Learning Variable-Rate Codes for CSI Feedback
Learning Variable-Rate Codes for CSI Feedback
复制标题
DOI：
10.1109/globecom48099.2022.10000622
复制
发表时间：
2022-12
期刊：
影响因子：
--
通讯作者：
Heasung Kim;Hyeji Kim;G. Veciana
中科院分区：
文献类型：
--
作者：
Heasung Kim;Hyeji Kim;G. Veciana
我们观察到当前基于深度学习（DL）的信道状态信息（CSI）编码器和解码器架构实现了高度依赖信道的失真。为了利用这一点，我们提出了一种新的基于学习的可变速率编码方案，以减少与CSI反馈相关的开销。为此，我们提出了一种架构，该架构结合了(a)训练一个有效的预测器，用于给定信道可实现的失真率权衡，以及(b)优化基于预测失真分配速率的决策逻辑。我们在各种无线信道数据集（包括3GPP 3D信道模型和COST2100与Massive MIMO信道模型）上评估了我们的方法，并显示出CSI反馈开销显著降低高达20%的潜力。
We observe that current Deep Learning (DL)-based Channel State Information (CSI) encoder and decoder architectures achieve a distortion which is highly channel-dependent. To exploit this, we propose a novel learning-based variable-rate coding scheme to reduce overheads associated with CSI feedback. To that end, we propose an architecture which combines (a) training an efficient predictor for the distortion rate tradeoffs achievable for a given channel, and (b) optimization of a decision logic which allocates rates based on the predicted distortion. We evaluate our approach on various wireless channel datasets including the 3GPP 3D channel model and COST2100 with Massive MIMO channel model, and show significant potential reductions of up to 20% in the CSI feedback overhead.