Interworking Layer of Distributed MQTT Brokers

Ryohei BANNO  Jingyu SUN  Susumu TAKEUCHI  Kazuyuki SHUDO  
[Paper on system development]

IEICE TRANSACTIONS on Information and Systems   Vol.E102-D   No.12   pp.2281-2294
Publication Date: 2019/12/01
Publicized: 2019/07/30
Online ISSN: 1745-1361
DOI: 10.1587/transinf.2019PAK0001
Type of Manuscript: Special Section PAPER (Special Section on Parallel and Distributed Computing and Networking)
Category: Information Network
MQTT,  publish/subscribe,  distributed systems,  IoT,  edge computing,  

Full Text: PDF>>
Buy this Article

MQTT is one of the promising protocols for various data exchange in IoT environments. Typically, those environments have a characteristic called “edge-heavy”, which means that things at the network edge generate a massive volume of data with high locality. For handling such edge-heavy data, an architecture of placing multiple MQTT brokers at the network edges and making them cooperate with each other is quite effective. It can provide higher throughput and lower latency, as well as reducing consumption of cloud resources. However, under this kind of architecture, heterogeneity could be a vital issue. Namely, an appropriate product of MQTT broker could vary according to the different environment of each network edge, even though different products are hard to cooperate due to the MQTT specification providing no interoperability between brokers. In this paper, we propose Interworking Layer of Distributed MQTT brokers (ILDM), which enables arbitrary kinds of MQTT brokers to cooperate with each other. ILDM, designed as a generic mechanism independent of any specific cooperation algorithm, provides APIs to facilitate development of a variety of algorithms. By using the APIs, we also present two basic cooperation algorithms. To evaluate the usefulness of ILDM, we introduce a benchmark system which can be used for both a single broker and multiple brokers. Experimental results show that the throughput of five brokers running together by ILDM is improved 4.3 times at maximum than that of a single broker.