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

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/application as well as the data provider who might 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.