Validating SAREF in a Smart Home Environment

Abstract

SAREF is an ontology created to enable interoperability between smart devices. While the IoT community has shown interest and understanding of SAREF as a means for interoperability, there is a lack in the literature of practical examples to implement SAREF in real applications. In order to validate the practical implementation of SAREF we perform two experiments. First we map IoT data available in a smart home into RDF using SAREF. In the second part of the paper an IoT environment is created by using the Knowledge Engine, a framework created to allow communication between smart devices, operating on Raspberry Pi’s emulating IoT devices, where the communication of the IoT devices is performed by sharing knowledge represented with SAREF. These experiments demonstrate that SAREF is an ontology that is successfully applicable in different situations, with data-mapping showing that SAREF is able to represent the information of different smart devices and by using the Knowledge Engine showing that SAREF can enable interoperability between smart devices.

Using Knowledge Graphs for Machine Learning in Smart Home Forecasters

“…To create an initial dataset of RDF data, a mapping for the output of nine different smart devices was created by hand [18]. These mappings were created in collaboration with domain experts knowledgeable about the devices and experts knowledgeable about the SAREF ontology.…”

“…To answer RQ1 an experiment with SAREF in a practical setting was created that used the Knowledge Engine [18]. The Knowledge Engine is a custom built interoperability framework, built by a partner from the Interconnect project, that allows multiple smart devices to communicate using RDF data.…”

“…After this first year of research the first research question has been partially answered by the two implementations of SAREF described in [18], showing how an ontology can be used to create a knowledge graph of IoT data. But more research will have to determine whether a knowledge graph can hold all the information required for the prediction algorithms that will be used for the other research questions.…”

“…GNN models will be implemented to create predictions based on the data in the IoT data knowledge graph. The resulting forecaster will be tested in a practical setting, as an extended version of the experiment performed in [18], to research the tradeoff between computational resources and accuracy. This forecasting system will initially be a specific forecaster focusing only on temperature.…”

“…The two implementations described in Sect. 6 and [18] describe how the data from a smart home can be mapped to a knowledge graph, showing that an ontology is capable of mapping relevant data available in a smart home, sufficiently to accomplish a scenario using multiple devices. To provide a more robust answer it will be tested thoroughly in combination with the prediction algorithms used in the other RQs.…”