[论文解读] RIS-Enabled Wireless Channel Equalization: Adaptive RIS Equalizer and Deep Reinforcement Learning

Gal Ben-Itzhak, E. Ayanoglu|arXiv (Cornell University)|Mar 3, 2026

Advanced Wireless Communication Technologies被引用 0

一句话总结

该论文将基于自适应 RIS 的均衡（ARISE）与无模型深度强化学习（DRL）方法（DDPG、TD3、SAC）在 RIS 辅助的脉冲响应均衡中的性能进行对比，结果表明 SAC 能在复杂度更低且无需显式 CSI 的情况下达到与 ARISE 相当的性能。

ABSTRACT

Reconfigurable Intelligent Surfaces (RISs) offer a promising means of reshaping the wireless propagation environment, yet practical methods for configuring large passive arrays to achieve reliable signal equalization remain limited. Equalization is essential in wideband links to counteract multipath-induced pulse distortion that otherwise degrades symbol recovery. This work investigates RIS-assisted pulse response equalization and signal boosting using both classical adaptive filtering and model-free deep reinforcement learning (DRL). We develop a steepest descent (SD) method that exploits cascaded BS-RIS-UE channel information to configure RIS coefficients for multipath mitigation and SNR enhancement, and we show that the tradeoffs between SD and DRL primarily arise from the extensive channel estimation required for accurate equalization with passive RIS hardware. Unlike traditional adaptive filtering, which updates delayed filter coefficients after signal reception, our approach uses the RIS positioned within the cascaded channel to perform equalization without delay elements, prior to reception at the UE. In this framework, the channel is estimated before equalization, forming the basis of what we term adaptive RIS equalization (ARISE). To overcome the reliance on channel estimation required for ARISE, we explore several DRL algorithms -- DDPG, TD3, and SAC -- that optimize RIS coefficients directly from the received pulse response without explicit channel estimation. Through extensive simulations across diverse channel conditions and RIS sizes, we show that SAC achieves fast, stable convergence and equalization performance comparable to ARISE while offering significantly lower implementation complexity. These results highlight the potential of DRL as a practical and scalable solution for real-time RIS control in future wireless systems.

研究动机与目标

• 将 RIS 作为空中传输的等化器，用以抑制宽带链路中的多径引起的 ISI。
• 开发基于 SD 的自适应 RIS 均衡算法（ARISE），需要级联的 BS-RIS-UE 通道估计。
• 研究无模型 DRL 替代方案（DDPG、TD3、SAC），直接从接收的脉冲响应中优化 RIS 系数，而无需显式通道估计。

提出的方法

• 将 RIS 基于脉冲响应的均衡公式化，并使用估计的级联 BS-RIS-UE 通道推导出 SD 基的 ARISE 算法。
• 定义基于 ISI 和主 taps 的代价函数 J，并导出 RIS 系数的梯度更新规则，同时进行归一化以 enforce passivity（被动性）。
• 通过将状态、动作、奖励从接收的脉冲响应建模，扩展分析到 DRL，并评估 DDPG、TD3、SAC。
• 对单天线 BS 与 UE、M 元 RIS，以及不同的瑞奇系数和 ISI 项进行 RIS 场景仿真，以比较 ARISE 与 DRL 的性能。
• 评估在收敛性和复杂度方面，通道估计开销与无模型 DRL 方法之间的权衡。

Figure 1 : Illustration of the downlink RIS scenario. LoS paths are marked by solid lines, while NLoS paths are marked by dotted lines. Delayed paths and ISI components are created by reflections from obstacles.

实验结果

研究问题

• RQ1 ARISE 是否能有效地通过利用级联的 BS-RIS-UE 通道来实现等化并提升 RIS 辅助信号？
• RQ2 DRL 方法（DDPG、TD3、SAC）是否在没有 CSI 的情况下直接从脉冲响应优化 RIS 系数，且与 ARISE 相比表现如何？
• RQ3 哪种方法在收敛速度、复杂度和对不同信道类型及 RIS 大小的鲁棒性方面表现更好？
• RQ4 与通道估计和硬件非理想性相关的 ARISE 的实际限制有哪些？

主要发现

• ARISE 通过使用级联通道估计来优化 RIS 相位，可以提高主峰功率并降低 ISI。
• SAC 实现快速、稳定的收敛，并且性能可与 ARISE 相当，同时实现复杂度较低。
• DRL 方法能够无需 CSI 从脉冲响应直接优化，减少与通道估计相关的延迟。
• 在高维级联通道和大 RIS 尺度下，由于 CSI 开销和估计需求，ARISE 的性能会下降。
• 在仿真中，ARISE 的目标函数值通常高于随机或反相位方案，但需要准确的 CSI 才能用于 RIS 更新。

Figure 2 : Left: conventional feedforward equalizer (FFE) at the receiver vs. right: our proposed RIS-based equalizer. The conventional equalizer processes the baseband signal after reception using $n$ delay taps, whereas the RIS-based equalizer is at the midpoint of the cascaded BS-RIS-UE link and