2022 Fiscal Year Final Research Report
A study on applications of artificial intelligence techniques to control systems for mobile communications
Project/Area Number |
18H01437
|
Research Category |
Grant-in-Aid for Scientific Research (B)
|
Allocation Type | Single-year Grants |
Section | 一般 |
Review Section |
Basic Section 21020:Communication and network engineering-related
|
Research Institution | Tokyo Institute of Technology |
Principal Investigator |
|
Co-Investigator(Kenkyū-buntansha) |
張 裕淵 東京工業大学, 工学院, 助教 (00725616)
|
Project Period (FY) |
2018-04-01 – 2023-03-31
|
Keywords | 次世代移動通信 / ヘトロジーニアス・ネットワーク / 干渉抑圧 / 送信電力制御 / 送信ビームフォーミング制御 / 機械学習 / CNN |
Outline of Final Research Achievements |
Densely deployed small cells are effective in improving the system capacity. However, reusing the same channels in neighboring cells causes inter-cell interference (ICI), and degrades the system capacity. To reduce an amount of ICI, base stations (BSs) can optimize both transmit power levels and beamforming vectors for multiple-input multiple-output (MIMO). As conventional control schemes, the exhaustive search and iterative methods search for the transmit power levels and beamforming vectors that can maximize the system capacity, but require a prohibitive amount of computational complexity. To drastically reduce such complexity, this study applies machine learning techniques into the joint control of the transmit power levels and beamforming vectors for MIMO small cell networks. Computer simulations demonstrate that the proposed schemes can improve the system capacity while reducing the computational complexity and run-time, compared to several conventional schemes.
|
Free Research Field |
無線通信
|
Academic Significance and Societal Importance of the Research Achievements |
本研究は,次世代移動通信の小セルを含むヘトロジーニアス・ネットワークにおいて,同一チャネル干渉を抑えるための干渉抑圧技術に関するものであり,受信側で干渉キャンセルするだけでなく,送信側の複雑な干渉抑圧制御をニューラルネットワーク等の機械学習の技術を用いて低演算量で実行可能なことを示した.これは他の無線通信を含む大規模通信システムの制御についても応用可能であり,大規模ネットワークの実時間制御を計算機シミュレーションに基づき実証したことは,学術的及び社会的貢献として大いに評価できる.
|