Localization in Low Power Wide Area Networks Using Wi-Fi Fingerprints

Abstract

Supply chain management requires regular updates of the location of assets, which can be enabled by low power wide area networks, such as Sigfox. While it is useful to localize a device simply by its communication signals, this is very difficult to do with Sigfox because of wide area and ultra narrowband nature. On the other hand, installing a satellite localization element on the device greatly increases its power consumption. We investigated using information about nearby Wi-Fi access points as a way to localize the asset over the Sigfox network, so without connecting to those Wi-Fi networks. This paper reports the location error that can be achieved by this type of outdoor localization. By using a combination of two databases, we could localize the device on all 36 test locations with a median location error of 39 m . This shows that the localization accuracy of this method is promising enough to warrant further study, most specifically the minimal power consumption.

Keywords

• localization
• Internet of Things
• low power wide area networks
• Wi-Fi
• Sigfox
• fingerprinting