Self-optimization of Resource Allocation for sixth-generation mobile communication system

2023 Fiscal Year Final Research Report

• Project/Area Number: 20K04466
• Research Category: Grant-in-Aid for Scientific Research (C)
• Allocation Type: Multi-year Fund
• Section: 一般
• Review Section: Basic Section 21020:Communication and network engineering-related
• Research Institution: Kagawa University
• Principal Investigator: Miki Nobuhiko 香川大学, 創造工学部, 教授 (90709247)
• Project Period (FY): 2020-04-01 – 2024-03-31
• Keywords: 凸最適化 / プロポーショナルフェアネス / 機械学習

Outline of Final Research Achievements

In order to achieve higher speed and capacity with 6G than with 5G, it is necessary to further increase the frequency bandwidth and network density. Under such conditions, it is essential to optimize the entire mobile network. In this study, we proposed an algorithm that optimize the network based on the proportional fair criteria.
The main features of the proposed algorithm are (1) it combines the advantages of both machine learning and convex optimization, and (2) it is an optimization algorithm that uses realistic information based on signaling between base stations and between base stations and terminals, as specified in 5G.
We confirm the effectiveness of the proposed algorithm based on the computer simulations.

Free Research Field

移動通信システム

Academic Significance and Societal Importance of the Research Achievements

移動通信システム全体に対して凸最適化を適用することで，プロポーショナルフェアネス規範に基づく最適解を導出することは可能であるが，非現実的な仮定が含まれている．
本研究では，凸最適化の最適解を導出できる特長を用いつつ，干渉適用時の分散制御の適用，セル選択規範に与えるオフセット値の機械学習による最適化を用いることにより，現実的なアルゴリズムを実現している．
本研究は，最適解との比較を通して現実的なアルゴリズムでどの程度まで最適解に近い特性を実現できるかを明確化している点が学術的に意義があり，現実的な基地局-基地局間，基地局-端末間のシグナリングに基づき最適化を行なっている点に社会的意義があると考える．