Robustness of AutoML for Time Series Forecasting in Sensor Networks
Tuomas Halvari, Jukka K. Nurminen, Tommi Mikkonen · 2021
Sensor data collection in IoT networks is sensitive to malfunction of sensors and communications. Hence, it is important that models using the data work in a reasonable way even when there are some, potentially temporary, problems. In this paper, we investigate the robustness of AutoML systems for time series forecasting in sensor networks, using temperature data as example. We experiment with different AutoML systems and study how the resulting models tolerate faults in their input data. The analyzed AutoML systems are Microsoft's Azure AutoML, Intel's Analytics Zoo AutoML, and Facebook's Prophet. As a result, we rank AutoML systems based on their performance with respect to data faults and their severity. In addition, we show how the AutoML generated models differ given the data fault type.