Ray-Tracing MIMO Channel Dataset for Machine Learning Applied to V2V Communication

Suzuki, Daniel Takashi Ne Do Nascimento; Oliveira, Ailton; Gonçalves, Luan Luiz; Correa, Ilan; Klautau, Aldebaro; Lins, Silvia; Batista, Paula

doi:10.1109/latincom56090.2022.10000783

Cited by 1 publication

(2 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…2 results show that Sionna's performance is ten times faster than WI simulations. Collecting the info from both WI and Sionna and calculates the Multiple-Input Multiple-Output (MIMO) channels, then it was calculated the Normalized Mean Square Error (NMSE) from the channels, such as in [4], using the WI as channel reference. Since Sionna does not provide the channel phase, we adopted a random uniform phase.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Generation of 5G/6G Wireless Channels Using Raymobtime with Sionna's Ray-Tracing

Bastos,

Oliveira,

Suzuki

et al. 2023

Anais Do XLI Simpósio Brasileiro De Telecomunicações E Processamento De Sinais

View full text Add to dashboard Cite

It is challenging to generate wireless channels for 5G/6G scenarios with sophisticated mobility patterns. Raytracing (RT) is one of the most adopted techniques, especially when 5G/6G millimeter frequency bands are considered. However, most ray tracers, such as Wireless InSite and Sionna's, provide limited support to mobility: only the radio transceivers move over time, while all other objects are held in fixed positions. The Raymobtime methodology was proposed to fill this gap. Raymobtime supports repositioning all mobile objects, which enables simulating advanced mobility patterns. When the Raymobtime methodology was first implemented, its RT was solely based on the commercial Wireless InSite ray tracer. This work expands Raymobtime software to also support the recent NVIDIA Sionna's ray tracer, which is open source and mostly written in Python. The preliminary results indicate that Sionna's brings a fast RT tool, but it still needs to be systematically validated against measured channels.

show abstract

Section: Resultsmentioning

confidence: 99%

“…When Raymobtime was proposed, ray-tracing was solely based in Wireless InSite (WI), with real world scenarios and mobile scatters thereby pursuing a heightened accuracy. WI is a robust software commercialized by Remcom, which has its results validated by several works [4].…”

Section: Introductionmentioning

confidence: 99%