Um controlador para um protocolo MAC híbrido em redes sem-fio baseado em aprendizado por reforço
Abstract
This paper proposes a reinforcement learning mechanism to select the operational mode of a hybrid MAC protocol, depending on traffic workload. This kind of protocol combines CSMA/CA and TDMA approaches, aiming to provide better throughput and lower latencies, and has been used in IEEE 802.11 wireless access networks. This paper presents a model of a controller for such MAC, which uses experience to learn to select the best operational model depending on the perceived state of the network.References
Ali, Z., Giupponi, L., Mangues, J., and Bojovic, B. (2017). Machine Learning Based Scheme for Contention Window Size Adaptation in LTE-LAA. In in Proceedings of 28th Annual IEEE International Symposium on Personal, Indoor and Mobile Radio Communications (IEEE PIMRC 2017), 8-13 October 2017, Montreal (Canada).
Amuru, S., Xiao, Y., van der Schaar, M., and Buehrer, R. M. (2015). To send or not to send - learning mac contention. In 2015 IEEE Global Communications Conference (GLOBECOM), pages 1–6.
Choe, C., Choi, J., Ahn, J., Park, D., and Ahn, S. (2020). Multiple channel access using deep reinforcement learning for congested vehicular networks. In 2020 IEEE 91st Vehicular Technology Conference (VTC2020-Spring), pages 1–6.
Edalat, Y. and Obraczka, K. (2019). Dynamically tuning ieee 802.11’s contention window using machine learning. In MSWIM ’19: Proceedings of the 22nd International ACM Conference on Modeling, Analysis and Simulation of Wireless and Mobile Systems, pages 19–26.
IEEE (2016). IEEE standard for information technology—telecommunications and information exchange between systems local and metropolitan area networks—specific requirements - part 11: Wireless lan medium access control (mac) and physical layer (phy) specifications. IEEE Std 802.11-2016 (Revision of IEEE Std 802.11-2012), pages 1–3534.
Israr, I., Yaqoob, M. M., Javaid, N., Qasim, U., and Khan, Z. A. (2012). Simulation analysis of medium access techniques. In 2012 Seventh International Conference on Broadband, Wireless Computing, Communication and Applications, pages 602–607.
Panigrahi, D. and Raman, B. (2009). Tdma scheduling in long-distance wifi networks. In IEEE INFOCOM 2009, pages 2931–2935.
Patra, R., Nedevschi, S., Surana, S., Sheth, A., Subramanian, L., and Brewer, E. (2007).Wildnet: Design and implementation of high performance wifi based long distance networks. In 4th USENIX Symposium on Networked Systems Design & Implementation (NSDI 07), Cambridge, MA. USENIX Association.
Pressas, A., Sheng, Z., Ali, F., and Tian, D. (2019). A q-learning approach with collective contention estimation for bandwidth-efficient and fair access control in IEEE 802.11p vehicular networks. IEEE Trans. Veh. Technol., 68(9):9136–9150.
Simó, J., Figuera, C., Seoane, J., and Mart’inez, A. (2007). Distance limits in IEEE 802.11 for rural networks in developing countries. proc. IEEE WRECOM.
Sutton, R. S. and Barto, A. G. (2018). Reinforcement learning: An introduction. MIT press.
Wang, Q., Jaffr`es-Runser, K., Xu, Y., Scharbarg, J., An, Z., and Fraboul, C. (2016). Tdma versus csma/ca for wireless multi-hop communications: A comparison for soft real-time networking. In 2016 IEEE World Conference on Factory Communication Systems (WFCS), pages 1–4.
Amuru, S., Xiao, Y., van der Schaar, M., and Buehrer, R. M. (2015). To send or not to send - learning mac contention. In 2015 IEEE Global Communications Conference (GLOBECOM), pages 1–6.
Choe, C., Choi, J., Ahn, J., Park, D., and Ahn, S. (2020). Multiple channel access using deep reinforcement learning for congested vehicular networks. In 2020 IEEE 91st Vehicular Technology Conference (VTC2020-Spring), pages 1–6.
Edalat, Y. and Obraczka, K. (2019). Dynamically tuning ieee 802.11’s contention window using machine learning. In MSWIM ’19: Proceedings of the 22nd International ACM Conference on Modeling, Analysis and Simulation of Wireless and Mobile Systems, pages 19–26.
IEEE (2016). IEEE standard for information technology—telecommunications and information exchange between systems local and metropolitan area networks—specific requirements - part 11: Wireless lan medium access control (mac) and physical layer (phy) specifications. IEEE Std 802.11-2016 (Revision of IEEE Std 802.11-2012), pages 1–3534.
Israr, I., Yaqoob, M. M., Javaid, N., Qasim, U., and Khan, Z. A. (2012). Simulation analysis of medium access techniques. In 2012 Seventh International Conference on Broadband, Wireless Computing, Communication and Applications, pages 602–607.
Panigrahi, D. and Raman, B. (2009). Tdma scheduling in long-distance wifi networks. In IEEE INFOCOM 2009, pages 2931–2935.
Patra, R., Nedevschi, S., Surana, S., Sheth, A., Subramanian, L., and Brewer, E. (2007).Wildnet: Design and implementation of high performance wifi based long distance networks. In 4th USENIX Symposium on Networked Systems Design & Implementation (NSDI 07), Cambridge, MA. USENIX Association.
Pressas, A., Sheng, Z., Ali, F., and Tian, D. (2019). A q-learning approach with collective contention estimation for bandwidth-efficient and fair access control in IEEE 802.11p vehicular networks. IEEE Trans. Veh. Technol., 68(9):9136–9150.
Simó, J., Figuera, C., Seoane, J., and Mart’inez, A. (2007). Distance limits in IEEE 802.11 for rural networks in developing countries. proc. IEEE WRECOM.
Sutton, R. S. and Barto, A. G. (2018). Reinforcement learning: An introduction. MIT press.
Wang, Q., Jaffr`es-Runser, K., Xu, Y., Scharbarg, J., An, Z., and Fraboul, C. (2016). Tdma versus csma/ca for wireless multi-hop communications: A comparison for soft real-time networking. In 2016 IEEE World Conference on Factory Communication Systems (WFCS), pages 1–4.
Published
2020-11-25
How to Cite
B. SOUSA, Camilla; M. SOBRAL, Marcelo.
Um controlador para um protocolo MAC híbrido em redes sem-fio baseado em aprendizado por reforço. In: REGIONAL SCHOOL OF COMPUTER NETWORKS (ERRC), 18. , 2020, Evento Online.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2020
.
p. 34-40.
DOI: https://doi.org/10.5753/errc.2020.15186.
