# DRL-AdaPart: DRL-Driven Adaptive STAR-RIS Partitioning for Fair and Efficient Resource Utilization

arXiv: https://arxiv.org/abs/2407.06868 · HTML: https://mlsanity.com/paper/2407.06868/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 55 references that are in the map.
- First posted on arXiv 9 Jul 2024.

## Builds on (most cited first, 26 of 26)

- [Continuous control with deep reinforcement learning](https://mlsanity.com/paper/1509.02971/) (2015)
- [Playing Atari with Deep Reinforcement Learning](https://mlsanity.com/paper/1312.5602/) (2013)
- [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016)
- [Non-convex Min-Max Optimization: Applications, Challenges, and Recent Theoretical Advances](https://mlsanity.com/paper/2006.08141/) (2020)
- [Wireless Communications Through Reconfigurable Intelligent Surfaces](https://mlsanity.com/paper/1906.09490/) (2019)
- [Deep Reinforcement Learning for Intelligent Reflecting Surfaces: Towards Standalone Operation](https://mlsanity.com/paper/2002.11101/) (2020)
- [Deep Reinforcement Learning based Blind mmWave MIMO Beam Alignment](https://mlsanity.com/paper/2001.09251/) (2020)
- [STAR-RIS Integrated Non-Orthogonal Multiple Access and Over-the-Air Federated Learning: Framework, Analysis, and Optimization](https://mlsanity.com/paper/2106.08592/) (2021)
- [Energy-Efficient Power Control: A Look at 5G Wireless Technologies](https://mlsanity.com/paper/1503.04609/) (2015)
- [Graph-Embedded Multi-Agent Learning for Smart Reconfigurable THz MIMO-NOMA Networks](https://mlsanity.com/paper/2107.07198/) (2021)
- [A DRL Approach for RIS-Assisted Full-Duplex UL and DL Transmission: Beamforming, Phase Shift and Power Optimization](https://mlsanity.com/paper/2212.13854/) (2022)
- [Reconfigurable Intelligent Surfaces: A Signal Processing Perspective With Wireless Applications](https://mlsanity.com/paper/2102.00742/) (2021)
- [Aerial STAR-RIS Empowered MEC: A DRL Approach for Energy Minimization](https://mlsanity.com/paper/2312.08714/) (2023)
- [Robust Beamforming for RIS-aided Communications: Gradient-based Manifold Meta Learning](https://mlsanity.com/paper/2402.10626/) (2024)
- [Wireless Network Coding with Intelligent Reflecting Surfaces](https://mlsanity.com/paper/2103.11982/) (2021)
- [Resource Allocation in STAR-RIS-Aided Networks: OMA and NOMA](https://mlsanity.com/paper/2111.03883/) (2021)
- [Sum Rate Maximization in STAR-RIS Assisted Full-Duplex Communication Systems](https://mlsanity.com/paper/2203.04709/) (2022)
- [Multiuser Full-Duplex Two-Way Communications via Intelligent Reflecting Surface](https://mlsanity.com/paper/2006.05147/) (2020)
- [Transforming Fading Channel from Fast to Slow: IRS-Assisted High-Mobility Communication](https://mlsanity.com/paper/2011.03147/) (2020)
- [Channel Estimation for STAR-RIS-aided Wireless Communication](https://mlsanity.com/paper/2112.01413/) (2021)
- [STAR-RIS-NOMA Networks: An Error Performance Perspective](https://mlsanity.com/paper/2202.09597/) (2022)
- [Two-Timescale Design for STAR-RIS Aided NOMA Systems](https://mlsanity.com/paper/2207.00792/) (2022)
- [Phase Shift-Free Passive Beamforming for Reconfigurable Intelligent Surfaces](https://mlsanity.com/paper/2208.09627/) (2022)
- [DRL Enabled Coverage and Capacity Optimization in STAR-RIS Assisted Networks](https://mlsanity.com/paper/2209.00511/) (2022)
- [Performance Analysis and Resource Allocation of STAR-RIS Aided Wireless-Powered NOMA System](https://mlsanity.com/paper/2301.08865/) (2023)
- [To Reflect or Not To Reflect: On-Off Control and Number Configuration for Reflecting Elements in RIS-Aided Wireless Systems](https://mlsanity.com/paper/2304.10322/) (2023)

## Abstract (arXiv)

Efficient resource utilization is proposed for simultaneously transmitting and reflecting reconfigurable intelligent surfaces (STAR-RIS) to ensure fair and high data rates. We optimize the number of STAR-RIS elements to be allocated to each user and maximize the sum of the user rates. To promote fairness, we introduce a soft fairness mechanism that guarantees a minimum STAR-RIS element allocation to every user. Subject to this requirement, the phase shifts of the STAR-RIS elements and the remaining element assignments are jointly optimized by harnessing an appropriately tailored deep reinforcement learning (DRL) algorithm. The proposed DRL method is also compared to Dinkelbach's algorithm and to a bespoke hybrid DRL approach. A deactivation incentive is incorporated into the DRL model for enhancing resource utilization by intelligently deactivating some of the STAR-RIS elements when not required. The proposed DRL method achieves fair and high data rates for both stationary and mobile users, while ensuring efficient resource utilization. Using the proposed DRL method, up to 34% and 23% of STAR-RIS elements can be deactivated in static and mobile scenarios, respectively, with negligible degradation in the average DL data rate.