D3QN-Based Joint Power and Reflection Optimization for Energy-Efficient Anti-Jamming against Dynamic Jamming Attacks in Backscatter-Enabled 6G IoT Networks
Aug 2026· Journal of Science and Technology on Information security· pp. 89-108· 0 citations· 54 references
TL;DR
A Dueling Double Deep Q-Network framework for joint transmit-power and reflection-coefficient control in backscatter-enabled 6G Internet-of-Things networks subject to random, reactive, and time-varying jamming is developed.
Abstract
This paper develops a Dueling Double Deep Q-Network (D3QN) framework for joint transmit-power and reflection-coefficient control in backscatter-enabled 6G Internet-of-Things networks subject to random, reactive, and time-varying jamming. The problem is formulated as a jammer-aware Markov decision process with a 20-action power–reflection space and a normalized reward that balances spectral efficiency, transmit-power consumption, and low-SINR outage. The proposed method is evaluated against DQN, DDQN, PPO, TD3, SAC, random selection, and fixed control over five independent seeds with 95% confidence intervals. Under random jamming at Pj = 30 dBm, D3QN improves spectral efficiency by 19.83% and reduces outage probability by 6.99% relative to DQN. Under a common dynamic-jamming trace, it provides a 2.12% spectral-efficiency gain while using an average transmit power of 0.427 W, with the maximum-power action selected in only 17.6% of the slots. The 20-action design also improves spectral efficiency by 4.21% over a 9-action grid while using 59.18% fewer outputs than a 49-action grid. Under strong reactive jamming, D3QN improves energy efficiency over DQN by 2.54%, but exhibits lower spectral efficiency and slightly higher outage, revealing a rate - energy - reliability trade -off. Overall, the proposed framework offers a practical balance among communication performance, energy use, and action-space complexity
Millimeter-wave (mmWave) communication systems are vulnerable to severe attenuation, blockage-induced LOS/NLOS transitions, and time-varying co-channel interference. This paper develops a lightweight distributed power-allocation framework in which each base station independently updates a tabular Q-learning policy using locally observable blockage-ratio, serving-distance, and aggregate-interference information. The proposed state-dependent dynamic reward is recalculated at every decision step, and its coefficients vary explicitly with the instantaneous blockage ratio, QoS satisfaction ratio, and normalized interference level. All learning-based and non-learning baselines are evaluated using the same topology realizations, blockage and mobility traces, and random seeds. Under the reconstructed simulation settings, the proposed method achieves performance comparable to fixed Q-learning while retaining a transparent blockage-aware state and low-complexity distributed implementation. DQN, greedy, and uniform power achieve higher raw capacity or QoS in the considered small-scale network. Results from 30 paired runs with 95% confidence intervals, together with ablation, sensitivity, beam-misalignment, and overhead analyses, clarify the empirical benefits, limitations, and deployment scope of the proposed method. The study focuses on power control after beam establishment; joint beam tracking and power allocation remain outside the present scope.
Zhuoning Yang, Ziwei Chen· Italian National Conference...· 0 citations
An adaptive multi-mode Deep Reinforcement Learning (DRL) framework for intelligent RIS-assisted anti-jamming communication in dynamic 6G wireless networks that maintains stable communication performance under strong jamming power, CSI uncertainty, and high-mobility scenarios is proposed.
Lê Hoàng Hiệp, Huu-Huy Ngo· Journal of Communications So...· 1 citation
Vehicle-to-everything (V2X) communication plays a crucial role in enabling connected and autonomous driving by supporting the reliable exchange of safety-critical information among vehicles and infrastructure. However, due to the open nature of wireless channels, V2X systems are vulnerable to various physical-layer attacks, among which jamming is one of the most intuitive and severe threats. In this paper, we propose a vehicle speed-aware jammer-resilient reception framework for multiuser multiple-input multiple-output (MIMO) V2X systems. The proposed method exploits the fundamental difference in Doppler characteristics between stationary jammers and moving vehicles. By transforming the received signal into the Doppler domain, the receiver identifies low-Doppler components associated with static interference and suppresses them through Doppler-domain filtering. Notably, the proposed approach does not require prior knowledge of the jammer channel or its spatial direction, making it suitable for practical V2X environments. Simulation results demonstrate that the proposed framework effectively mitigates strong jamming signals and significantly improves the achievable sum-rate compared with conventional receivers.
Hanyoung Park, Yongjae Jang, Ji-Woong Choi· International Conference on...· 0 citations
To achieve a full spatial coverage and higher spectral efficiency for the future sixth generation (6G) wireless networks, simultaneous transmission and reflection reconfigurable intelligent surfaces (STAR-RISs) has been proposed as a technology solution. The outage and diversity performance of STAR-RIS-assisted rate-splitting multiple access (RSMA) is investigated on Nakagami-m fading channels. RSMA systems dynamically control the interference by splitting the shared and private streams to improve the reliability of the transmission system under different channel conditions. The analytical frameworks are established for the composite STAR-RIS channels: central limit theorem model for the case of large number of elements, curve-fitting model for the moderate number of elements and M-Fold Convolution model for the case of high signal to noise ratio diversity assessment. The energy-splitting (ES), mode-switching (MS), and time-switching (TS) STAR-RIS protocols are studied and closed-form formulas for outage probability are derived for the three protocols. The results show that increasing the number of STAR-RIS elements from 20 to 40 significantly improves the outage performance, yielding several orders of magnitude reduction in outage probability due to enhanced beamforming gain and spatial diversity. In addition, the reduced order of the MS protocol is mMk due to partial allocation of elements, and the ES/TS protocol has a diversity order of mM. It is found that the OP of the reflecting user is less than 10−6 at approximately 115 dB for M = 40, which demonstrates the effectiveness of the STAR-RIS Assisted RSMA systems in improving the reliability, spatial diversity and interference management in the future 6G wireless communication systems.
Shahnaz Fatima, B. P. Chapa, Mahesh Babu Ammisetty et al.· Engineering Research Express· 0 citations
This paper investigates a blockage-aware anti-jamming strategy for UAV-assisted data harvesting in dense urban environments. Ground jammers (GJs) not only emit interference but also attempt to detect UAVs via line-of-sight (LoS) surveillance. To counter this, the UAV leverages urban building layouts to remain hidden from GJs and attenuate their jamming signals, while maintaining LoS connectivity with ground sensors (GSs) for secure and efficient data collection. To maximize the minimum average spectral efficiency among GSs, we jointly optimize the user scheduling and UAV trajectory based on a blockage-aware channel model that captures LoS/NLoS conditions induced by building layouts and relative node positions. This results in a challenging mixed-integer nonconvex problem due to binary scheduling variables, nonconvex trajectory constraints, and the use of sigmoid-approximated channel models. To tackle this, we decompose the original problem into two convex subproblems using successive convex approximation, quadratic transform, and geometry-based convexification techniques. An iterative block coordinate descent-based algorithm is then proposed, enabling efficient convergence with polynomial complexity. Simulation results confirm the superiority of the proposed scheme over baselines, particularly under severe jamming and building blockage conditions, demonstrating improved resilience and throughput in urban UAV networks.
A cross-layer end-to-end (E2E) resource orchestration framework for green CF-mMIMO ISAC systems with distributed multi-target detection is developed and a fundamental implementation trade-off is revealed: FIS provides lower detector-processing complexity and higher detection performance, whereas PIS substantially reduces fronthaul requirements.
Z. Behdad, Özlem Tuğfe Demir, Ki Won Sung et al.· 0 citations