Deep Reinforcement Learning for Optimization of STAR-RIS Phase and Energy Splitting Coefficients in OTFS-NOMA Framework
Abstract
This paper considers a downlink communication framework comprising a simultaneously transmitting and reflecting reconfigurable intelligent surface (STAR-RIS)-aided by orthogonal time frequency space (OTFS) and non-orthogonal multiple access (NOMA) technologies. Further, delay-Doppler mobility in such frameworks renders classical alternating optimization impractical for per-coherence interval reconfiguration. To mitigate such issues, the STAR-RIS phase-shift and energy-splitting design is formulated as a constrained, non-convex sum-rate maximization problem with closed-form maximum ratio transmission beamforming and fixed NOMA power allocation. To circumvent the per-interval re-optimization burden, a deep reinforcement learning (DRL) approach is adopted that maps observed channel realizations to STAR-RIS configurations through a single forward pass. Specifically, Beta-Space Soft Actor-Critic (SAC-BSE), a maximum entropy DRL agent, is proposed. Simulation results, with two NOMA-multiplexed users on each STAR-RIS branch, confirm rapid convergence, limit the sum-rate degradation to roughly 10\% across a 128-fold user-speed range, and yield consistent gains over OTFS-only, NOMA-only, STAR-RIS-only, fixed-split, and mode-switching baselines as transmit power and the number of STAR-RIS elements increase.
Related
- Extending graph metrics to hyperspaces of vertex sets: optimization and reinforcement learning applications
- Efficient Joint Trajectory Optimization and Resource Allocation for Secure UAV Networks: A Deep Reinforcement Learning Approach
- HALO: Hierarchical Evidence Selection and Reinforcement Learning for Allocating Budgeted Label Optimization from Longitudinal Clinical Records
- Deep Reinforcement Learning-Aided Optimization of Multi-Interface Allocation for Short-Packet Communications
- Distribution-Agnostic Robust Trajectory Optimization via Chance-Constrained Reinforcement Learning
BibTeX
@misc{gachaba2026deep,
title = {{Deep Reinforcement Learning for Optimization of STAR-RIS Phase and Energy Splitting Coefficients in OTFS-NOMA Framework}},
author = {Rais. J. Gachaba and Manobendu Sarker and Anirban Bhowal},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.04536},
eprint = {2609.04536},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.04536},
}
RIS
TY - UNPB
TI - Deep Reinforcement Learning for Optimization of STAR-RIS Phase and Energy Splitting Coefficients in OTFS-NOMA Framework
AU - Rais. J. Gachaba
AU - Manobendu Sarker
AU - Anirban Bhowal
PY - 2026
DA - 2026/09/03
PB - arXiv
DO - 10.48550/arxiv.2609.04536
UR - https://arxiv.org/abs/2609.04536
AB - This paper considers a downlink communication framework comprising a simultaneously transmitting and reflecting reconfigurable intelligent surface (STAR-RIS)-aided by orthogonal time frequency space (OTFS) and non-orthogonal multiple access (NOMA) technologies. Further, delay-Doppler mobility in such frameworks renders classical alternating optimization impractical for per-coherence interval reconfiguration. To mitigate such issues, the STAR-RIS phase-shift and energy-splitting design is formulated as a constrained, non-convex sum-rate maximization problem with closed-form maximum ratio transmission beamforming and fixed NOMA power allocation. To circumvent the per-interval re-optimization burden, a deep reinforcement learning (DRL) approach is adopted that maps observed channel realizations to STAR-RIS configurations through a single forward pass. Specifically, Beta-Space Soft Actor-Critic (SAC-BSE), a maximum entropy DRL agent, is proposed. Simulation results, with two NOMA-multiplexed users on each STAR-RIS branch, confirm rapid convergence, limit the sum-rate degradation to roughly 10\% across a 128-fold user-speed range, and yield consistent gains over OTFS-only, NOMA-only, STAR-RIS-only, fixed-split, and mode-switching baselines as transmit power and the number of STAR-RIS elements increase.
ER -