Intelligent Reflecting Surface-Aided Wireless Communications: A Tutorial

IEEE Transactions on Communications, Journal Year: 2021, Volume and Issue: 69(5), P. 3313 - 3351

Published: Feb. 25, 2021

Intelligent reflecting surface (IRS) is an enabling technology to engineer the radio signal propagation in wireless networks. By smartly tuning reflection via a large number of low-cost passive elements, IRS capable dynamically altering channels enhance communication performance. It thus expected that new IRS-aided hybrid network comprising both active and components will be highly promising achieve sustainable capacity growth cost-effectively future. Despite its great potential, faces challenges efficiently integrated into networks, such as optimization, channel estimation, deployment from design perspectives. In this paper, we provide tutorial overview communications address above issues, elaborate models, hardware architecture practical constraints, well various appealing applications Moreover, highlight important directions worthy further investigation future work.

Language: Английский

---

Federated Learning in Mobile Edge Networks: A Comprehensive Survey

IEEE Communications Surveys & Tutorials, Journal Year: 2020, Volume and Issue: 22(3), P. 2031 - 2063

Published: Jan. 1, 2020

In recent years, mobile devices are equipped with increasingly advanced sensing and computing capabilities. Coupled advancements in Deep Learning (DL), this opens up countless possibilities for meaningful applications, e.g., medical purposes vehicular networks. Traditional cloud-based Machine (ML) approaches require the data to be centralized a cloud server or center. However, results critical issues related unacceptable latency communication inefficiency. To end, Mobile Edge Computing (MEC) has been proposed bring intelligence closer edge, where is produced. conventional enabling technologies ML at edge networks still personal shared external parties, servers. Recently, light of stringent privacy legislations growing concerns, concept Federated (FL) introduced. FL, end use their local train an model required by server. The then send updates rather than raw aggregation. FL can serve as technology since it enables collaborative training also DL network optimization. large-scale complex network, heterogeneous varying constraints involved. This raises challenges costs, resource allocation, security implementation scale. survey, we begin introduction background fundamentals FL. Then, highlight aforementioned review existing solutions. Furthermore, present applications Finally, discuss important future research directions

Language: Английский

---

Adaptive Federated Learning in Resource Constrained Edge Computing Systems

IEEE Journal on Selected Areas in Communications, Journal Year: 2019, Volume and Issue: 37(6), P. 1205 - 1221

Published: March 11, 2019

Emerging technologies and applications including Internet of Things, social networking, crowd-sourcing generate large amounts data at the network edge. Machine learning models are often built from collected data, to enable detection, classification, prediction future events. Due bandwidth, storage, privacy concerns, it is impractical send all a centralized location. In this paper, we consider problem model parameters distributed across multiple edge nodes, without sending raw place. Our focus on generic class machine that trained using gradient-descent-based approaches. We analyze convergence bound gradient descent theoretical point view, based which propose control algorithm determines best tradeoff between local update global parameter aggregation minimize loss function under given resource budget. The performance proposed evaluated via extensive experiments with real datasets, both networked prototype system in larger-scale simulated environment. experimentation results show our approach performs near optimum various different distributions.

Language: Английский

---

Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing

Proceedings of the IEEE, Journal Year: 2019, Volume and Issue: 107(8), P. 1738 - 1762

Published: June 12, 2019

With the breakthroughs in deep learning, recent years have witnessed a booming of artificial intelligence (AI) applications and services, spanning from personal assistant to recommendation systems video/audio surveillance. More recently, with proliferation mobile computing Internet Things (IoT), billions IoT devices are connected Internet, generating zillions bytes data at network edge. Driving by this trend, there is an urgent need push AI frontiers edge so as fully unleash potential big data. To meet demand, computing, emerging paradigm that pushes tasks services core edge, has been widely recognized promising solution. The resulted new interdiscipline, or (EI), beginning receive tremendous amount interest. However, research on EI still its infancy stage, dedicated venue for exchanging advances highly desired both computer system communities. end, we conduct comprehensive survey efforts EI. Specifically, first review background motivation running We then provide overview overarching architectures, frameworks, key technologies learning model toward training/inference Finally, discuss future opportunities believe will elicit escalating attentions, stimulate fruitful discussions, inspire further ideas

Language: Английский

---

The Roadmap to 6G: AI Empowered Wireless Networks

IEEE Communications Magazine, Journal Year: 2019, Volume and Issue: 57(8), P. 84 - 90

Published: Aug. 1, 2019

The recent upsurge of diversified mobile applications, especially those supported by AI, is spurring heated discussions on the future evolution wireless communications. While 5G being deployed around world, efforts from industry and academia have started to look beyond conceptualize 6G. We envision 6G undergo an unprecedented transformation that will make it substantially different previous generations cellular systems. In particular, go Internet be required support ubiquitous AI services core end devices network. Meanwhile, play a critical role in designing optimizing architectures, protocols, operations. this article, we discuss potential technologies for enable as well AI-enabled methodologies network design optimization. Key trends also discussed.

Language: Английский

---

Deep Learning in Mobile and Wireless Networking: A Survey

IEEE Communications Surveys & Tutorials, Journal Year: 2019, Volume and Issue: 21(3), P. 2224 - 2287

Published: Jan. 1, 2019

The rapid uptake of mobile devices and the rising popularity applications services pose unprecedented demands on wireless networking infrastructure. Upcoming 5G systems are evolving to support exploding traffic volumes, real-time extraction fine-grained analytics, agile management network resources, so as maximize user experience. Fulfilling these tasks is challenging, environments increasingly complex, heterogeneous, evolving. One potential solution resort advanced machine learning techniques, in order help manage rise data volumes algorithm-driven applications. recent success deep underpins new powerful tools that tackle problems this space. In paper, we bridge gap between research, by presenting a comprehensive survey crossovers two areas. We first briefly introduce essential background state-of-the-art techniques with networking. then discuss several platforms facilitate efficient deployment onto systems. Subsequently, provide an encyclopedic review research based learning, which categorize different domains. Drawing from our experience, how tailor environments. complete pinpointing current challenges open future directions for research.

Language: Английский

---

Towards 6G wireless communication networks: vision, enabling technologies, and new paradigm shifts

Science China Information Sciences, Journal Year: 2020, Volume and Issue: 64(1)

Published: Nov. 24, 2020

Abstract The fifth generation (5G) wireless communication networks are being deployed worldwide from 2020 and more capabilities in the process of standardized, such as mass connectivity, ultra-reliability, guaranteed low latency. However, 5G will not meet all requirements future 2030 beyond, sixth (6G) expected to provide global coverage, enhanced spectral/energy/cost efficiency, better intelligence level security, etc. To these requirements, 6G rely on new enabling technologies, i.e., air interface transmission technologies novel network architecture, waveform design, multiple access, channel coding schemes, multi-antenna slicing, cell-free cloud/fog/edge computing. Our vision is that it have four paradigm shifts. First, satisfy requirement be limited terrestrial networks, which need complemented with non-terrestrial satellite unmanned aerial vehicle (UAV) thus achieving a space-air-ground-sea integrated network. Second, spectra fully explored further increase data rates connection density, including sub-6 GHz, millimeter wave (mmWave), terahertz (THz), optical frequency bands. Third, facing big datasets generated by use extremely heterogeneous diverse scenarios, large numbers antennas, wide bandwidths, service enable range smart applications aid artificial (AI) technologies. Fourth, security strengthened when developing networks. This article provides comprehensive survey recent advances trends aspects. Clearly, additional technical beyond those faster communications extent boundary between physical cyber worlds disappears.

Language: Английский

---

A Survey on the Edge Computing for the Internet of Things

IEEE Access, Journal Year: 2017, Volume and Issue: 6, P. 6900 - 6919

Published: Nov. 29, 2017

The Internet of Things (IoT) now permeates our daily lives, providing important measurement and collection tools to inform every decision. Millions sensors devices are continuously producing data exchanging messages via complex networks supporting machine-to-machine communications monitoring controlling critical smart-world infrastructures. As a strategy mitigate the escalation in resource congestion, edge computing has emerged as new paradigm solve IoT localized needs. Compared with well-known cloud computing, will migrate computation or storage network "edge", near end users. Thus, number nodes distributed across can offload computational stress away from centralized center, significantly reduce latency message exchange. In addition, structure balance traffic avoid peaks networks, reducing transmission between edge/cloudlet servers users, well response times for real-time applications comparison traditional services. Furthermore, by transferring communication overhead limited battery supply significant power resources, system extend lifetime individual nodes. this paper, we conduct comprehensive survey, analyzing how improves performance networks. We categorize into different groups based on architecture, study their comparing latency, bandwidth occupation, energy consumption, overhead. consider security issues evaluating availability, integrity, confidentiality strategies each group, propose framework evaluation computing. Finally, compare various (smart city, smart grid, transportation, so on) architectures.

Language: Английский

---

Digital Twin: Values, Challenges and Enablers From a Modeling Perspective

IEEE Access, Journal Year: 2020, Volume and Issue: 8, P. 21980 - 22012

Published: Jan. 1, 2020

Digital twin can be defined as a virtual representation of physical asset enabled through data and simulators for real-time prediction, optimization, monitoring, controlling, improved decision making. Recent advances in computational pipelines, multiphysics solvers, artificial intelligence, big cybernetics, processing management tools bring the promise digital twins their impact on society closer to reality. twinning is now an important emerging trend many applications. Also referred megamodel, device shadow, mirrored system, avatar or synchronized prototype, there no doubt that plays transformative role not only how we design operate cyber-physical intelligent systems, but also advance modularity multi-disciplinary systems tackle fundamental barriers addressed by current, evolutionary modeling practices. In this work, review recent status methodologies techniques related construction mostly from perspective. Our aim provide detailed coverage current challenges enabling technologies along with recommendations reflections various stakeholders.

Language: Английский

---

Integrated Sensing and Communications: Toward Dual-Functional Wireless Networks for 6G and Beyond

IEEE Journal on Selected Areas in Communications, Journal Year: 2022, Volume and Issue: 40(6), P. 1728 - 1767

Published: March 17, 2022

As the standardization of 5G solidifies, researchers are speculating what 6G will be. The integration sensing functionality is emerging as a key feature Radio Access Network (RAN), allowing for exploitation dense cell infrastructures to construct perceptive network. In this IEEE Journal on Selected Areas in Communications (JSAC) Special Issue overview, we provide comprehensive review background, range applications and state-of-the-art approaches Integrated Sensing (ISAC). We commence by discussing interplay between communications (S&C) from historical point view, then consider multiple facets ISAC resulting performance gains. By introducing both ongoing potential use cases, shed light industrial progress activities related ISAC. analyze number tradeoffs S&C, spanning information theoretical limits physical layer tradeoffs, cross-layer design tradeoffs. Next, discuss signal processing aspects ISAC, namely waveform receive processing. step further, our vision deeper S&C within framework networks, where two functionalities expected mutually assist each other, i.e., via communication-assisted sensing-assisted communications. Finally, identify with other communication technologies, their positive impacts future wireless networks.

Language: Английский

---