arXiv subjects

Symeon Chatzinotas

Publications and source records attributed to Symeon Chatzinotas.

At least 91 records · Page 5Linked to original sources

arXiv2025

Multi-Agent Deep Reinforcement Learning for Collaborative UAV Relay Networks under Jamming Atatcks

The deployment of Unmanned Aerial Vehicle (UAV) swarms as dynamic communication relays is critical for next-generation tactical networks. However, operating in contested environments requires solving a complex trade-off, including maximizing system throughput while ensuring collision avoidance and resilience against adversarial jamming. Existing heuristic-based approaches often struggle to find effective solutions due to the dynamic and multi-objective nature of this problem. This paper formulates this challenge as a cooperative Multi-Agent Reinforcement Learning (MARL) problem, solved using the Centralized Training with Decentralized Execution (CTDE) framework. Our approach employs a centralized critic that uses global state information to guide decentralized actors which operate using only local observations. Simulation results show that our proposed framework significantly outperforms heuristic baselines, increasing the total system throughput by approximately 50% while simultaneously achieving a near-zero collision rate. A key finding is that the agents develop an emergent anti-jamming strategy without explicit programming. They learn to intelligently position themselves to balance the trade-off between mitigating interference from jammers and maintaining effective communication links with ground users.

cs.NI↗

arXiv2025

Deep Learning-Based Joint Uplink-Downlink CSI Acquisition for Next-Generation Upper Mid-Band Systems

In next-generation wireless communication systems, the newly designated upper mid-band has attracted considerable attention, also called frequency range 3 (FR3), highlighting the need for downlink (DL) transmission design, which fundamentally relies on accurate CSI. However, CSI acquisition in FR3 systems faces significant challenges: the increased number of antennas and wider transmission bandwidth introduces prohibitive training overhead with traditional estimation approaches, as each probing captures only incomplete spatial-frequency observation, while higher carrier frequencies lead to faster temporal channel variation. To address these challenges, we propose a novel CSI acquisition framework that integrates CSI feedback, uplink (UL) and DL channel estimation, as well as channel prediction in the FR3 TDD massive MIMO systems. Specifically, we first develop the Joint UL and DL Channel Estimation Network (JUDCEN) to fuse incomplete observations based on the SRSs and CSI-RSs. By exploiting the complementary characteristics of preliminary UL and DL estimation features, obtained through initial UL estimation and quantized-feedback-assisted DL estimation, it enables full CSI reconstruction in the spatial domain. To mitigate the performance degradation in the feedback process, we propose the Transformer-MLP CSI Feedback Network (TMCFN), employing an MLP-based module to jointly exploit angle- and delay-domain features. Building upon the reconstructed full CSI, we further develop the Mamba-based Channel Prediction Network (MCPN), which exploits selective state-space model (SSM) mechanism to capture long-range temporal dynamics in the angle-delay domain for future CSI prediction. Simulation results demonstrate that the proposed framework consistently outperforms benchmarks in both CSI acquisition accuracy and transmission spectral efficiency with lower computational complexity.

eess.SP↗

arXiv2025

Design and Optimization of Adaptive Diversity Schemes in Quantum MIMO Channels

As quantum networks evolve toward a full quantum Internet, reliable transmission in quantum multiple-input multiple-output (QuMIMO) settings becomes essential, yet remains difficult due to noise, crosstalk, and the mixing of quantum information across subchannels. To improve reliability in such settings, we study an adaptive diversity strategy for discrete-variable QuMIMO systems based on universal asymmetric cloning at the transmitter and probabilistic purification at the receiver. An input qubit is encoded into M approximate clones, transmitted over an N x N multi-mode quantum channel, and recovered through a purification map optimized using available channel state information (CSI). For the given cloning asymmetry parameters, we derive an eigenvalue-based expression for the decoder-optimal end-to-end fidelity in the form of a generalized Rayleigh quotient, which enables efficient tuning of the cloner without iterative optimization. As a design choice, we employ semidefinite program (SDP) to construct the purification map for only a targeted success probability p. This numerical framework is used to study fixed-noise, dimension-scaling noise, and stochastic depolarization regimes. A cloning asymmetry index is introduced to quantify the distribution of quantum information across the multiple subchannels across these operating conditions. The results show that the proposed scheme yields significant fidelity gains in crosstalk-dominated settings and automatically adapts to channel symmetry and channel conditions. This work provides design guidelines for future QuMIMO systems and establishes a robust baseline for more advanced transmission and decoding strategies.

quant-ph↗

arXiv2025

Fairness Designs for Load Balancing Optimization in Satellite-Cell-Free Massive MIMO Systems

Space-ground communication systems are important in providing ubiquitous services in a large area. This paper considers the fairness designs under a load-balancing framework with heterogeneous receivers comprising access points (APs) and a satellite. We derive an ergodic throughput of each user in the uplink data transmission for an arbitrary association pattern and imperfect channel state information, followed by a closed-form expression with the maximum-ratio combining and rich scattering environments. We further formulate a generic fairness optimization problem, subject to the optimal association patterns for all the users. Despite the combinatorial structure, the global optimal solution to the association patterns can be obtained by an exhaustive search for small-scale networks with several APs and users. We design a low computational complexity algorithm for large-scale networks based on evolutionary computation that obtains good patterns in polynomial time. Specifically, the genetic algorithm (GA) is adapted to the discrete feasible region and the concrete fairness metrics. We extensively observe the fairness design problem by incorporating transmit power control and propose a hybrid genetic algorithm to address the problem. Numerical results demonstrate that the association pattern to each user has a significant impact on the network throughput. Moreover, the proposed GA-based algorithm offers the same performance as an exhaustive search for small-scale networks, while it unveils interesting practical association patterns as the network dimensions go large. The load-balancing approach, combined with power control factors, significantly enhances system performance compared to conventional schemes and configurations with fixed factors.

cs.IT↗

arXiv2025

Quantum Reinforcement Learning for 6G and Beyond Wireless Networks

While 5G is being deployed worldwide, 6G is receiving increasing attention from researchers to meet the growing demand for higher data rates, lower latency, higher density, and seamless communications worldwide. To meet the stringent requirements of 6G wireless communications networks, AI-integrated communications have become an indispensable part of supporting 6G systems with intelligence, automation, and big data training capabilities. However, traditional artificial intelligence (AI) systems are difficult to meet the stringent latency and high throughput requirements of 6G with limited resources. In this article, we summarize, analyze, discuss the potential, and benefits of Quantum Reinforcement Learning (QRL) in 6G. As an example, we show the superiority of QRL in dynamic spectrum access compared to the conventional Deep Reinforcement Learning (DRL) approach. In addition, we provide an overview of what DRL has accomplished in 6G and its challenges and limitations. From there, we introduce QRL and potential research directions that should continue to be of interest in 6G. To the best of our knowledge, this is the first review and vision article on QRL for 6G wireless communication networks.

cs.NI↗

arXiv2025

Asynchronous Risk-Aware Multi-Agent Packet Routing for Ultra-Dense LEO Satellite Networks

The rise of ultra-dense LEO constellations creates a complex and asynchronous network environment, driven by their massive scale, dynamic topologies, and significant delays. This unique complexity demands an adaptive packet routing algorithm that is asynchronous, risk-aware, and capable of balancing diverse and often conflicting QoS objectives in a decentralized manner. However, existing methods fail to address this need, as they typically rely on impractical synchronous decision-making and/or risk-oblivious approaches. To tackle this gap, we introduce PRIMAL, an event-driven multi-agent routing framework designed specifically to allow each satellite to act independently on its own event-driven timeline, while managing the risk of worst-case performance degradation via a principled primal-dual approach. This is achieved by enabling agents to learn the full cost distribution of the targeted QoS objectives and constrain tail-end risks. Extensive simulations on a LEO constellation with 1584 satellites validate its superiority in effectively optimizing latency and balancing load. Compared to a recent risk-oblivious baseline, it reduces queuing delay by over 70%, and achieves a nearly 12 ms end-to-end delay reduction in loaded scenarios. This is accomplished by resolving the core conflict between naive shortest-path finding and congestion avoidance, highlighting such autonomous risk-awareness as a key to robust routing.

cs.NI↗

arXiv2025

Towards Quantum Enhanced Adversarial Robustness with Rydberg Reservoir Learning

Quantum reservoir computing (QRC) leverages the high-dimensional, nonlinear dynamics inherent in quantum many-body systems for extracting spatiotemporal patterns in sequential and time-series data with minimal training overhead. Although QRC inherits the expressive capabilities associated with quantum encodings, recent studies indicate that quantum classifiers based on variational circuits remain susceptible to adversarial perturbations. In this perspective, we investigate the first systematic evaluation of adversarial robustness in a QRC based learning model. Our reservoir comprises an array of strongly interacting Rydberg atoms governed by a fixed Hamiltonian, which naturally evolves under complex quantum dynamics, producing high-dimensional embeddings. A lightweight multilayer perceptron serves as the trainable readout layer. We utilize the balanced datasets, namely MNIST, Fashion-MNIST, and Kuzushiji-MNIST, as a benchmark for rigorously evaluating the impact of augmenting the quantum reservoir with a Multilayer perceptron (MLP) in white-box adversarial attacks to assess its robustness. We demonstrate that this approach yields significantly higher accuracy than purely classical models across all perturbation strengths tested. This hybrid approach reveals a new source of quantum advantage and provides practical guidance for the secure deployment of machine learning models on quantum-centric supercomputing with near-term hardware.

quant-ph↗

arXiv2025

Robust Beamforming Optimization for STAR-RIS Empowered Multi-User RSMA Under Hardware Imperfections and Channel Uncertainty

This study explores the synergy between rate-splitting multiple access (RSMA) and simultaneous transmitting and reflecting reconfigurable intelligent surface (STAR-RIS) as a unified framework to enable ubiquitous, intelligent, and resilient connectivity in future sixth-generation networks, while improving spectral and energy efficiency. Specifically, we investigate a STAR-RIS-assisted multi-user RSMA system and develop an intelligent optimization strategy that jointly designs the transmitter's active beamforming, the common stream rate allocation, and the passive beamforming vectors for the STAR-RIS transmission and reflection regions, considering transceiver hardware impairments and imperfect channel state information (CSI). In addition, system robustness is ensured via a bounded channel estimation error model that captures CSI imperfections and guarantees resilience against worst-case errors. To address the highly non-convex problem, we propose an iterative optimization algorithm that decomposes it into two sub-problems. Firstly, active beamforming vectors for the common and private signals are determined by reformulating the original problem into a convex semi-definite programming (SDP) form using successive convex approximation (SCA) and semi-definite relaxation (SDR). Secondly, passive beamforming vectors are optimized through a convex SDP reformulation by exploiting SCA and SDR techniques. Moreover, when higher-rank solutions arise, Gaussian randomization is applied to obtain rank-one solutions. Numerical simulations demonstrate that the proposed strategy achieves significant performance gains over benchmark schemes and exhibits fast convergence.

eess.SP↗

arXiv2025

When 5G NTN Meets GNSS: Tracking GNSS Signals under Overlaid 5G Waveforms

Global Navigation Satellite Systems (GNSS) provide the backbone of Positioning, Navigation, and Timing (PNT) but remain vulnerable to interference. Low Earth Orbit (LEO) constellations within Fifth-Generation (5G) Non-Terrestrial Networks (NTN) can enhance resilience by jointly supporting communication and navigation. This paper presents the first quantitative analysis of GNSS tracking and navigation message demodulation under a hybrid waveform where a low-power Direct-Sequence Spread Spectrum (DSSS) component is overlaid on an Orthogonal Frequency-Division Multiplexing (OFDM) 5G downlink. We evaluate a minimally modified GNSS receiver that tracks a legacy Global Positioning System (GPS) L1 Coarse/Acquisition (C/A) overlay aligned with 5G frames while treating the 5G waveform as structured interference. Using Monte Carlo simulations under realistic LEO Doppler dynamics, we analyze the Bit Error Rate (BER) of GPS L1 C/A navigation bits and the subframe decoding probability versus Signalto- Interference-plus-Noise Ratio (SINR) for multiple Signalto- Interference Ratios (SIR) and dynamic classes. Results show reliable demodulation across wide SINR ranges for low and medium dynamics, whereas high dynamics impose strict lock limits. These findings confirm the feasibility of Joint Communication and Positioning (JCAP) using a near-legacy GNSS chipset with minimal receiver modifications.

eess.SP↗

arXiv2025

Quantum Reinforcement Learning: Recent Advances and Future Directions

As quantum machine learning continues to evolve, reinforcement learning stands out as a particularly promising yet underexplored frontier. In this survey, we investigate the recent advances in QRL to assess its potential in various applications. While QRL has generally received less attention than other quantum machine learning approaches, recent research reveals its distinct advantages and transversal applicability in both quantum and classical domains. We present a comprehensive analysis of the QRL framework, including its algorithms, architectures, and supporting SDK, as well as its applications in diverse fields. Additionally, we discuss the challenges and opportunities that QRL can unfold, highlighting promising use cases that may drive innovation in quantum-inspired reinforcement learning and catalyze its adoption in various interdisciplinary contexts.

quant-ph↗

arXiv2025

SmartUT: Receive Beamforming for Spectral Coexistence of NGSO Satellite Systems

In this paper, we investigate downlink co-frequency interference (CFI) mitigation in non-geostationary satellites orbits (NGSOs) co-existing systems. Traditional mitigation techniques, such as Zero-forcing (ZF), produce a null towards the direction of arrivals (DOAs) of the interfering signals, but they suffer from high computational complexity due to matrix inversions and required knowledge of the channel state information (CSI). Furthermore, adaptive beamformers, such as sample matrix inversion (SMI)-based minimum variance, provide poor performance when the available snapshots are limited. We propose a Mamba-based beamformer (MambaBF) that leverages an unsupervised deep learning (DL) approach and can be deployed on the user terminal (UT) antenna array, for assisting downlink beamforming and CFI mitigation using only a limited number of available array snapshots as input, and without CSI knowledge. Simulation results demonstrate that MambaBF consistently outperforms conventional beamforming techniques in mitigating interference and maximizing the signal-to-interference-plus-noise ratio (SINR), particularly under challenging conditions characterized by low SINR, limited snapshots, and imperfect CSI.

eess.SP↗

arXiv2025

Multilayer Non-Terrestrial Networks with Spectrum Access aided by Beyond-Diagonal RIS

In this work, we study a multi-user NTN in which a satellite serves as the primary network and a high-altitude platform station (HAPS) operates as the secondary network, acting as a cognitive radio. To reduce the cost, complexity, and power consumption of conventional antenna arrays, we equip the HAPS with a transmissive BD-RIS antenna front end. We then formulate a joint optimization problem for the BD-RIS phase response and the HAPS transmit power allocation under strict per-user interference temperature constraints. To tackle the resulting highly nonconvex problem, we propose an alternating-optimization framework: the power-allocation subproblem admits a closed-form, water-filling-type solution derived from the Karush-Kuhn-Tucker (KKT) conditions, while the BD-RIS configuration is refined via Riemannian manifold optimization. Simulation results show significant gains in data rate and interference suppression over diagonal RIS-assisted benchmarks, establishing BD-RIS as a promising enabler for future multilayer NTNs.

eess.SP↗

arXiv2025

Unlocking Symbol-Level Precoding Efficiency Through Tensor Equivariant Neural Network

Although symbol-level precoding (SLP) based on constructive interference (CI) exploitation offers performance gains, its high complexity remains a bottleneck. This paper addresses this challenge with an end-to-end deep learning (DL) framework with low inference complexity that leverages the structure of the optimal SLP solution in the closed-form and its inherent tensor equivariance (TE), where TE denotes that a permutation of the input induces the corresponding permutation of the output. Building upon the computationally efficient model-based formulations, as well as their known closed-form solutions, we analyze their relationship with linear precoding (LP) and investigate the corresponding optimality condition. We then construct a mapping from the problem formulation to the solution and prove its TE, based on which the designed networks reveal a specific parameter-sharing pattern that delivers low computational complexity and strong generalization. Leveraging these, we propose the backbone of the framework with an attention-based TE module, achieving linear computational complexity. Furthermore, we demonstrate that such a framework is also applicable to imperfect CSI scenarios, where we design a TE-based network to map the CSI, statistics, and symbols to auxiliary variables. Simulation results show that the proposed framework captures substantial performance gains of optimal SLP, while achieving an approximately 80-times speedup over conventional methods and maintaining strong generalization across user numbers and symbol block lengths.

eess.SP↗

arXiv2025

Joint Communications, Sensing, and Positioning in 6G Multi-Functional Satellite Systems: Survey and Open Challenges

Satellite systems are expected to be a cornerstone of sixth-generation (6G) networks, providing ubiquitous coverage and supporting a wide range of services across communications, sensing, and positioning, navigation, and timing (PNT). Meeting these demands with current function-specific payload architectures is challenging in terms of cost, spectral use, and sustainability. This survey introduces the framework of multi-functional satellite systems (MFSS), which integrate two or more of these core services into a single payload, enabling resource sharing and functional synergy. A unified taxonomy is proposed, covering joint communications and sensing (JCAS), joint communications and PNT (JCAP), joint sensing and PNT (JSAP), and fully integrated joint communications, sensing, and PNT (JCSAP) systems. The paper reviews the state-of-the-art in each domain, examines existing payload architectures, and outlines cooperative, integrated, and joint design strategies. Key challenges, including waveform co-design, synchronization, interference mitigation, and resource management, are discussed, along with potential solutions and future research directions. By unifying diverse satellite capabilities within a single platform, MFSS can achieve higher spectral efficiency, reduced launch mass and cost, improved energy use, and enhanced service versatility, contributing to the development of sustainable and intelligent non-terrestrial networks (NTNs) for the 6G and beyond space era.

eess.SP↗

arXiv2025

From Legacy to Leadership Intelligent Radio Network Planning Framework for Cell-Free Massive MIMO in B5G6G Era

The proliferation of cell-free Massive MIMO represents a transformative shift in wireless network architecture, addressing critical limitations of conventional distributed Massive MIMO systems. This paper presents an intelligent radio network planning framework that bridges legacy 5G infrastructures with future B5G/6G networks through cell-free architectures. By leveraging operational insights from existing 5G deployments, we systematically address coverage optimization, and capacity enhancement. Our scalable framework enables seamless evolution from legacy designs to next-generation cell-free systems. Through extensive simulations in dense urban environments, we demonstrate substantial improvements: 45% spectral efficiency gains, 30% interference reduction, and significantly enhanced uniform coverage. The proposed framework provides network operators with a practical roadmap for transitioning from traditional cellular architectures to demanding B5G/6G requirements while maximizing existing infrastructure investments.

eess.SY↗

arXiv2025

Joint Communications and Sensing for 6G Satellite Networks: Use Cases and Challenges

Satellite networks (SN) have long provided two fundamental services: global communications and Earth-oriented sensing, supporting applications from connectivity and navigation to disaster management and environmental monitoring. Yet, the accelerating demand for data and the emergence of new applications render the independent evolution of communication and sensing payloads increasingly unsustainable. Joint communications and sensing (JCAS) has emerged as a transformative paradigm, integrating both functions within a unified payload to enhance spectral efficiency, reduce operational costs, and minimize hardware redundancy. Beyond efficiency, this integration creates opportunities for novel services that are infeasible under separate payload designs. This paper motivates the role of JCAS in shaping the sixth-generation (6G) of satellite networks, explores a representative use case to assess its feasibility, and discusses key challenges that must be addressed to unlock its full potential. By highlighting these opportunities inherent to the space environment, we aim to stimulate the development of JCAS as a cornerstone technology for the next-generation space era

eess.SP↗

arXiv2025

Secure Short-Packet Communications for RIS-Assisted AAV Networks

Advancements toward 6G have intensified demands for ultra-reliable low-latency communication, positioning shortpacket communications as a critical technology for autonomous aerial vehicle (AAV) networks. However, the open broadcast nature introduces significant security vulnerabilities. Although physical-layer security offers a low-complexity solution by exploiting wireless channel randomness, the AAV communication performance severely degrades in weak-coverage or non-line-of sight scenarios. To overcome these limitations, this paper proposes a short-packet communications framework for AAV networks that leverages reconfigurable intelligent surfaces (RIS) with the aim of extending coverage and enhancing secrecy capabilities. Analytical frameworks are developed to evaluate the average secrecy throughput (AST) in finite blocklength constraints for both external and internal avesdropping scenarios, which incorporates non-orthogonal multiple access with imperfect successive interference cancellation. Asymptotic approximations of AST are derived as transmit power approaches infinity. Furthermore, we formulate a blocklength optimization problem to maximize the AST, effectively resolving the trade-offs among delay, reliability, and secrecy. Extensive simulations validate the analytical frameworks, which reveal that large-scale RIS deployment significantly boosts AST, and the power allocation coefficient exhibits dual effects in the internal eavesdropping scenario. These observations provide useful insights for designing reliable and secure lowlatency AAV communications systems.

eess.SY↗

arXiv2025

Energy Efficiency for Massive MIMO Integrated Sensing and Communication Systems

This paper explores the energy efficiency (EE) of integrated sensing and communication (ISAC) systems employing massive multiple-input multiple-output (mMIMO) techniques to leverage spatial beamforming gains for both communication and sensing. We focus on an mMIMO-ISAC system operating in an orthogonal frequency-division multiplexing setting with a uniform planar array, zero-forcing downlink transmission, and mono-static radar sensing to exploit multi-carrier channel diversity. By deriving closed-form expressions for the achievable communication rate and Cramér-Rao bounds (CRBs), we are able to determine the overall EE in closed-form. A power allocation problem is then formulated to maximize the system's EE by balancing communication and sensing efficiency while satisfying communication rate requirements and CRB constraints. Through a detailed analysis of CRB properties, we reformulate the problem into a more manageable form and leverage Dinkelbach's and successive convex approximation (SCA) techniques to develop an efficient iterative algorithm. A novel initialization strategy is also proposed to ensure high-quality feasible starting points for the iterative optimization process. Extensive simulations demonstrate the significant performance improvement of the proposed approach over baseline approaches. Results further reveal that as communication spectral efficiency rises, the influence of sensing EE on the overall system EE becomes more pronounced, even in sensing-dominated scenarios. Specifically, in the high $ω$ regime of $2 \times 10^{-3}$, we observe a 16.7\% reduction in overall EE when spectral efficiency increases from $4$ to $8$ bps/Hz, despite the system being sensing-dominated.

cs.IT↗