We found a match
Your institution may have rights to this item. Sign in to continue.
- Title
Low-power Mesh Network Based on Message Queue Telemetry Transport Broker for Industrial IoT with Long Short-term Memory Forecasting.
- Authors
Chi-Chia Sun; Dang Quang Vu Hoang
- Abstract
The Industrial Internet of Things (IIoT) connects devices with the ability to monitor sensor data and exchange it through the internet. The necessities of reliability and high-quality data mean that data monitoring must be able to meet the requirements of the IIoT industrial standards as soon as possible. Recently, researchers have created more capable communication protocols for IIoT devices, each with their own advantages. These protocols include Extensible Messaging and Presence Protocol (XMPP), Message Queue Telemetry Transport (MQTT), and Advanced Message Queuing Protocol (AMQP), of which the MQTT protocol is the most widely used. We propose the use of an MQTT broker as a communication protocol; MQTT has shown its abilities in data communication protocols for IIoT. We used temperature and humidity sensors, vibration sensors, and current and voltage sensors because the digital and analog parameters often serve as parameters of IIoT conditions. We also used wireless mesh networks (WMNs) to deliver data from the source to the destination efficiently. A long short-term memory (LSTM) framework was applied for the energy consumed by communication in mesh networks to forecast time series and save energy. Experimental results show that power consumption is reduced by 16.66 to 50% at different nodes. LSTM forecasting results show that the mean squared error (MSE) is less than 0.07%, ensuring the quality and reliability of the transmission of data using MQTT protocol and power saving in mesh networks.
- Subjects
MESH networks; TELEMETRY; TELECOMMUNICATION systems; DATA transmission systems; WIRELESS mesh networks; INTERNET of things
- Publication
Sensors & Materials, 2022, Vol 34, Issue 4 Part 1, p1297
- ISSN
0914-4935
- Publication type
Article
- DOI
10.18494/SAM3505