Exploring Partially Overlapping Channels for Low Power Wide Area Networks
Exploring Partially Overlapping Channels for Low Power Wide Area Networks
复制标题
探索低功耗广域网的部分重叠通道
DOI：
10.1145/3546075
复制
发表时间：
2022
期刊：
影响因子：
--
通讯作者：
Qian Zhang
中科院分区：
文献类型：
--
作者：
Lu Wang;Xiaoke Qi;Ruifeng Huang;Kaishun Wu;Qian Zhang
支持大量物联网（IoT）应用需要大量的频谱池。动态频谱管理（DSM）是一种提高频谱利用率的有效方法。在远程WAN广域网（LoRaWAN）时代，物理硬件约束以及沿着的带宽需求应用提出了新的挑战。在本文中，我们研究了一种新的基于深度强化学习的频谱共享范式，称为智能重叠，它探索了LoRaWAN中并发频谱访问的部分重叠信道（POC）。我们的关键见解是利用编码冗余来扩展可用频谱，而无需复杂的数据处理算法。特别地，我们通过深度Q学习网络（DQN）从非重叠频谱上的数据中学习额外的编码冗余，并应用这种冗余来恢复重叠频谱上的数据。在MAC层中，我们预测信道条件，并且策略性地学习并将适当的重叠部分分配给并发接入终端设备。在物理层，我们利用交织来随机化相互干扰，以确保所有数据都保持可解码。仿真结果表明，与传统的DSM机制相比，智能重叠大大提高了频谱效率，具有快速的收敛速度。
Supporting a massive amount of Internet of Things (IoT) applications requires a large pool of spectrum. Dynamic spectrum management (DSM) is a promising ecosystem to improve the spectrum efficiency. In the era of Long-Range WAN Wide Area Networks (LoRaWAN), the physical hardware constraints, along with the bandwidth hungry applications pose new challenges. In this paper, we investigate a novel deep reinforcement learning based spectrum sharing paradigm, termed Intelligent Overlapping, that explores partially overlapping channels (POCs) for concurrent spectrum access in LoRaWAN. Our key insight is to leverage the coding redundancy to expand the available spectrum without complicated data processing algorithms. In particular, we learn the extra coding redundancy from the data on the non-overlapping spectrum via a deep Q-learning network (DQN), and apply such redundancy to recover the data on the overlapping spectrum. In the MAC layer, we predict the channel condition, and strategically learn and assign the appropriate overlapping portion to the concurrent access end devices. In the PHY layer, we harness interleaving to randomize the mutual interference to ensure that all the data remains decodable. Simulation results demonstrate that Intelligent Overlapping greatly improves the spectrum efficiency with a fast convergence rate compared to the conventional DSM mechanisms.