5g kablosuz ağlarda veri dayalı mimari kullanarak kişiselleştirilmiş deneyim kalitesi (QOE) yönetimi

The objectives of this research is to use Data Driven Architecture to manage personalised Quality of Experience (QOE) in 5G Wireless Networks that use less energy. The present project will be a component of a larger current research. that reflects on an issue that several companies face while implementing an Enterprise Architecture to facilitate the analysis of heterogeneous resources all across enterprises. With the exponential increase of digital data use and video conferencing as the most common network, both telecommunications companies and their customers place a premium on available bandwidth in phone carriers. For QoE adaptation and higher levels of customer, the ability to actually assess visual Quality of Experience is critical. Machine learning were used to build simulations QoE regarding the network Qos, both connectivity and fifth - generation (5) variables, in this study. To find the information set to train, a 5G model that represents the current traffic information environment was developed. To collect the QoE information required to practice the predictions, an unbiased method for image QoE evaluation was being used. For Performance of Encounter estimation, Svms, Random Forest, Boosted Regression Trees, and Neural Network nn were selected as machine learning methods. and it has been shown that they have a high level of accuracy. Wifi parameters were also examined for their effect on QoE forecasting, and it has been found that they are ideal for use in Quality of Encounter predictions. The issue is that with Scientifically Based Architectures, enterprises do not realize and they have or will find vulnerabilities in their Enterprise - wide (DDA). The responsibilities related will be structured to support both Transitional Gap Analysis (TGA) and Comparable Impact Assessment (CGA) and is based on principles from Wireless Devices with Driven Architectures (CGA). TGA is assisted by a comparison of a base Computationally Efficient Infrastructure (DDA) to a desired Quality of Experience (QoE), in which both DDA have been identified from a strategic point of view. The routing of a QoE to two or more 53 g facilitates DDA. The dissertation' theoretical framework is systematic review study for a 54 g with QoE administration. The QOE for 5G sensor network and application in a range of sample organisations. The thesis's purpose is to explain a structure, called QOE, in the form of a planning and development template that visualises vulnerabilities (weak spots) in suggested or current business processes and supports a quantitative statistical process with different a5Grnative roundupa collection of specifications for QOE maintenance can be provided, and the structures can be implemented using Matlab