Economia de Energia através da Configuração Inteligente de Parâmetros de Camada Física em Redes LoRa
Abstract
LoRa (Long Range) technology is characterized by long-distance communications and strong resilience to interference. In LoRa, the modulation is adjusted to allow higher data transmission rates due to the reception sensitivity threshold and communication distance. The spreading factor and transmission power, in turn, are directly related to energy consumption, influencing network performance. This paper proposes the use of supervised learning techniques for simultaneous selection of the spreading factor and transmission power. This approach differs from the literature as it configures two parameters in a supervised way instead of just one, the scattering factor. Through simulations of a LoRa network, different learning techniques are evaluated. Simulations compare the performance of the proposal with the traditional LoRaWAN protocol and the state-of-the-art in the intelligent selection of the spreading factor. The results reveal that the proposal can predict transmission success and adjust the referred parameters to reduce energy consumption without reducing the throughput and packet delivery rate.
References
Bor, M. C., Roedig, U., Voigt, T., and Alonso, J. M. (2016b). Do lora low-power widearea networks scale? In MSWiM ’16: Proceedings of the 19th ACM International Conference on Modeling, Analysis and Simulation of Wireless and Mobile Systems, New York, NY, United States. Association for Computing Machinery.
Cuomo, F., Campo, M., Caponi, A., Bianchi, G., Rossini, G., and Pisani, P. (2017). Explora: Extending the performance of lora by suitable spreading factor allocations. In IEEE 13th International Conference on Wireless and Mobile Computing, Networking and Communications (WiMob), Rome, Italy. IEEE.
Georgiou, O. and Raza, U. (2017). Low power wide area network analysis: Can lora scale? IEEE Wireless Communications Letters, 6(2):162–165.
Park, G., Lee, W., and Joe, I. (2020). Network resource optimization with reinforcement learning for low power wide area networks. EURASIP Journal onWireless Communications and Networking, 2020(176).
Raza, U., Kulkarni, P., and Sooriyabandara, M. (2017). Low power wide area networks: an overview. IEEE Communications Surveys & Tutorials, 19(2):855–873.
Ross, S. (1996). Stochastic processes. Wiley, New York, NY.
Semtech Corp. (2015). Lora modulation basics an1200.22. Disponível em: https://www.frugalprototype.com/wp-content/uploads/2016/08/an1200.22.pdf. Acessado em janeiro de 2022.
Ta, D.-T., Khawam, K., Lahoud, S., Adjih, C., and Martin, S. (2019). Lora-mab: A flexible simulator for decentralized learning resource allocation in iot networks. In 12th IFIP Wireless and Mobile Networking Conference (WMNC), Paris, France. IEEE.
Tijms, H. C. (2003). A first course in stochastic models. Wiley, New York, NY.
Yatagan, T. and Oktug, S. (2019). Smart spreading factor assignment for lorawans. In IEEE Symposium on Computers and Communications (ISCC), Barcelona, Spain. IEEE.
