TY  - JOUR
ID  - SisLab3588
UR  - http://www.sciencepublishinggroup.com/journal/paperinfo?journalid=517&doi=10.11648/j.ijics.20190404.11
IS  - 4
A1  - Pham, Manh Linh
A1  - Nguyen, Truong Thang
A1  - Tran, Manh Dong
N2  - Cloud computing is an evolution in IT consumption and delivery which makes available self-management on the Internet with a flexible, pay-as-you-go business model. Within the context of Internet of Things, the MQTT (Message Queuing Telemetry Transport) protocol that is implemented broadly by the applications of ?Publish-Subscribe? paradigm has a vital role. However, MQTT brokers are saturated easily if they have to cope with huge and speedy data generated by IoT ?chatty? devices. With capability of provisioning/deprovisioning granular virtual resources, Cloud computing empowered MQTT brokers by enabling its elasticity feature. Elasticity helps the brokers deal with a very large variety of data integrated into the IoT every single day. However, there was lack of sturdy benchmarking tools that judge all the aspects of MQTT brokers in order to advocate correct elastic decision-making. This article focuses on the work of benchmarking MQTT by introducing a new developed tool called MQTTBrokerBench. With this tool, users not only can benchmark MQTT brokers but also can specify saturation points where the IoT load makes the brokers be saturated. Those saturation points can be used to set thresholds for elastic decision-making. Furthermore, the article also demonstrates the results acquired by this tool through the experiments on Windows Azure Cloud Platform.
VL  - 4
TI  - A Benchmarking Tool for Elastic MQTT Brokers in IoT Applications
AV  - public
EP  - 78
Y1  - 2019/12/01/
PB  - Science Publishing Group
JF  - International Journal of Information and Communication Sciences
KW  - Benchmarking
KW  -  MQTT
KW  -  Cloud Computing
KW  -  Internet of Things
SN  - 2575-1719
SP  - 70
ER  -