Skip to content
Open access

Active STAR-RIS-Aided Secure Integrated Sensing, Communication, and Power Transfer System: A Deep Reinforcement Learning Approach

2026 · IEEE Transactions on Green Communications and Networking · Vol 10, pp. 4537-4550 · 0 citations · 45 references

TL;DR

This paper investigates an active simultaneously transmitting and reflecting reconfigurable intelligent surface (STAR-RIS)-aided secure ISCPT system, and proposes a long short-term memory-enhanced proximal policy optimization (LSTM-PPO) deep reinforcement learning framework that achieves superior convergence performance compared with baseline algorithms.

Abstract

Integrated sensing, communication, and power transfer (ISCPT) is a promising paradigm for future Internet of Things (IoT) networks. Nevertheless, practical ISCPT implementations face two critical bottlenecks: severe multiplicative fading in non-line-of-sight scenarios and inherent physical-layer security risks, wherein sensing targets can act as potential eavesdroppers and intercept confidential information. This paper investigates an active simultaneously transmitting and reflecting reconfigurable intelligent surface (STAR-RIS)-aided secure ISCPT system, where the base station (BS) performs target sensing, confidential communication, and wireless power transfer simultaneously with the assistance of an active STAR-RIS. We formulate a non-convex optimization problem to maximize the average secrecy sum rate subject to sensing-accuracy and energy-harvesting constraints, by jointly optimizing BS beamforming, STAR-RIS transmission-reflection coefficients, and user power-splitting ratios. To address this computationally intractable problem, we transform the original optimization task into a Markov decision process and propose a long short-term memory-enhanced proximal policy optimization (LSTM-PPO) deep reinforcement learning framework. The embedded LSTM module extracts temporal correlations from sequential observations to boost policy adaptability under dynamic wireless channels. Simulation results demonstrate that the proposed LSTM-PPO achieves superior convergence performance compared with baseline algorithms. Benefiting from the spatial multiplexing and amplification gains of active STAR-RIS, the developed scheme yields enhanced secrecy sum rate, which makes it well-suited for secure next-generation IoT deployments.

Read PDF

Similar papers

Open access 2026

Self-Sustainable DF-IRS-Aided Integrated Sensing, Communication, and Power Transfer

This paper establishes a self-sustainable dual-functional intelligent reflecting surface (S-DF-IRS)-assisted integrated sensing, communication, and power transfer (ISCPT) system that synergistically combines target sensing, user communication, and wireless energy harvesting. Unlike existing studies, we conduct a system...

Xue-Yan Cao, Gerile Ge, Fei Xu et al. · 0 citations
Preprint Oct 2026

Dual Secure Sensing and Communications in MA-Enabled Networked ISAC Systems

Detailed numerical results validate the effectiveness of the proposed algorithms, demonstrating that the proposed MA-enabled networked cooperative ISAC design significantly outperforms conventional fixed-position antenna-based designs in terms of security performance, while achieving notable power- and antenna-saving g...

Yan Yang, Jian-Wei Zhao, Zhen-Dong Li et al. · 0 citations
Open access 2026

Secure Transmission Design for Active RIS-Aided ISAC System With Discrete Phase Shifts and Colluding Eavesdroppers

This letter investigates secure transmission in active reconfigurable intelligent surface (RIS)-assisted integrated sensing and communication (ISAC) systems. We consider a scenario with multiple colluding eavesdroppers (Eves), where a dual-functional ISAC base station (BS) simultaneously serves multiple legitimate user...

Jia-Le Shi, Yu-Hang Li, Li-Meng Dong et al. · 0 citations
Open access 2026

Robust Beamforming for Full-Duplex Integrated Secure Communication, Computation, and Energy Networks Under Imperfect CSI

This paper proposes a robust beamforming framework for a full-duplex (FD) integrated secure communication, computation, and energy (ISC2E) network. In the considered network, an FD base station (BS) simultaneously performs downlink wireless power transfer while aggregating uplink over-the-air computation data and recei...

Chang-Jie Hu, Jiashuo Sun, Tuo Wu et al. · 0 citations
2026

Robust IRS-Aided Secure Integrated Sensing and Communication With Artificial Noise

Integrated sensing and communication (ISAC) can concurrently enhance the hardware utilization and spectrum efficiency. However, due to the signal multiplexing and the openness of wireless channels, ISAC faces increased difficulty to prevent information eavesdropping. In this paper, we propose a robust secure beamformin...

Kai Chen, Jin-Lei Xu, Na Deng et al. · 0 citations
Open access Oct 2026

AI-Driven Secure Channel Estimation and Energy-Efficient Power Allocation for Cell-Free Massive MIMO

Cell-free massive multiple-input multiple-output (MIMO) improves user fairness by allowing many distributed access points (APs) to cooperatively serve users without fixed cell boundaries. Its practical reliability, however, is limited by pilot contamination, pilot spoofing, channel state-information (CSI) uncertainty,...

M. R. A. Albahri, M. Hankel · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.