arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1905.04041eess.SPcs.ITmath.IT
收藏

基于深度强化学习的共生无线电网络智能用户关联

Intelligent User Association for Symbiotic Radio Networks using Deep Reinforcement Learning

Qianqian Zhang, Ying-Chang Liang, H. Vincent Poor

摘要:

在本文中,我们感兴趣的是共生无线电网络,其中物联网(IoT)网络寄生在主网络中,以实现频谱,能源和基础设施高效的通信。具体地,BS使用时分多址接入(TDMA)来服务多个蜂窝用户,并且每个IoT设备与一个蜂窝用户相关联以用于信息传输。我们专注于用户关联问题,其目标是通过最大化所有物联网设备的总速率将每个物联网设备链接到适当的蜂窝用户。然而,在获得完整的实时信道信息的困难,这使得它很难设计一个最优的策略,这个问题。为了克服这个问题,我们提出了两种深度强化学习(DRL)算法,它们都使用历史信息来推断当前信息,以便做出适当的决策。其中一种算法是集中式DRL,它利用全局信息同时为所有物联网设备做出决策。另一种算法是分布式DRL,它使用本地信息一次只为一个IoT设备做出决定。仿真结果表明,作为最优的用户关联策略,两种DRL算法的性能相当,且分布式DRL算法具有可扩展性的优势。

英文摘要:

In this paper, we are interested in symbiotic radio networks, in which an Internet-of-Things (IoT) network parasitizes in a primary network to achieve spectrum-, energy-, and infrastructure-efficient communications. Specifically, the BS serves multiple cellular users using time division multiple access (TDMA) and each IoT device is associated with one cellular user for information transmission. We focus on the user association problem, whose objective is to link each IoT device to an appropriate cellular user by maximizing the sum rate of all IoT devices. However, the difficulty in obtaining the full real-time channel information makes it difficult to design an optimal policy for this problem. To overcome this issue, we propose two deep reinforcement learning (DRL) algorithms, both use the historical information to infer the current information in order to make appropriate decisions. One algorithm, centralized DRL, makes decisions for all IoT devices at one time with global information. The other algorithm, distributed DRL, makes a decision only for one IoT device at one time using local information. Finally, simulation results show that the two DRL algorithms achieve comparable performance as the optimal user association policy which requires perfect real-time information, and the distributed DRL algorithm has the advantage of scalability.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑