论文标题
演示：基于RIS和AI的低功率通信用于6G
Demo: low-power communications based on RIS and AI for 6G
论文作者
论文摘要
超质量的多输入量输出（UM-MIMO）有望满足未来6G的高利率要求。但是，由于天线和高路径损失，硬件功耗和UM-MIMO的计算功耗将是无法承受的。为了解决这个问题，我们基于可重新配置的智能表面（RIS）和人工智能（AI）实施了低功率通信系统。对于硬件设计，我们在基站使用256个元素的RI来替换传统的分阶段阵列。此外，开发了2304个元素的RIS作为继电器，以帮助传播功率大大降低。对于软件实施，我们开发了一种基于AI的传输设计，以减少计算功耗。通过共同设计硬件和软件，该原型可以实现实时的4K视频传输，而功耗大大降低。
Ultra-massive multiple-input-multiple-output (UM-MIMO) is promising to meet the high rate requirements for future 6G. However, due to the large number of antennas and high path loss, the hardware power consumption and computing power consumption of UM-MIMO will be unaffordable. To address this problem, we implement a low-power communication system based on reconfigurable intelligent surface (RIS) and artificial intelligence (AI) for 6G. For hardware design, we employ a 256-element RIS at the base station to replace the traditional phased array. Moreover, a 2304-element RIS is developed as a relay to assist communication with much reduced transmit power. For software implementation, we develop an AI-based transmission design to reduce computing power consumption. By jointly designing the hardware and software, this prototype can realize real-time 4K video transmission with much reduced power consumption.
