5G-EmPOWER, a novel, programmable, and open-source Software-Defined Networking (SDN) platform for heterogeneous 5G RANs, guaranteeing simultaneous management of Wi-Fi and cellular networks.…”

“…However, all these solutions still do not take into consideration a number of aspects that can further improve the performance of the users' connections. For instance, although all these papers advocate coexistence between cellular networks and Wi-Fi, they either do not aim to enhance Wi-Fi network performance and focus on 5G UEs' benefit only, such as [12,18,21], or focus only on LTE and Wi-Fi networks without considering 5G technologies, such as [1,17,19,20]. Additionally, a key limitation of all the solutions illustrated in this section is that they try to optimize objective key metrics in each access node, such as throughput, packet losses, and delay without taking into account the actual ongoing applications experienced by the wireless users.…”

Paving the Way for Distributed Artificial Intelligence over the Air

“…On the other hand, based on existing artificial intelligence (AI) architectures, protecting digital privacy is, to some extent, contradictory to the demand of user data by intelligent communication services [2]. This is because user data are required to be collected, processed, and utilized to precisely identify user demands so that truly intelligent and high-quality communication services can be provided to end users [3]. These user data inevitably contain personal and sensitive information that users are not willing to share and should be restricted by legislation [4].…”

Contribución al desarrollo de técnicas avanzadas para la evaluación de prestaciones en la Internet de las Cosas

“…Estas anomalías son el origen de caídas de rendimiento en cualquier dispositivo o red.De forma similar, López-Martin et al[137] aplican un modelo de DL basado en CNN y RNN para predecir valores actuales y futuros de QoE en series temporales. También con foco en la QoE, Ibarrola et al[138] hacen hincapié en la correcta selección de los KPIs más relevantes para estimar correctamente el valor de QoE en un escenario WiFi mediante algoritmos de ML supervisados y no supervisados. Li et al[89] proponen un modelo en un escenario IoT que utiliza regresión multilinear para estimar valores de QoE y Asma Ben Letaifa[123] proponen un método para estimar el valor de QoE basado en la escala MOS pero limitado a escenarios web.En comparación con estos trabajos previos, nuestra contribución en este sentido será la incorporación de un sistema que permita el análisis predictivo de todas las componentes de calidad del modelo de evaluación de prestaciones para los servicios sobre IoT descrito en el capítulo 3.Partimos de los datos generados mediante simulación para demostrar la validez del modelo holístico para medir el nivel de rendimiento en un entorno IoT.…”