FML: Fast Machine Learning for 5G mmWave Vehicular Communications

Asadi, Arash; Müller, Sabrina; Sim, Gek Hong; Klein, Anja; Hollick, Matthias

doi:10.1109/infocom.2018.8485876

Cited by 79 publications

(41 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The authors in [14] proposed the unimodal beam alignment (UBA) algorithm that restricts the search set of the best directions by using the correlation between consecutive beams and the unimodality of the power of the received signal. An online beamalignment algorithm for mmWave vehicular communications was introduced in [15], which uses the vehicle's direction of arrival as a contextual information. In [16], another beamalignment policy was investigated, which requires the perfect knowledge of the data rates for all chosen beam directions.…”

Section: A Existing Workmentioning

confidence: 99%

“…All the existing MAB-based policies above [14], [15], [16], [17], [18] depend on a central authority, which first chooses jointly the best pair of beam directions of the transmitter and the receiver, and then feedbacks the result to both devices resulting in a high signaling overhead. Moreover, these approaches are deterministic and exploit the so-called upper confidence bound (UCB).…”

Section: A Existing Workmentioning

confidence: 99%

“…In this work, we focus squarely on distributed beamalignment policies that do not require the existence of a central node nor rely on any assumptions regarding the network dynamics, as opposed to [14], [15], [16], [17], [18]. For this, we build on the exponential weights algorithm for exploration and exploitation (EXP3) in [19] to define novel beam-alignment policies capable to adapt to such arbitrary and unpredictable environments.…”

Section: B Our Contributionsmentioning

confidence: 99%

See 2 more Smart Citations

One-Bit Feedback Exponential Learning for Beam Alignment in Mobile mmWave

2020

View full text Add to dashboard Cite

Efficient beam alignment in wireless networks capable of supporting device mobility is currently one of the major challenges in mmWave communications. In this context, we formulate the beam-alignment problem via the adversarial multi-armed bandit (MAB) framework, which copes with arbitrary network dynamics including non-stationary or adversarial components. Building on the well known exponential weights algorithm (EXP3) and by exploiting the structure and sparsity of the mmWave channel, we propose a modified (MEXP3) policy that requires solely one-bit of feedback information (reducing the amount of exchanged data during the beam-alignment process). Our MEXP3 comes with optimal theoretical guarantees in terms of asymptotic regret. Moreover, for finite horizons, our regret upper-bound is tighter than that of the original EXP3 suggesting better performance in practice. We then introduce an additional modification that accounts for the temporal correlation between successive beams and propose another beam-alignment policy. Our numerical results demonstrate that our beam-alignment policies outperform existing ones with respect to the regret but also to the outage, throughput and delay in typical mobile mmWave settings.

show abstract

Section: A Existing Workmentioning

confidence: 99%

Section: A Existing Workmentioning

confidence: 99%

Section: B Our Contributionsmentioning

confidence: 99%

See 1 more Smart Citation

One-Bit Feedback Exponential Learning for Beam Alignment in Mobile mmWave

2020

View full text Add to dashboard Cite

show abstract

“…The need for extra hardware or RF channel limits the practical use of these approaches. Asadi et al [24] proposed a simpler machine learning mechanism to adapt beam selection to the V2X environment. In contrast, our work shows that a small set of beams can cover most of the possible best AoA/AoD due to their sparsity and persistence.…”

Section: Related Workmentioning

confidence: 99%

Demystifying millimeter-wave V2X

Wang

Huang

Zhang

2020

Proceedings of the 26th Annual International Conference on Mobile Computing and Networking

View full text Add to dashboard Cite

Millimeter-wave (mmWave) networking represents a core technology to meet the demanding bandwidth requirements of emerging connected vehicles. However, the feasibility of mmWave vehicleto-everything (V2X) connectivity has long been questioned. One major doubt lies in how the highly directional mmWave links can sustain under high mobility. In this paper, we present the first comprehensive reality check of mmWave V2X networks. We deploy an experimental testbed to mimic a typical mmWave V2X scenario, and customize a COTS mmWave radio to enable microscopic investigation of the channel and the link. We further construct a high-fidelity 3D ray-tracer to reproduce the mmWave characteristics at scale. With this toolset, we study the mmWave V2X coverage, mobility and blockage, codebook/beam management, and spatial multiplexing. Our measurement debunks some common misperceptions of mmWave V2X networks. In particular, due to the constrained roadway network structures, we find the beam management can be handled easily by the often-denounced beam scanning schemes, as long as the codebook is properly designed. Blockage can be almost eliminated through proper basestation deployment and cooperation. Highly effective spatial multiplexing can be realized even without sophisticated MIMO radios. Our work points to possible ways to realize efficient and reliable mmWave networks under high mobility, while maintaining the simplicity of standard network protocols.

show abstract

“…One of the first beam-alignment strategies using the MAB framework is based on the upper confidence bound (UCB) [6], where the authors exploit the correlation among beams and the unimodality properties of the channel. Another beamalignment algorithm is proposed in [7], in which the vehicle's direction of arrival is exploited as contextual information. The authors of [8] use a UCB-based policy for beam-alignment in high speed train applications.…”

Section: Introductionmentioning

confidence: 99%

Exploiting Channel Sparsity for Beam Alignment in mmWave Systems via Exponential Learning

Chafaa

Belmega

Debbah

2020

2020 IEEE International Conference on Communications Workshops (ICC Workshops)

View full text Add to dashboard Cite

The large available spectrum in the millimeter wave (mmWave) band represents an attractive alternative for the congested sub-6 GHz spectrum. To overcome the difficult propagation conditions at high frequencies, directional communications via multiple antenna arrays and high-gain beams can be employed. Nevertheless, these beams need to be well aligned to reliably transmit data, which is a challenging task given the user mobility and the unpredictable changes of the wireless environment. In this paper, we propose a new distributed beam-alignment strategy relying on a single bit of feedback, which equals one if the signal-to-interference-plus-noise (SINR) reaches a predefined threshold. The novelty consists in a modified reward function, inspired from the sparse nature of the mmWave channel, coupled with the well-known exponential weights algorithm (EXP3). First, we show that our resulting adaptive policy comes with optimal theoretical guarantees in terms of sub-linear regret. Second, our numerical results demonstrate significant performance gains of our beam-alignment policy compared with the original EXP3 algorithm and other existing policies in a mmWave setting with user mobility.

show abstract

FML: Fast Machine Learning for 5G mmWave Vehicular Communications

Cited by 79 publications

References 23 publications

One-Bit Feedback Exponential Learning for Beam Alignment in Mobile mmWave

One-Bit Feedback Exponential Learning for Beam Alignment in Mobile mmWave

Demystifying millimeter-wave V2X

Exploiting Channel Sparsity for Beam Alignment in mmWave Systems via Exponential Learning

Contact Info

Product

Resources

About