Personalized Quality of Experience (QOE) Management using Data Driven Architecture in 5G Wireless Networks

Abstract

the aim of this paper is to Personalized Quality of Experience (QOE) Management using Data driven Architecture in 5G Wireless Networks that consume less resources. The proposed research will be the part of the overall research project, which focuses on addressing a problem that many organizations experience that introduce an Enterprise Architecture to support the integration of different services across the enterprise. With the rapid growth in mobile network usage and video streaming being the most popular service, Quality of Experience of video in mobile networks is of extreme importance to both service providers and their customers. The ability to effectively predict Quality of Experience of video is key for QoE adaptation and higher levels of customer satisfaction. In this work machine learning algorithms were used to create models that predict QoE with network QoS parameters, including wireless-specific and 5Gspecific parameters. An 5G simulation that reflects the current mobile traffic landscape was created to obtain the data set for training. An objective tool for video QoE evaluation was used to gather QoE data necessary to train the prediction models. Support Vector Machines, Random Forest, Gradient Boosted Trees and Neural Networks were chosen as the machine learning algorithms for Quality of Experience prediction, and it was shown that they achieve high accuracy. Influence of wireless-specific parameters on QoE prediction was also investigated, and it was discovered that they are suitable for use in Quality of Experience prediction models.The problem is that; organizations do not know where they either have or may encounter weaknesses in their Enterprise Architecture with Data Driven Architecture (DDA). The framework presented is based on concepts from Wireless Networks with Driven Architecture will be designed to support both Transitional Gap Analysis (TGA) and Comparative Gap Analysis (CGA). TGA is supported by comparing a baseline Data Driven Architecture (DDA) to a target QoE where both DDA have been defined from the management perspective. DDA is facilitated by mapping a QoE to two or more 5G networks. The research methodology used in the paper is design science research for the QoE management based 5G network. The QOE for implementation of 5th generation network and apply it in many different real-world organizations. The goal of the paper is to present a framework in the form an implementation and management model, called QOE, that visualizes the gaps (weaknesses) in proposed or existing enterprise architectures and to support a comparative analysis process for different a5Grnative solution approaches. a set of requirements on the QOE management can be presented and the frameworks are applied on Matlab for implementation.