Anomaly detection on compressed data in resource-constrained smart water meters

Abstract

Increasing amount of devices in our daily life are equipped with sensors that transfer information to a cloud solution where the data is finally analysed. By improving the data intelligence on the edge, the data transfer can be reduced, which not only saves bandwidth and thus reduces energy consumption, but also leads to increased privacy protection. In this paper, we propose a privacy-friendly water leakage detection approach for various kind of water meters (optical and digital) performed on a very constrained, wireless devices.