Proposta de Controle de Espalhamento Espectral Utilizando Aprendizado por Reforço Profundo para Otimização do Desempenho de Redes LoRa/LoRaWAN
Resumo
O número de dispositivos de Internet das Coisas (IoT) conectados cresce cada vez mais e tende a aumentar nos próximos anos, principalmente com a chegada das redes 5G. Isso resultará em um intenso tráfego de dados no sistema de comunicação, podendo prejudicar a qualidade de transmissão devido aos congestionamentos e perdas de pacote por colisão. O objetivo desse artigo e propor um método inteligente baseado em redes Deep Q Networks (DQN), onde o agente é treinado para aprender uma política de ações envolvendo parâmetros de modulação do protocolo LoRa, de forma que a conexão multiusuário seja otimizada. A metodologia de desenvolvimento desse artigo é por meio de simulações computacionais. Os resultados apontam para uma técnica de otimização e controle promissora.Referências
Al-Fuqaha, A., Guizani, M., Mohammadi, M., Aledhari, M., and Ayyash, M. (2015). Internet of things: A survey on enabling technologies, protocols, and applications. IEEE Communications Surveys Tutorials, 17(4):2347–2376.
Augustin, A., Clausen, T., J.Yi, and Townsley, W. (2016). A study of lora: Long range low power networks for the internet of things. MDPI - Sensors, 4(2):16.
De Poorter, E., Hoebeke, J., Strobbe, M., Moerman, I., Latre, S., Weyn, M., Lannoo, B., and Famaey, J. (2017). Sub-ghz lpwan network coexistence, management and virtualization : an overview and open research challenges. WIRELESS PERSONAL COMMUNICATIONS, 95.
Hasegawa, S., Kim, S. J., Y.Shoji, and Hasegawa, M. (2020). Performance evaluation of machine learning based channel selection algorithm implemented on iot sensor devices in coexisting iot networks. 2020 IEEE 17th Annual Consumer Communications Networking Conference (CCNC)., 4(2):201–213.
Marais, J. M., Abu-Mahfouz, A. M., and Hancke, G. P. (2019). A review of lorawan simulators: Design requirements and limitations. In 2019 International Multidisciplinary Information Technology and Engineering Conference (IMITEC), pages 1–6.
Park, G., Lee, W., and I.Joe (2020). Network resource optimization with reinforcement learning for low power wide area networks. EURASIP Journal on Wireless Communications and Networking, (176).
Raza, U., Kulkarni, P., and Sooriyabandara, M. (2017). Low power wide area networks: An overview. IEEE Communications Surveys Tutorials, 19(2):855–873.
Semtech (2019). An1200.22 lora modulation basics. Technical Report 2, Semtech - LoRa Alliance, Semtech Corporation.
Tesfay, A. A., Simon, E. P., Nevat, I., and Clavier, L. (2020). Multiuser detection for downlink communication in lora- like networks. IEEE Access, 8:199001–199015.
Weyn, M. (2016). Lpwan simulation. https://github.com/maartenweyn/lpwansimulation.
Xu, Z., Luo, J., Yin, Z., He, T., and Dong, F. (2020). S-mac: Achieving high scalability via adaptive scheduling in lpwan. In IEEE INFOCOM 2020 - IEEE Conference on Computer Communications, pages 506–515.
Augustin, A., Clausen, T., J.Yi, and Townsley, W. (2016). A study of lora: Long range low power networks for the internet of things. MDPI - Sensors, 4(2):16.
De Poorter, E., Hoebeke, J., Strobbe, M., Moerman, I., Latre, S., Weyn, M., Lannoo, B., and Famaey, J. (2017). Sub-ghz lpwan network coexistence, management and virtualization : an overview and open research challenges. WIRELESS PERSONAL COMMUNICATIONS, 95.
Hasegawa, S., Kim, S. J., Y.Shoji, and Hasegawa, M. (2020). Performance evaluation of machine learning based channel selection algorithm implemented on iot sensor devices in coexisting iot networks. 2020 IEEE 17th Annual Consumer Communications Networking Conference (CCNC)., 4(2):201–213.
Marais, J. M., Abu-Mahfouz, A. M., and Hancke, G. P. (2019). A review of lorawan simulators: Design requirements and limitations. In 2019 International Multidisciplinary Information Technology and Engineering Conference (IMITEC), pages 1–6.
Park, G., Lee, W., and I.Joe (2020). Network resource optimization with reinforcement learning for low power wide area networks. EURASIP Journal on Wireless Communications and Networking, (176).
Raza, U., Kulkarni, P., and Sooriyabandara, M. (2017). Low power wide area networks: An overview. IEEE Communications Surveys Tutorials, 19(2):855–873.
Semtech (2019). An1200.22 lora modulation basics. Technical Report 2, Semtech - LoRa Alliance, Semtech Corporation.
Tesfay, A. A., Simon, E. P., Nevat, I., and Clavier, L. (2020). Multiuser detection for downlink communication in lora- like networks. IEEE Access, 8:199001–199015.
Weyn, M. (2016). Lpwan simulation. https://github.com/maartenweyn/lpwansimulation.
Xu, Z., Luo, J., Yin, Z., He, T., and Dong, F. (2020). S-mac: Achieving high scalability via adaptive scheduling in lpwan. In IEEE INFOCOM 2020 - IEEE Conference on Computer Communications, pages 506–515.
Publicado
25/10/2021
Como Citar
BEZERRA, Carlos D.; OLIVEIRA-JR, Antonio; VIEIRA, Flávio H. T..
Proposta de Controle de Espalhamento Espectral Utilizando Aprendizado por Reforço Profundo para Otimização do Desempenho de Redes LoRa/LoRaWAN. In: ESCOLA REGIONAL DE INFORMÁTICA DE GOIÁS (ERI-GO), 9. , 2021, Evento Online.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2021
.
p. 54-67.
DOI: https://doi.org/10.5753/erigo.2021.18433.
