LinUCB–SF: A Lightweight Linear Upper Confidence Bandit for Device-Side Spreading Factor Selection in LoRaWAN

LoRaWAN has become a leading Low Power Wide Area Network (LPWAN) technology for Industrial Internet of Things (IIoT) applications, offering long range communication with low energy consumption. A fundamental challenge lies in selecting the appropriate Spreading Factor (SF) for each device, since this directly influences coverage, packet success ratio (PSR), and airtime. The default Adaptive Data Rate (ADR) mechanism is static and fails to adapt under dynamic network conditions such as mobility. This paper proposes a lightweight linear upper confidence bandit (LinUCB–SF) based reinforcement learning approach for adaptive SF selection. Each end device uses locally observable features to autonomously select its SF, balancing exploration and exploitation. The method is implemented and validated in ns-3 simulations across a range of deployment densities. Results show that our proposed LinUCB-SF algorithm reduces energy consumption by 19.3% in mobile scenarios and 37.8% in static scenarios, while improving PSR by 9.1% and 9.0%, respectively, compared to the EXP3 baseline.