Q-Learning-Based Spinal Code Transmission Strategy in Long Distance FSO Communication

In this paper, a spinal code transmission strategy based on Q-learning algorithm is proposed for long distance free space optical communication. The strategy adopts the Q-learning algorithm with the main objective of reducing the retransmission times to optimize the decoding waiting time and improve the transmission efficiency. The simulation results illustrate that, under the same turbulent conditions, the average retransmission times of the proposed transmission strategy is maintained at about one time, which is 94-99% less than the traditional spinal code transmission strategy and 78-92% less than the linear transmission strategy. Thus effectively improves the transmission efficiency of long-distance optical communication.