A novel system to control and forecast QoX performance in IoT‐based monitoring platforms

Abstract

Abstract Communication architectures based on the Internet of Things (IoT) are increasingly frequent. Commonly, these solutions are used to carry out control and monitoring activities. It is easy to find cases for manufacturing, prediction maintenance, Smart Cities, etc., where sensors are deployed to capture data that is sent to the cloud through edge devices or gateways. Then that data is processed to provide useful information and perform additional actions if required. As crucial as deploying these monitoring solutions is to verify their operation. In this article, we propose a novel warning method to monitor the performance of IoT‐based systems. The proposal is based on a holistic quality model called Quality of X (QoX). QoX refers to the use of a variety of metrics to measure system performance at different quality dimensions. These quality dimensions are data (Quality of Data, QoD), information (Quality of Information, QoI), users' experience (Quality of user Experience, QoE), and cost (Quality Cost, QC). In addition to showing the IoT system performance in terms of QoX in real‐time, our proposal includes (i) a forecasting model for independent estimation of QoX applying Deep Learning (DL), specifically using a Long Short‐Term Memory (LSTM) and time series, and (ii) the warning system. In light of our results, our proposal shows a better capacity to forecast quality drops in the IoT‐based monitoring system than other solutions from the related literature.

Keywords

• artificial intelligence
• deep learning
• internet of things
• performance evaluation
• quality of service