Maher Guizani

6G non-terrestrial networks (NTNs) will strengthen global Earth observation (EO) by linking low Earth orbit (LEO) satellite constellations, high altitude platforms (HAPs), and unmanned aerial vehicles (UAVs). However, long paths, intermittent links, and tight spectrum make traditional bit-centric pipelines brittle and bandwidth-heavy. Traditional semantic communication (SC) approaches also fall short because they rely on a single-source processing and degrade severely under low signal-to-noise ratio (SNR), multi-hop, and noisy orbital conditions. Therefore, we present a unified multi-source SC with an intelligent denoising framework that transmits meaning rather than raw symbols, fuses complementary features from multiple satellites, and restores semantics in the presence of noise. We first discuss the fundamentals of the unified multi-source SC with an intelligent denoising framework. Then, we explain our proposed framework in detail. Our framework couples the multi-hop inter-satellite delivery of compact semantic features with transformer-based denoising to maintain fidelity at low SNR and receiver-side image merging and large language model (LLM)-assisted semantic refinement to assemble overlapping segments into a coherent EO product aligned with a shared knowledge base. As a proof of concept, we present a case study on EO image delivery over LEO satellite, which shows improved robustness and bandwidth efficiency relative to conventional SC without denoising and traditional communications, with higher peak SNR (PSNR) and multi-scale structural similarity index (MS-SSIM), and reduced loss across SNR regimes. Finally, we provide several open challenges and conclude the paper.

Accurate mobile network traffic prediction is crucial for transit infrastructure service optimization in industrial informatization. Traditional linear models fail to capture complex non-linear dynamics, while existing deep learning methods struggle with rapid temporal changes, signal fluctuations, and diverse network conditions, limiting real-time applicability. To address these challenges, this paper proposes a hybrid model integrating Convolutional Neural Networks (CNNs) and Transformers, tailored for High-Speed Railway (HSR) environments. The proposed hybrid model is evaluated using both public datasets and a real-world HSR dataset collected through empirical field measurements, it not only achieves state-of-the-art (SOTA) predictive accuracy, reducing root mean square error by 4.7% over strong baselines in the challenging HSR environment, but also delivers this performance with superior computational efficiency, achieving over 3.6 times lower inference latency than leading SOTA models. This establishes an optimal performance-to-cost ratio, demonstrating its practical value for real-time HSR systems.

The rapid advancement of wireless networks has resulted in numerous challenges stemming from their extensive demands for quality of service towards innovative quality of experience metrics (e.g., user-defined metrics in terms of sense of physical experience for haptics applications). In the meantime, large language models (LLMs) emerged as promising solutions for many difficult and complex applications/tasks. These lead to a notion of the integration of LLMs and wireless networks. However, this integration is challenging and needs careful attention in design. Therefore, in this article, we present a notion of rational wireless networks powered by telecom LLMs, namely, LLM-native wireless systems. We provide fundamentals, a vision, and a case study of a distributed implementation of LLM-native wireless systems. In the case study, we propose a solution based on double deep Q-learning (DDQN) that outperforms existing DDQN solutions. Finally, we provide open challenges.

A metaverse can bring many benefits (i.e., self-sustaining and proactive analytics (e.g., analysis before user requests)) to wireless applications; however, its deployment is very challenging due to simultaneous quality of service (QoS) and quality of physical experience (QoE) constraints. Furthermore, the computing and communication resources of end-nodes are limited. Therefore, this paper proposes a novel task offloading framework for metaverse-empowered wireless systems. Our formulated problem aims at minimizing the cost of task offloading in the metaverse while considering both QoS and QoE constraints by optimizing the task offloading, resource allocation, and transmit power allocation variables. To optimize the formulated problem, we use a decomposition-based scheme that further uses modified block-successive upper-bound minimization (BSUM), convex optimization, and multi-agent reinforcement learning (MARL) for transmit power allocation, resource allocation, and task offloading, respectively. Our solution of using convex optimization-assisted MARL for joint resource allocation and task offloading significantly improves the performance of learning in terms of reward. Furthermore, BSUM significantly improves transmit power allocation when used in conjunction with a convex optimizer and MARL. Other than that, we also use dueling to further improve the performance of MARL. Our analyses show that convex optimization, BSUM, and dueling help in significantly improving the performance of MARL. Compared to traditional MARL, our proposal results in significant improvement in terms of reward and cost, as illustrated by the results.

Digital twin (DT) and mobile edge computing (MEC) are two promising solutions for achieving latency-sensitive and computing-intensive applications in Industrial Internet of Things (IIoT). However, existing collaborative task offloading schemes with DT empowerment are faced with challenges, such as the complex collaborative relationship between tasks and multiple edge servers (ESs), and spatio-temporal heterogeneity of ES resources. This article investigates the issues of parallel collaborative offloading and resource allocation under the assistance of the DT and overlapping coalition formation (OCF) game. One novel scheme, abbreviated as OCF-based PCORA, is proposed. With comprehensive information within the digital space, the OCF-based PCORA scheme dynamically models collaborative relationships between tasks and ESs. Subsequently, each task is offloaded to its optimal ES coalition for efficient collaborative processing. The offloading request is formulated as a nonconvex problem. To make the nonconvex problem solvable in polynomial time, the original problem is decomposed into three subproblems: ED association, bandwidth allocation, and collaborative task processing. The first subproblem is transformed through slack variable relaxation and solved using the interior-point method. The second subproblem, being naturally convex, is addressed via a convex optimization method. The third subproblem is modeled as an OCF game with transferable utility. On top of this, a bilevel iterative optimization algorithm is proposed to form overlapping task coalitions in a distributed manner. Numerical results demonstrate that the proposed scheme reduces the average task completion latency by 16.01%–44.97% and decreases the task offloading failure rate by 28.99%–75.41%, compared to state-of-the-art baselines.

The complexity of modern network resource management has significantly increased due to the proliferation of IoT devices and the demand for differentiated quality of service (QoS) for user tasks. Cloud-centric service delivery models encounter challenges related to latency and scalability. The integration of software-defined networking and edge computing technologies offers a new paradigm for task processing in networks, leveraging computing power close to the data source to address these issues. However, edge servers often have limited resources, and the diverse QoS requirements of users complicate the achievement of a load-balanced state. To overcome these limitations, this paper explores service demand uncertainty and virtual network embedding (VNE) algorithms to maximize the utilization of physical infrastructure. We present a service demand-based resource allocation framework that effectively performs task allocation in scenarios characterized by demand uncertainty. Additionally, we introduce a task-driven VNE algorithm that optimizes a multi-task resource scheduling scheme using a multi-layer policy network. Experimental results demonstrate that our approach reduces resource consumption by an average of 11.24% compared to other algorithms.

The rapid expansion of vehicular networks has intensified congestion and privacy risks. Although Federated Learning (FL) addresses both challenges through decentralized model training while preserving data locality, existing FL-based client selection strategies often fall short in highly heterogeneous vehicular environments. Specifically, the inherent heterogeneity in vehicular networks—characterized by diverse data distributions and system resources—complicates current methods. The imbalanced nature of local data further exacerbates model divergence, resulting in degraded overall system performance. To solve the above problems, in the process of vehicle selection, this paper comprehensively considers three kinds of heterogeneity and proposes an FL model with adaptive proximal term. The weight coefficient of this model is dynamically adjusted based on the difference between the local and global model parameters. Based on this, a contribution score-based vehicle selection strategy (CSVS), considering the dynamics of vehicles, is proposed to alleviate the problem of traditional model weight divergence and minimize system cost. Experimental results on two classic datasets demonstrate that the proposed strategy significantly outperforms baseline methods in reducing system cost and improving model training performance, particularly in highly heterogeneous vehicular environments.