Improving LoRaWAN Localization in Industrial Environments Using Merging Path-Loss Modeling with Extended Kalman Filtering and adopting Map-Matching

Abstract In industrial environments, accurate location information is crucial in enabling the seamless operation of technologies. Localization based on the signal features of the implemented network (such as RSSI) is becoming an appropriate substitute to solve its problems, such as low power consumption and cost. LoRaWAN, a contemporary LPWAN technology, can provide long-range coverage, an important requirement for several industrial application domains. RSSI-based localization in LoRaWAN is a widely used low-cost method, but it is susceptible to environmental changes and noise, leading to low performance and accuracy especially in industrial environments. So, applying an adoptable noise-filtering method based on the environment, to make measured RSSI usable in industrial applications such as asset management localization and tracking, is essential. This paper proposes a novel method that merges an Extended Kalman Filter (EKF) with Path-Loss modeling (PLM) for noise filtering in LoRaWAN system. Additionally, we incorporate map considerations to further improve the accuracy of location estimation. For the evaluation step, the proposed method is implemented and tested in a harbor in a highly dynamic and harsh industrial environment. The detailed evaluation demonstrates that the proposed approach leads to an improvement between 15% and 46% compared to normal PLM. In addition, adding map-matching leads to a 36% improvement in location estimation.