Press Releases

November 20, 2024

6G Radio-interface Indoor Test Using AI in the 4.8 GHz Band for the First Time in Japan Improves Throughput up to 18%

  • Print

TOKYO, JAPAN, November 20, 2024 --- NTT DOCOMO, INC., working in cooperation with NTT Corporation, Nokia and SK Telecom Co., Ltd., an international telecommunications operator, announced today that in an indoor test*1 *2 with radio waves in the 4.8Ghz band of 6G wireless technology using AI for the first time in Japan, *3 *4 *5 they confirmed that communication speeds can be improved up to 18% compared to conventional methods indoors.

Moving towards the era of 6G, DOCOMO conducted the test with NTT, Nokia and SK Telecom, using AI technology to optimize transmission and reception processing for various radio wave propagation environments.

Specifically, the test confirmed that communication performance can be improved by using AI-based baseband transmission and reception processing developed by Nokia to design optimum modulation schemes according to the radio wave propagation environment and applied it to a wireless interface. In addition, the reception process using AI does not use a known signal*6 between the transmitter and receiver (reference signal), which is conventionally needed to estimate the propagation channel, but instead uses AI to realize a series of reception processes from channel estimation to signal detection in one step. The result is higher transmission efficiency and improved communication speeds (see figure).

AI-supported 6G indoor test site, diagram and confirmed results
AI-supported 6G indoor test site, diagram and confirmed results

With further upgrades, the technology is expected to optimize modulation and demodulation schemes for diverse propagation environments and thereby improve communication quality across a broad range of wireless transmission usage cases.

Going forward, DOCOMO will continue further tests initiatives with major domestic and international vendors as well as international operators. DOCOMO expects to accelerate 6G R&D and contribute to 6G's global standardization and commercialization.

Some of the results of the test mentioned in this announcement will be showcased at the New windowNTT R&D Forum 2024 - IOWN INTEGRAL from November 25.

  1. DOCOMO and NTT to Collaborate on 6G Experimental Trials with World-leading Mobile Technology Vendors
    https://www.docomo.ne.jp/english/info/media_center/pr/2022/0606_00.html
  2. DOCOMO and NTT Expand 6G Collaborations with World-leading Vendors Including Ericsson and Keysight Technologies
    https://www.docomo.ne.jp/english/info/media_center/pr/2023/0227_01.html
  3. For this trial, a test station license was obtained, and for the first time in Japan, a 4.8 GHz frequency band was used for test conducted on the premises of NTT's research facility.
  4. DOCOMO and NTT Expand 6G Collaborations with SK Telecom and Rohde & Schwarz to Realize 6G
    https://www.docomo.ne.jp/english/info/media_center/pr/2024/0222_00.html
  5. A signal shared between the transmitter and receiver. The receiver uses this signal to estimate unknown propagation channels.

Appendix

Overview of Demonstration Test Conducted with Nokia and SK Telecom

  • 1. Overview

    DOCOMO and NTT have been working with seven companies including international vendors and operators to develop new 6G wireless technologies since June 2022, and currently are conducting test across various 6G frequency bands. In partnership with NTT, Nokia and SK Telecom, DOCOMO conducted the first demonstration test in Japan using AI technology to optimize transmission and reception processing for various indoor radio-wave propagation environments. In wireless processing utilizing AI, the transmission process improves communication performance by designing and learning optimal modulation schemes for each specific radio propagation environment. In addition, AI-based reception processing does not use traditional reference signals inserted into the transmitter to estimate the propagation channel between the transmitter and receiver. Instead, AI estimates the propagation channel. Since no reference signal is used, higher transmission efficiency is achieved.

  • 2. Results

    In the test conducted at NTT Yokosuka Research and Development Center, after obtaining a radio license, actual radio waves were transmitted in a laboratory (7×13 meters) to measure throughput characteristics (see figure below). AI-based baseband transmission and reception processing was implemented using software on a GPU server. The 4.8 GHz frequency band was tested via a hardware for Software Defined Radio (SDR) .*7 Using 5G New Radio (NR)*8 as the base radio communication method, the receiving antenna was mounted on a movable trolley to perform measurements. Compared to conventional methods without AI, throughput characteristics were measurably improved by 6-16%, and stationary tests conducted at 25 points along the route confirmed an 18% improvement. The results demonstrate that AI-enabled modulation and demodulation technology improves communication performance in both mobile and stationary environments.

Going forward, further testing will be conducted in more complex indoor and outdoor environments to clarify the range of possible applications for AI-enabled modulation and demodulation technology and to verify technologies for broad commercial deployment.

Configuration and results of test
Configuration and results of test
  1. A platform for research and development of Software Defined Radio which enables to develop and verify transmission and reception processing and algorithm by using programmable devices.
  2. A wireless interface standard that is commonly used in commercial 5G systems.
Go to top of the page