STAR-RIS-assisted Collaborative Beamforming for Low-altitude Wireless Networks

TL;DR

The paper tackles obstacle-induced link vulnerabilities in low-altitude wireless networks by integrating a UAV swarm with STAR-RIS to enable omnidirectional beamforming. It formulates a non-convex joint rate-energy optimization problem ($JREOP$) and proposes the heterogeneous multi-agent collaborative dynamic (HMCD) framework, combining an SA-based STAR-RIS controller (ATSO) with an enhanced MADRL controller (self-attention MASAC and adaptive velocity). Key contributions include reformulating the problem as a heterogeneous MDP, introducing collaboration-aware self-attention in the critic, and an adaptive velocity mechanism to stabilize training, with extensive simulations showing improved convergence, throughput, and energy efficiency that scale with UAVs and STAR-RIS elements. The work demonstrates practical potential for robust, energy-aware, and flexible LAWNs in urban environments and outlines future directions for security, multi-STAR-RIS deployments, and AI-driven high-dimensional optimization.

Abstract

While low-altitude wireless networks (LAWNs) based on uncrewed aerial vehicles (UAVs) offer high mobility, flexibility, and coverage for urban communications, they face severe signal attenuation in dense environments due to obstructions. To address this critical issue, we consider introducing collaborative beamforming (CB) of UAVs and omnidirectional reconfigurable beamforming (ORB) of simultaneous transmitting and reflecting reconfigurable intelligent surfaces (STAR-RIS) to enhance the signal quality and directionality. On this basis, we formulate a joint rate and energy optimization problem (JREOP) to maximize the transmission rate of the overall system, while minimizing the energy consumption of the UAV swarm. Due to the non-convex and NP-hard nature of JREOP, we propose a heterogeneous multi-agent collaborative dynamic (HMCD) optimization framework, which has two core components. The first component is a simulated annealing (SA)-based STAR-RIS control method, which dynamically optimizes reflection and transmission coefficients to enhance signal propagation. The second component is an improved multi-agent deep reinforcement learning (MADRL) control method, which incorporates a self-attention evaluation mechanism to capture interactions between UAVs and an adaptive velocity transition mechanism to enhance training stability. Simulation results demonstrate that HMCD outperforms various baselines in terms of convergence speed, average transmission rate, and energy consumption. Further analysis reveals that the average transmission rate of the overall system scales positively with both UAV count and STAR-RIS element numbers.

Figures (7)

• Figure 1: The model of the STAR-RIS-assisted UVAA communication system using joint CB and ORB while the direct channel is obscured.
• Figure 2: The proposed HMCD structure has two core components: an ATSO strategy for STAR-RIS control and an MADRL method for UAV coordination. The MADRL method features two key improvements: a self-attention evaluation mechanism and an adaptive velocity transition mechanism.
• Figure 3: Hyperparameter tuning results and convergence performance obtained by different methods. (a) Convergence verification versus different learning rate. (b) Convergence verification versus different discount factors. (c) Convergence performance comparison.
• Figure 4: Average transmission rate under different number of UAVs.
• Figure 5: Total energy consumption under different number of UAVs.