DRL-driven Online Optimization for Joint Traffic Reshaping and Channel Reconfiguration in RIS-assisted Semantic NOMA Communications

2026-03-22

AI Summary

This work addresses the high computational overhead and energy efficiency optimization challenges in reconfigurable intelligent surface (RIS)-assisted semantic-aware non-orthogonal multiple access (NOMA) networks under time-varying conditions, where multiple coupled variables complicate system design. To tackle this, the paper proposes a delay-tolerant semantic extraction mechanism that enhances NOMA decoding flexibility through traffic shaping and jointly optimizes RIS passive beamforming, semantic extraction policies, and user decoding order. An online adaptive framework based on deep reinforcement learning (DRL) is developed to enable joint decision-making over channel reconfiguration, traffic scheduling, and resource allocation. Experimental results demonstrate that the proposed approach significantly improves long-term energy efficiency, substantially reduces runtime, and achieves superior learning performance compared to state-of-the-art methods.

Technology Category

• Search and Optimization: Learning to Search
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Intelligent Robots: Learning & Optimization for ROB

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

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.

Problem

• RIS
• Semantic Communications
• NOMA
• Energy Efficiency
• Online Optimization

Innovation

• Deep Reinforcement Learning
• Reconfigurable Intelligent Surface
• Semantic Communication
• NOMA
• Online Optimization