Author

Ruichen Zhang

View on Semantic Scholar

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

2026

Near-Field Wideband SWIPT With Delay-Phase Precoding: Beam Training and Optimization

To address the dual demands of high data transmission and energy supply in sixth-generation (6G) networks, this paper investigates near-field wideband simultaneous wireless information and power transfer (SWIPT) with power splitting for multiple mobile stations. To mitigate the beam splitting effect, we introduce fully- and sub-connected delay-phase precoding (DPP) architectures. Under energy harvesting constraints, we formulate a sum spectral efficiency maximization problem by jointly optimizing phase shifter (PS)- and true-time-delay (TTD)-based analog precoders, digital precoders, power allocation, and power splitting factors. We reveal controllable beam splitting and beam focusing phenomena in near-field wideband DPP, which can be flexibly adjusted through TTD and PS tuning. For the fully-connected DPP, we propose an efficient beam training scheme via frequency-domain angle search and time-domain distance search. Moreover, for the sub-connected DPP, we develop a structured precoding approximation matching (SPAM) mechanism. Based on beam training results, we design information decoding-oriented and energy harvesting-oriented digital precoders to balance the spectral efficiency-energy harvesting trade-off. Finally, we propose an alternating optimization framework and a low-complexity sequential quadratic programming method to solve the joint power allocation and splitting optimization. Simulation results demonstrate that the proposed schemes achieve superior spectral and energy efficiency in near-field wideband SWIPT systems.

Junjie Li, Jie Zhang, Liang Yang et al. · IEEE Transactions on Communi... · 0 citations

Review Open access Dec 2025

Tutorial on Large Language Model-Enhanced Reinforcement Learning for Wireless Networks

Reinforcement Learning (RL) has shown remarkable success in enabling adaptive and data-driven optimization for various applications in wireless networks. However, classical RL suffers from limitations in generalization, learning feedback, interpretability, and sample efficiency in dynamic wireless environments. Large Language Models (LLMs) have emerged as a transformative Artificial Intelligence (AI) paradigm with exceptional capabilities in knowledge generalization, contextual reasoning, and interactive generation, which have demonstrated strong potential to enhance classical RL. This paper serves as a comprehensive tutorial on LLM-enhanced RL for wireless networks. We propose a taxonomy to categorize the roles of LLMs into four critical functions: state perceiver, reward designer, decision-maker, and generator. Then, we review existing studies exploring how each role of LLMs enhances different stages of the RL pipeline. Moreover, we provide a series of case studies to illustrate how to design and apply LLM-enhanced RL in low-altitude economy networking, vehicular networks, and space–air–ground integrated networks. Finally, we conclude with a discussion on potential future directions for LLM-enhanced RL and offer insights into its future development in wireless networks.

Lingyi Cai, Wenjie Fu, Yuxi Huang et al. · IEEE Communications Surveys... · 2 citations