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

Abstract

Next-generation wireless ecosystems are expected to comprise heterogeneous technologies and diverse deployment scenarios. Ensuring quality of service (QoS) will be one of the major challenges on account of a variety of factors that are beyond the control of network and service providers in these environments. In this context, ITU-T is working on defining new Recommendations related to QoS and users' quality of experience (QoE) for the 5G era. Considering the new 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 (ML). The methodological approach is based on the use of supervised and unsupervised ML techniques in order to identify both the KQIs relevant for the users and the network performance (NP) anomalies. The proposed methodology links the NP and QoE via inductive ML algorithms and provides information about the areas where corrective actions are required. The results from a case study conducted to validate the model in real-world Wi-Fi deployment scenarios are also presented.