基于强化学习的自适应编码调制策略

Adaptive coding modulation strategy based on reinforcement learning

NTN(Non-Terrestrial Network)是面向卫星通信和低空通信的重要应用场景,标志着5G技术应用从陆地通信走向了空间通信,可以预见卫星网络将是未来6G通信网络中重要组成。为了满足卫星通信质量要求、最大程度地增大系统容量,需要应用自适应编码调制技术根据信道状态信息在不断变化的通信环境下动态调整调制阶数和编码码率。人工智能在解决卫星高动态场景下信道条件快速变化所产生的问题具有明显的潜力。采用基于强化学习的低轨卫星自适应编码调制策略,解决了卫星通信环境的变化造成的门限表与实际信道不匹配的问题,与传统ARIMA (Autoregressive Integrated Moving Average)算法相比提升达到20%以上。

NTN(non-terrestrial network)is an important application scenario for satellite communications and low-altitude communications,marking the transition of 5G technology applications from land communications to space communications.It is foreseeable that satellite networks will be an important component of future 6G communications networks.In order to meet the quality requirements of satellite communication and maximize the system capacity,it is necessary to apply adaptive coding and modulation technology to dynamically adjust the modulation order and coding rate according to the channel state information in the changing communication environment.AI has clear potential to solve problems arising from rapidly changing channel conditions in satellite high-dynamic scenarios.This paper adopts the low-orbit satellite adaptive coding and modulation strategy based on reinforcement learning to solve the problem of the mismatch between the threshold table and the actual channel caused by the change of the satellite communication environment,which is improved by above 20%compared with the traditional ARIMA(autoregressive integrated moving average)algorithm.