Artificial Intelligence | News | Insights | AiThority
[bsfp-cryptocurrency style=”widget-18″ align=”marquee” columns=”6″ coins=”selected” coins-count=”6″ coins-selected=”BTC,ETH,XRP,LTC,EOS,ADA,XLM,NEO,LTC,EOS,XEM,DASH,USDT,BNB,QTUM,XVG,ONT,ZEC,STEEM” currency=”USD” title=”Cryptocurrency Widget” show_title=”0″ icon=”” scheme=”light” bs-show-desktop=”1″ bs-show-tablet=”1″ bs-show-phone=”1″ custom-css-class=”” custom-id=”” css=”.vc_custom_1523079266073{margin-bottom: 0px !important;padding-top: 0px !important;padding-bottom: 0px !important;}”]

Viettel High Tech and DeepSig Announce AI/ML-based Neural Receiver Operating in Live 5G Network

DeepSig’s AI-Native Software on VHT’s Open RAN Distributed Unit Delivers Uplink Throughput Gain

Viettel High Technology Industries Corporation (VHT), the pioneer of development, manufacturing and commercialization of telco solutions, and DeepSig, experts in artificial intelligence (AI) and machine learning (ML) for wireless communications, announce the industry’s first live AI/ML-based neural receiver in a 5G Open virtualized radio access network (vRAN), in Hanoi. For the first time, AI/ML applied physical layer signal processing is deployed on 5G ORAN equipment manufactured by VHT in Viettel’s network.

Recommended AI News: NTT and Red Hat Fuel AI Analysis at the Edge with IOWN Technologies

“IN ADDITION, DEEPSIG AND VIETTEL HIGH TECH ACCOMPLISHED THIS ON A LIVE 5G NETWORK USING GENERAL PURPOSE INTEL XEON PROCESSORS, WITHOUT REQUIRING DEDICATED AI HARDWARE. IT’S AN EXTRAORDINARY CREDIT TO THE INNOVATION OF BOTH COMPANIES.”

The ongoing collaboration features the integration of DeepSig’s OmniPHY-5G neural receiver software into VHT’s Distributed Unit (DU) based on Intel Xeon processors and Intel FlexRAN reference software to improve 5G user throughput and resource utilization in an Open vRAN deployment. The DeepSig software operates channel estimation and equalization with AI/ML-based algorithms which enhance the Signal to Interference and Noise Ratio (SINR) of the physical shared uplink channel (PUSCH). And VHT’s DU ORAN equipment system is controlling many cells with large user capacity and high load in the trial network. The resulting improvement in 5G RAN capacity and hardware efficiency enables mobile network operators to deliver higher user quality of experience without additional hardware.

Related Posts
1 of 40,589

Nguyen Vu Ha, CEO of VHT shared, “VHT is confident that the collaboration with DeepSig is a pioneer in deploying AI/ML into ORAN standard device systems supporting 5G. DeepSig always quickly changes and responds best to VHT’s equipment and systems, contributing to improving performance and capacity, especially Uplink decoding processing. The contribution of equipment systems and real data sources from deployment on Viettel network is proud to be a prerequisite for optimal AI/ML operation.”

Recommended AI News: Red Hat and Tech Mahindra Enable Hybrid Cloud Flexibility for Telco Workloads

“Our close partnership with VHT is proving how DeepSig’s AI software improves user throughput in real-world conditions. VHT’s urban 5G trial network is an ideal environment for the integrated 5G neural receiver to validate increased radio performance. VHT’s adoption of AI/ML technology in their 5G Open vRAN portfolio shows true innovation leadership,” said Jim Shea, CEO DeepSig. “We are proud to achieve this important industry milestone with VHT and more to come.”

“This deployment illustrates how a fully virtualized RAN makes it possible to quickly implement new innovations that bring real benefits to operators,” said Cristina Rodriguez, vice president and general manager, Wireless Access Networking Division at Intel. “In addition, DeepSig and Viettel High Tech accomplished this on a live 5G network using general purpose Intel Xeon processors, without requiring dedicated AI hardware. It’s an extraordinary credit to the innovation of both companies.”

Recommended AI News: Lenovo Unveils Trailblazing Products and Solutions Designed to Power AI for All at MWC 2024

[To share your insights with us as part of editorial or sponsored content, please write to sghosh@martechseries.com]

Comments are closed.