[论文解读] Learning-based Predictive Beamforming for Integrated Sensing and Communication in Vehicular Networks
该论文提出了一种基于深度学习的预测波束成形框架,用于车辆网络中的感知与通信一体化(ISAC),利用历史信道估计来预测最优波束成形器,而无需显式进行信道跟踪。该方法在保持严格感知精度的同时,实现了接近最优的和速率性能,仿真结果验证了其CRLB性能可低至10⁻⁴ m,且和速率接近理想基准(genie-aided基准)。
This paper investigates the integrated sensing and communication (ISAC) in vehicle-to-infrastructure (V2I) networks. To realize ISAC, an effective beamforming design is essential which however, highly depends on the availability of accurate channel tracking requiring large training overhead and computational complexity. Motivated by this, we adopt a deep learning (DL) approach to implicitly learn the features of historical channels and directly predict the beamforming matrix to be adopted for the next time slot to maximize the average achievable sum-rate of an ISAC system. The proposed method can bypass the need of explicit channel tracking process and reduce the signaling overhead significantly. To this end, a general sum-rate maximization problem with Cramer-Rao lower bounds (CRLBs)-based sensing constraints is first formulated for the considered ISAC system taking into account the multiple access interference. Then, by exploiting the penalty method, a versatile unsupervised DL-based predictive beamforming design framework is developed to address the formulated design problem. As a realization of the developed framework, a historical channels-based convolutional long short-term memory (LSTM) network (HCL-Net) is devised for predictive beamforming in the ISAC-based V2I network. Specifically, the convolution and LSTM modules are successively adopted in the proposed HCL-Net to exploit the spatial and temporal dependencies of communication channels to further improve the learning performance. Finally, simulation results show that the proposed predictive method not only guarantees the required sensing performance, but also achieves a satisfactory sum-rate that can approach the upper bound obtained by the genie-aided scheme with the perfect instantaneous channel state information available.
研究动机与目标
- 解决传统基于ISAC的V2I网络中通道跟踪带来的高训练开销和计算复杂度问题。
- 实现在高速移动车辆环境中实时波束成形,其中信道状态信息迅速过时。
- 在实际硬件和频谱约束下,联合优化通信速率与感知精度。
- 开发一种无需模型、无监督的深度学习框架,从历史信道估计中学习,以预测未来的波束成形器。
- 在高 spectral efficiency 和高精度定位之间实现平衡。
提出的方法
- 建立一个以Cramer-Rao下界(CRLB)为基础的约束条件的通用和速率最大化问题,以确保所需的感知精度。
- 应用惩罚法将约束优化问题转化为无约束问题,以支持端到端的深度学习训练。
- 设计了一种新型HCL-Net架构,结合卷积层与长短期记忆(LSTM)网络,以捕捉信道的空间与时间相关性。
- 以历史估计的信道矩阵作为HCL-Net的输入,使网络能够隐式学习信道动态特性,而无需瞬时CSI。
- 采用结合和速率最大化与基于CRLB的感知约束的损失函数,对HCL-Net进行无监督训练。
- 在训练过程中采用基于惩罚的松弛方法,以强制执行感知性能约束,避免在每个时隙中显式进行信道估计。
实验结果
研究问题
- RQ1深度学习模型能否足够准确地预测未来波束成形器,以在高速移动的V2I场景中维持高通信和速率?
- RQ2仅基于历史信道估计进行训练的模型,在感知性能上能在多大程度上接近具备完美瞬时CSI系统的性能?
- RQ3所提方法在ISAC系统中如何平衡通信速率与定位精度之间的权衡?
- RQ4HCL-Net在不同移动性和系统参数下的收敛行为与泛化能力如何?
- RQ5所提出的无监督学习框架能否消除对显式信道跟踪的需求,同时保持性能接近理想基准(genie-aided upper bound)?
主要发现
- 所提出的HCL-Net在测试中达到的平均和速率接近于具备完美瞬时CSI的理想方案(genie-aided scheme)的上界。
- 在48根发射与接收天线配置下,该方法实现了距离估计的CRLB^(1/2)为10⁻⁴ m,足以支持高速车辆跟踪。
- HCL-Net在和速率与CRLB指标上均在6个训练周期内收敛至稳定性能,表明其训练速度快且高效。
- 感知-通信权衡关系得到量化,表明当CRLB阈值超过9×10⁻³时,和速率趋于饱和,表明在宽松感知约束下性能达到平台期。
- 该模型在不同发射功率水平和天线配置下表现出鲁棒性,同时保持高性能并仅引入极低的信令开销。
- 卷积LSTM结构能有效捕捉信道动态的空间与时间特征,在波束成形预测任务中优于简单架构。
更好的研究,从现在开始
从阅读论文到最终审阅,大幅缩短您的研究时间。
无需绑定信用卡
本解读由 AI 生成,并经人工编辑审核。