A dataset for RSSI based outdoor localization using LoRaWAN in a harbor as a harsh and industrial environment

Enabling precise device localization is a critical requirement for the future of industry. Leveraging signal features for location determination has emerged as a leading approach and good alternative for Global Navigation Satellite Systems (GNSS) because of their limitations (low accuracy for indoor environments, expensive chips, and high energy consumption). On this basis, to provide localization for IoT in an industry with a harsh environment, the adopted wireless networks should have a long range coverage area. LoRaWAN is one of the most common communication networks that can provide large coverage with low power consumption and low implementation cost. Between various signal features that can be used for localization, Received Signal Strength (RSS) received more attention because of their low-cost deployment. But, RSS is highly dependent and sensitive to environmental changes, such as temperature, humidity, and background noise. This sensitivity becomes more intensive in an industrial environment with a harsh and dynamic environment. In order to evaluate the environmental effects on RSS in the harsh and highly dynamic industry, we present a comprehensive repository of LoRaWAN Received Signal Strength Indicator (RSSI) measurements, collected in a harbor as a testbed featuring three LoRaWAN gateways and one mobile end node. During the data collecting process, the mobile device obtains its location via a GPS and transmits it as the LoRaWAN message. In addition, to provide more insight of the effect of dynamic environment on the RSSI, two end nodes are implemented in fixed locations. These end nodes transmit messages with fixed time intervals including their unique id. The collected dataset includes RSSI and SNR measurements recorded by multiple gateways for each transmitted packet by fixed or mobile end nodes, and timestamp. This dataset enables the development and evaluation of RSSI-based localization and allows researchers to explore the challenges and opportunities associated with localization in dynamic IoT deployments.