Low-Cost Traffic Sensing System Based on LoRaWAN for Urban Areas

TL;DR

This paper presents a low-cost, scalable traffic sensing system using LoRaWAN technology that estimates vehicle flow in urban areas by analyzing RSSI signals, achieving up to 96% accuracy.

Contribution

It introduces a novel method of using LoRaWAN RSSI data combined with machine learning to accurately estimate urban traffic flow, demonstrating practical deployment and high accuracy.

Findings

Achieved up to 96% correct traffic level detection.

Demonstrated feasibility of large-scale urban traffic monitoring with LoRaWAN.

Validated the system through real-world deployment over miles of urban roads.

Abstract

The advent of Low Power Wide Area Networks (LPWAN) has enabled the feasibility of wireless sensor networks for environmental traffic sensing across urban areas. In this study, we explore the usage of LoRaWAN end nodes as traffic sensing sensors to offer a practical traffic management solution. The monitored Received Signal Strength Indicator (RSSI) factor is reported and used in the gateways to assess the traffic of the environment. Our technique utilizes LoRaWAN as a long-range communication technology to provide a largescale system. In this work, we present a method of using LoRaWAN devices to estimate traffic flows. LoRaWAN end devices then transmit their packets to different gateways. Their RSSI will be affected by the number of cars present on the roadway. We used SVM and clustering methods to classify the approximate number of cars present. This paper details our experiences with the design and real implementation of this system across an area that stretches for miles in urban scenarios. We continuously measured and reported RSSI at different gateways for weeks. Results have shown that if a LoRaWAN end node is placed in an optimal position, up to 96% of correct environment traffic level detection can be obtained. Additionally, we share the l