Abstract—To improve the throughput of ALOHA in Ad Hoc, we proposed a fast convergence framed ALOHA (F-ALOHA). F-ALOHA combines ALOHA with reinforcement learning to achieve an optimal way to select time slot. Q-learning is applied to update the Q-value of the slot by feedback and memory. The agents remember the number of consecutive conflicts or successes in the current slot and the idle slots in the last frame. The truncated binary exponential increase algorithm is adopted to update Q-value to accelerate convergence. The simulation results show that the average convergence time of this algorithm is significantly lower than other ALOHA algorithms, and the throughput is higher than others.
Index Terms—Ad Hoc, ALOHA, reinforcement learning, time slot.
Shuai Xiaoying, Yin Yuxia, and Zhang Bin are with the Taizhou University, Taizhou, 225300, China (e-mail: xyshuai@163.com, shuaicz@yeah.net, 476382399@qq.com).
[PDF]
Cite:Shuai Xiaoying, Yin Yuxia, and Zhang Bin, "A Fast Convergence ALOHA Based on Reinforcement Learning," International Journal of Computer Theory and Engineering vol. 13, no. 3, pp. 96-99, 2021.
Copyright © 2021 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).
