QoE-Driven Big Data Architecture for Smart City

Abstract

In the era of big data, the applications/services of the smart city are expected to offer end users better QoE than in a conventional smart city. Nevertheless, various types of sensors will produce an increasing volume of big data along with the implementation of a smart city, where we face redundant and diverse data. Therefore, providing satisfactory QoE will become the major challenge in the big-data-based smart city. In this article, to enhance the QoE, we propose a novel big data architecture consisting of three planes: the data storage plane, the data processing plane, and the data application plane. The data storage plane stores a wide variety of data collected by sensors and originating from different data sources. Then the data processing plane filters, analyzes, and processes the ocean of data to make decisions autonomously for extracting high-quality information. Finally, the application plane initiates the execution of the events corresponding to the decisions delivered from the data processing plane. Under this architecture, we particularly use machine learning techniques, trying to acquire accurate data and deliver precise information to end users. Simulation results indicate that our proposals could achieve high QoE performance for the smart city.