This paper explores a reconfigurable intelligent surface (RIS)-assisted and semantic-aware wireless network, where multiple semantic users (SUs) transmit semantic information to an access point (AP) using the non-orthogonal multiple access (NOMA) method. The RIS reconfigures channel conditions, while semantic extraction reshapes traffic demands, providing enhanced control flexibility for NOMA transmissions. To enable efficient long-term resource allocation, we propose a deferrable semantic extraction scheme that can distribute the semantic extraction tasks across multiple time slots. We formulate a long-term energy efficiency maximization problem by jointly optimizing the RIS's passive beamforming, the SUs' semantic extraction, and the NOMA decoding order. Note that this problem involves multiple and coupled control variables, which can incur significant computational overhead in time-varying network environments. To support low-complexity online optimization, a deep reinforcement learning (DRL)-driven online optimization framework is developed. Specifically, the DRL module facilitates the adaptive selection and optimization of the most suitable option from traffic reshaping, channel reconfiguration, or NOMA decoding order assignment based on the dynamic network status. Numerical results demonstrate that the deferrable semantic extraction scheme significantly improves the long-term energy efficiency. Meanwhile, the DRL-driven online optimization framework effectively reduces the running time while maintaining superior learning performance compared to state-of-the-art methods.

翻译：本文研究了一种可重构智能表面（RIS）辅助的语义感知无线网络，其中多个语义用户（SUs）采用非正交多址接入（NOMA）方法向接入点（AP）传输语义信息。RIS对信道条件进行重构，而语义提取则重塑流量需求，为NOMA传输提供了更强的控制灵活性。为支持高效的长期资源分配，我们提出一种可延迟语义提取方案，能够将语义提取任务分散到多个时隙中执行。通过联合优化RIS的被动波束赋形、SUs的语义提取以及NOMA解码顺序，构建了长期能量效率最大化问题。需注意该问题涉及多个耦合控制变量，在时变网络环境下会产生显著的计算开销。为支持低复杂度在线优化，我们开发了一种深度强化学习（DRL）驱动的在线优化框架。具体而言，DRL模块根据动态网络状态，自适应选择并优化流量整形、信道重构或NOMA解码顺序分配中的最优方案。数值结果表明，可延迟语义提取方案显著提升了长期能量效率。同时，与现有最优方法相比，DRL驱动的在线优化框架在保持优越学习性能的同时有效降低了运行时间。