Search

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. [ABSTRACT FROM AUTHOR]

Summary: The deployment of Internet of Things (IoT) solutions in smart cities or industrial environments (Industrial IoT, IIoT) demands careful consideration in terms of user‐centric or system‐centric target metrics. A better monitoring system able to transform performance outputs into decision‐making and intelligent actions requires less restrictive performance evaluation methods. Classic approaches to performance evaluation in telecommunication networks rely on Quality of Service (QoS) and/or Quality of user Experience (QoE) assessment models. However, the new IoT paradigm establishes a completely different scenario, where, for instance, consumers might no longer be users but machines. In this paper, we propose the evaluation of the performance of IoT services and applications comprising the combination of four quality measures, namely, Quality of Data (QoD), Quality of Information (QoI), Quality of user Experience (QoE), and Quality Cost (QC). The proposal is analyzed using computing simulations. Specifically, we improve the simulation tool FLoRa (Framework for LoRa) incorporating additional LoRa Wide Area Network (LoRaWAN) features. LoRaWAN is a Low‐Power Wide Area Network (LPWAN) technology that operates on the LoRa modulation scheme. Long coverage ranges, low power consumption, and support for a massive number of IoT devices using a limited infrastructure are the main assets of LoRaWAN, establishing it as one of the top IoT technologies. Results show that it is easier and more efficient to disassociate metrics into different dimensions in order to provide a clear vision of the performance of IoT services. This performance evaluation method can be customized and applied to different IoT markets. [ABSTRACT FROM AUTHOR]

New verticals within the Internet of Things (IoT) paradigm such as smart cities, smart farming, or goods monitoring, among many others, are demanding strong requirements to the Radio Access Network (RAN) in terms of coverage, end-node’s power consumption, and scalability. The technologies employed so far to provide IoT scenarios with connectivity, e.g., wireless sensor network and cellular technologies, are not able to simultaneously cope with these three requirements. Thus, a novel solution known as Low Power - Wide Area Network (LP-WAN) has emerged as a promising alternative to provide with low-cost and low-power-consumption connectivity to end-nodes spread in a wide area. Concretely, the Long-Range Wide Area Network (LoRaWAN) technology is one of the LP-WAN platforms that is receiving greater attention from both the industry and the academia. For that reason, in this work, a comprehensive performance evaluation of LoRaWAN under different environmental conditions is presented. The results are obtained from three real scenarios, namely, urban, suburban, and rural, considering both dynamic and static conditions, hence a discussion about the most proper LoRaWAN physical-layer configuration for each scenario is provided. Besides, a theoretical coverage study is also conducted by the use of a radio planning tool considering topographic maps and a precise propagation model. From the attained results, it can be concluded that it is necessary to evaluate the propagation conditions of the deployment scenario prior to the system implantation in order to reach a compromise between the robustness of the network and the transmission data-rate. [ABSTRACT FROM AUTHOR]