Virtual Sensor Creation to Replace Faulty Sensors Using Automated Machine Learning Techniques

by | Jun 4, 2020

(From the article abstract)
With the introduction of the Internet of Things (IoT) into every area of life, more and more applications are created that rely on information collected from IoT sensors. These applications are developed by third-party developers and depend on a continuous information flow, but do not operate the sensor network themselves. However, in case of sensor failures, the flow of information will be interrupted which will pose a problem for the user, applications that rely on the flow, as well as the data provider who may not be able to replace the sensor in time. Depending on the requirements of the application, estimators which are trained through machine learning algorithms, called Virtual Sensors, can ensure the uninterrupted operation of the application. However, for a solution that can be used in practice, the deployment of such a Virtual Sensor needs to be fast enough as well as fully automated, so that no human interaction and domain knowledge is required. This paper describes a framework that is capable of finding correlating IoT sensors in the surrounding environment, selecting a machine learning algorithm, and training a fitting model to run a Virtual Sensor.

While satellite or cellular positioning implies dedicated hardware or network infrastructure functions, indoor navigation or novel IoT positioning techniques include flexible storage and computation requirements that can be fulfilled by both end-devices or cloud backends. Hybrid positioning systems support the integration of several algorithms and technologies; however, the common trend of delegating position calculation and storage of local geoinformation to mobile devices or centralized servers causes performance degradation in terms of delay, battery usage and waste of network resources.

The strategy followed in this work is off-loading this computational effort onto the network edge, following a Mobile Edge Computing (MEC) approach. MEC nodes in the access network of the mobile device are in charge of receiving navigation data coming from both the smart infrastructure and mobile devices, in order to compute the final position following a hybrid approach. With the aim of supporting mobility and the access to multiple networks, an Information Centric Networking (ICN) solution is used to access generic position information resources.

The presented system currently supports WiFi, Bluetooth LE, GPS, cellular and NFC technologies, involving both indoor and outdoor positioning, using fingerprinting and proximity for indoor navigation, and the integration of smart infrastructure data sources such as the door opening system within real smart campus deployment.
Evaluations carried out reveal latency improvements of 50%, compared with a regular configuration where position fixes are computed by mobile devices; at the same time the MEC solution offers extra flexibility features to manage positioning databases, algorithms and move extensive computation from constrained devices to the edge.

Eushay Bin Ilyas, Marten Fischer, Thorben Iggena and Ralf Tönjes

University of Applied Science Osnabrück

WordPress Appliance - Powered by TurnKey Linux