Fog-based Data Fusion for Heterogeneous IoT Sensor Networks: A Real Implementation

Abstract

The Internet of Things (IoT) is an environment that can be divided in three large layers: the sensor/actuator level where a wide variety of objects with different computing, sensors and communication capabilities resides, the communication layer with wireless technologies such as ZigBee, Bluetooth and emerging 6LoWPAN (e.g LoRa), and the intelligence layer, where computing analytics/decisions occur. IoT can be used for monitoring, inferring problems, decision making at a business level or actuating at the edge via IoT nodes. As the IoT sensor network grows, an enormous amount of data from multiple sources flows to the intelligence layer. In order to make decisions based on analytics over these data, the measurements need to be precise and accurate. Data fusion is an effective way to improve data quality, however, IoT environments are still evolving and the best way and location where data fusion should happen is an open problem. This paper presents one potential strategy for IoT sensor data fusion by implementing multi-sensor data fusion as microservices using a container platform built into an opensource IoT middleware based in a fog computing infrastructure which is can scale automatically as the influx of data from the IoT nodes grows. A number of data fusion tests were performed for different amounts of IoT nodes and sensor readings over ZigBee and LoRa using a specific data fusion algorithm. The results show that, the strategy can be effectively used in IoT heterogeneous environments.