Priority Based Adaptive Slotted ALOHA Method Using Q-Learning 


Vol. 48,  No. 3, pp. 350-358, Mar.  2023
10.7840/kics.2023.48.3.350


PDF
  Abstract

In this paper, we propose Priority-based Adaptive slotted ALOHA (PAS-ALOHA), which applies Q-learning and priorities to existing slotted ALOHA method. The PAS-ALOHA method prioritizes devices with many number of successful transmissions of data packets in the previous state according to the  -value of each device. Next, when transmitting the remaining data packet, since it is not restricted by other devices, the success ratio is increased and the collision ratio is reduced. In addition, the fairness of each device is compared according to negative reward by applying the Jain's Fairness Index. Experiments showed that the success ratio increased by about 69% and the collision ratio decreased by up to 30%. Therefore, even if the number of devices increases in the 5G MTC environment, it is expected that data packets can be successfully and fairly transmitted by adapting to the channel state.

  Statistics
Cumulative Counts from November, 2022
Multiple requests among the same browser session are counted as one view. If you mouse over a chart, the values of data points will be shown.


  Related Articles
  Cite this article

[IEEE Style]

JeenaKim, ByungchanKim, CheolwooYou, HyunheePark, "Priority Based Adaptive Slotted ALOHA Method Using Q-Learning," The Journal of Korean Institute of Communications and Information Sciences, vol. 48, no. 3, pp. 350-358, 2023. DOI: 10.7840/kics.2023.48.3.350.

[ACM Style]

JeenaKim, ByungchanKim, CheolwooYou, and HyunheePark. 2023. Priority Based Adaptive Slotted ALOHA Method Using Q-Learning. The Journal of Korean Institute of Communications and Information Sciences, 48, 3, (2023), 350-358. DOI: 10.7840/kics.2023.48.3.350.

[KICS Style]

JeenaKim, ByungchanKim, CheolwooYou, HyunheePark, "Priority Based Adaptive Slotted ALOHA Method Using Q-Learning," The Journal of Korean Institute of Communications and Information Sciences, vol. 48, no. 3, pp. 350-358, 3. 2023. (https://doi.org/10.7840/kics.2023.48.3.350)
Vol. 48, No. 3 Index