Optimizing LoRaWAN Performance Through Learning Automata-Based Channel Selection

The rising demand for long-range, low-power wireless communication in applications such as monitoring, smart metering, and wide-area sensor networks have emphasized the critical need for efficient spectrum utilization in LoRaWAN (Long Range Wide Area Network). In response to this challenge, this paper proposes a novel channel selection framework based on Hierarchical Discrete Pursuit Learning Automata (HDPA), aimed at enhancing the adaptability and reliability of LoRaWAN operations in dynamic and interference-prone environments. The HDPA framework capitalizes on the adaptive decision-making capabilities of Learning Automata (LA) to monitor and predict channel conditions in real time, enabling intelligent and sequential channel selection that maximizes transmission performance while reducing packet loss and co-channel interference. By integrating a hierarchical structure and discrete pursuit learning strategy, the proposed model achieves improved learning speed and accuracy in identifying optimal transmission channels from diverse frequency options. The methodology includes a detailed theoretical formulation of the HDPA algorithm and extensive simulations to evaluate its performance. Results demonstrate that HDPA outperforms Hierarchical Continuous Pursuit Automata (HCPA), particularly in convergence speed and selection accuracy.