Advancements in 6G wireless technology have elevated the importance of beamforming, especially for attaining ultra-high data rates via millimeter-wave (mmWave) frequency deployment. Although promising, mmWave bands require substantial beam training to achieve precise beamforming. While initial deep learning models that use RGB camera images demonstrated promise in reducing beam training overhead, their performance suffers due to sensitivity to lighting and environmental variations. Due to this sensitivity, Quality of Service (QoS) fluctuates, eventually affecting the stability and dependability of networks in dynamic environments. This emphasizes a critical need for more robust solutions. This paper proposes a robust beamforming technique to ensure consistent QoS under varying environmental conditions. An optimization problem has been formulated to maximize users' data rates. To solve the formulated NP-hard optimization problem, we decompose it into two subproblems: the semantic localization problem and the optimal beam selection problem. To solve the semantic localization problem, we propose a novel method that leverages the k-means clustering and YOLOv8 model. To solve the beam selection problem, we propose a novel lightweight hybrid architecture that utilizes various data sources and a weighted entropy-based mechanism to predict the optimal beams. Rapid and accurate beam predictions are needed to maintain QoS. A novel metric, Accuracy-Complexity Efficiency (ACE), has been proposed to quantify this. Six testing scenarios have been developed to evaluate the robustness of the proposed model. Finally, the simulation result demonstrates that the proposed model outperforms several state-of-the-art baselines regarding beam prediction accuracy, received power, and ACE in the developed test scenarios.
相關內容
The simulation of electromagnetic devices with complex geometries and large-scale discrete systems benefits from advanced computational methods like IsoGeometric Analysis and Domain Decomposition. In this paper, we employ both concepts in an Isogeometric Tearing and Interconnecting method to enable the use of parallel computations for magnetostatic problems. We address the underlying non-uniqueness by using a graph-theoretic approach, the tree-cotree decomposition. The classical tree-cotree gauging is adapted to be feasible for parallelization, which requires that all local subsystems are uniquely solvable. Our contribution consists of an explicit algorithm for constructing compatible trees and combining it with a dual-primal approach to enable parallelization. The correctness of the proposed approach is proved and verified by numerical experiments, showing its accuracy, scalability and optimal convergence.
The landscape of wireless communication systems is evolving rapidly, with a pivotal role envisioned for dynamic network structures and self-organizing networks in upcoming technologies like the 6G mobile communications standard. This evolution is fueled by the growing demand from diverse sectors, including industry, manufacturing, agriculture, and the public sector, each with increasingly specific requirements. The establishment of non-public networks in the current 5G standard has laid a foundation, enabling independent operation within certain frequencies and local limitations, notably for Internet of Things applications. This paper explores the progression from non-public networks to nomadic non-public networks and their significance in the context of the forthcoming 6G era. Building on existing work in dynamic network structures, non-public networks regulations, and alternative technological solutions, this paper introduces specific use cases enhanced by nomadic networks. In addition, relevant Key Performance Indicators are discussed on the basis of the presented use cases. These serve as a starting point for the definition of requirement clusters and thus for a evaluation metric of nomadic non-public networks. This work lays the groundwork for understanding the potential of nomadic non-public networks in the dynamic landscape of 6G wireless communication systems.
The surge in Internet of Things (IoT) devices and data generation highlights the limitations of traditional cloud computing in meeting demands for immediacy, Quality of Service, and location-aware services. Fog computing emerges as a solution, bringing computation, storage, and networking closer to data sources. This study explores the role of Deep Reinforcement Learning in enhancing fog computing's task offloading, aiming for operational efficiency and robust security. By reviewing current strategies and proposing future research directions, the paper shows the potential of Deep Reinforcement Learning in optimizing resource use, speeding up responses, and securing against vulnerabilities. It suggests advancing Deep Reinforcement Learning for fog computing, exploring blockchain for better security, and seeking energy-efficient models to improve the Internet of Things ecosystem. Incorporating artificial intelligence, our results indicate potential improvements in key metrics, such as task completion time, energy consumption, and security incident reduction. These findings provide a concrete foundation for future research and practical applications in optimizing fog computing architectures.
Transmit power control, as in the mobile wireless channels, can enable a robust and spectrally efficient communication through atmospheric turbulence in terrestrial free-space optical (FSO) channels. With optical bandwidths in excess of several GHz and eye safety regulations limiting the transmit optical power, the per hertz signal-to-noise ratio (SNR) in terrestrial FSO systems can possibly become limited, especially true for future high-bandwidth and long-haul applications. Hence, power control becomes significant in terrestrial FSO systems. However, a comprehensive study of dynamic power adaptation in the existing FSO systems is lacking in the literature. In this paper, we investigate FSO communication systems capable of beam power control with heterodyne detection and direct detection based receivers operating under shot noise-limited conditions. Under these considerations, we derive unified exact and asymptotic capacity formulas for the Gamma-Gamma turbulence channels with and without pointing errors; these novel closed-form capacity expressions provide new insights into the impact of varying turbulence conditions and pointing errors. Further, the numerical results highlight the intricate relations of atmospheric turbulence and pointing error parameters in typical terrestrial FSO channel setting. A concrete assessment of the impact of the key channel parameters on the capacity performances of the aforementioned FSO systems is performed revealing several novel and interesting insights.
In the rapidly evolving landscape of wireless networks, achieving enhanced throughput with low latency for data transmission is crucial for future communication systems. While low complexity OSPF-type solutions have shown effectiveness in lightly-loaded networks, they often falter in the face of increasing congestion. Recent approaches have suggested utilizing backpressure and deep learning techniques for route optimization. However, these approaches face challenges due to their high implementation and computational complexity, surpassing the capabilities of networks with limited hardware devices. A key challenge is developing algorithms that improve throughput and reduce latency while keeping complexity levels compatible with OSPF. In this collaborative research between Ben-Gurion University and Ceragon Networks Ltd., we address this challenge by developing a novel approach, dubbed Regularized Routing Optimization (RRO). The RRO algorithm offers both distributed and centralized implementations with low complexity, making it suitable for integration into 5G and beyond technologies, where no significant changes to the existing protocols are needed. It increases throughput while ensuring latency remains sufficiently low through regularized optimization. We analyze the computational complexity of RRO and prove that it converges with a level of complexity comparable to OSPF. Extensive simulation results across diverse network topologies demonstrate that RRO significantly outperforms existing methods.
State-of-the-art LLMs often rely on scale with high computational costs, which has sparked a research agenda to reduce parameter counts and costs without significantly impacting performance. Our study focuses on Transformer-based LLMs, specifically applying low-rank parametrization to the computationally intensive feedforward networks (FFNs), which are less studied than attention blocks. In contrast to previous works, (i) we explore low-rank parametrization at scale, up to 1.3B parameters; (ii) within Transformer language models rather than convolutional architectures; and (iii) starting from training from scratch. Experiments on the large RefinedWeb dataset show that low-rank parametrization is both efficient (e.g., 2.6$\times$ FFN speed-up with 32\% parameters) and effective during training. Interestingly, these structured FFNs exhibit steeper scaling curves than the original models. Motivated by this finding, we develop the wide and structured networks surpassing the current medium-sized and large-sized Transformer in perplexity and throughput performance. Our code is available at //github.com/CLAIRE-Labo/StructuredFFN/tree/main.
Extremely large-scale antenna arrays (ELAA) play a critical role in enabling the functionalities of next generation wireless communication systems. However, as the number of antennas increases, ELAA systems face significant bottlenecks, such as excessive interconnection costs and high computational complexity. Efficient distributed signal processing (SP) algorithms show great promise in overcoming these challenges. In this paper, we provide a comprehensive overview of distributed SP algorithms for ELAA systems, tailored to address these bottlenecks. We start by presenting three representative forms of ELAA systems: single-base station ELAA systems, coordinated distributed antenna systems, and ELAA systems integrated with emerging technologies. For each form, we review the associated distributed SP algorithms in the literature. Additionally, we outline several important future research directions that are essential for improving the performance and practicality of ELAA systems.
Digital Twins (DTs) are set to become a key enabling technology in future wireless networks, with their use in network management increasing significantly. We developed a DT framework that leverages the heterogeneity of network access technologies as a resource for enhanced network performance and management, enabling smart data handling in the physical network. Tested in a \textit{Campus Area Network} environment, our framework integrates diverse data sources to provide real-time, holistic insights into network performance and environmental sensing. We also envision that traditional analytics will evolve to rely on emerging AI models, such as Generative AI (GenAI), while leveraging current analytics capabilities. This capacity can simplify analytics processes through advanced ML models, enabling descriptive, diagnostic, predictive, and prescriptive analytics in a unified fashion. Finally, we present specific research opportunities concerning interoperability aspects and envision aligning advancements in DT technology with evolved AI integration.
Movable antennas (MAs), traditionally explored in antenna design, have recently garnered significant attention in wireless communications due to their ability to dynamically adjust the antenna positions to changes in the propagation environment. However, previous research has primarily focused on characterizing the performance limits of various MA-assisted wireless communication systems, with less emphasis on their practical implementation. To address this gap, in this article, we propose several general MA architectures that extend existing designs by varying several key aspects to cater to different application scenarios and tradeoffs between cost and performance. Additionally, we draw from fields such as antenna design and mechanical control to provide an overview of candidate implementation methods for the proposed MA architectures, utilizing either direct mechanical or equivalent electronic control. Simulation results are finally presented to support our discussion.
Face recognition technology has advanced significantly in recent years due largely to the availability of large and increasingly complex training datasets for use in deep learning models. These datasets, however, typically comprise images scraped from news sites or social media platforms and, therefore, have limited utility in more advanced security, forensics, and military applications. These applications require lower resolution, longer ranges, and elevated viewpoints. To meet these critical needs, we collected and curated the first and second subsets of a large multi-modal biometric dataset designed for use in the research and development (R&D) of biometric recognition technologies under extremely challenging conditions. Thus far, the dataset includes more than 350,000 still images and over 1,300 hours of video footage of approximately 1,000 subjects. To collect this data, we used Nikon DSLR cameras, a variety of commercial surveillance cameras, specialized long-rage R&D cameras, and Group 1 and Group 2 UAV platforms. The goal is to support the development of algorithms capable of accurately recognizing people at ranges up to 1,000 m and from high angles of elevation. These advances will include improvements to the state of the art in face recognition and will support new research in the area of whole-body recognition using methods based on gait and anthropometry. This paper describes methods used to collect and curate the dataset, and the dataset's characteristics at the current stage.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191