AI based optimization of the spectrum and energy efficiency for Intelligent 6G
| Project/Area Number |
22K14263
|
|---|
| Research Category |
Grant-in-Aid for Early-Career Scientists
|
| Allocation Type | Multi-year Fund |
|---|
| Review Section |
Basic Section 21020:Communication and network engineering-related
|
|---|
| Research Institution | The University of Electro-Communications |
|---|
Principal Investigator |
李 傲寒 電気通信大学, 大学院情報理工学研究科, 助教 (50876810)
|
|---|
| Project Period (FY) |
2022-04-01 – 2025-03-31
|
| Project Status |
Granted (Fiscal Year 2023)
|
| Budget Amount *help |
¥4,420,000 (Direct Cost: ¥3,400,000、Indirect Cost: ¥1,020,000)
Fiscal Year 2024: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
Fiscal Year 2023: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
Fiscal Year 2022: ¥1,820,000 (Direct Cost: ¥1,400,000、Indirect Cost: ¥420,000)
|
|---|
| Keywords | Intelligent 6G / AI based optimization / Spectrum efficiency / Energy efficiency / Optimization / Spectrum Efficiency / Energy Efficiency |
|---|
| Outline of Research at the Start |
It is a significant challenge to utilize limited wireless resources (e.g., spectrum resources and energy resources) to effectively achieve the goals of Intelligent 6G, particularly for distributed decision making by user equipment with limited memory and computational ability. In this research project, I will research lightweight artificial intelligence algorithms that can automatically determine the appropriate transmission parameters to achieve the optimal spectrum and energy efficiency.
|
| Outline of Annual Research Achievements |
1) Automatics communication parameter decision in a practical uncertain wireless environment. It is verified that spectrum efficiency can be improved by considering more transmission parameters, such as transmission interval.
2) AI algorithms to improve energy efficiency. A lightweight AI algorithm has been proposed to improve the energy efficiency while an experimental platform for verifying the performance of the proposed AI algorithm in energy efficiency is built.
3) A Quantum-annealing-based ultrafast optimization algorithm is proposed for optimizing the multiplexed techniques-based network performance.
Based on the research results, two journal papers have been published, and more than three reports have been presented or will be presented in international conferences/workshops.
|
| Current Status of Research Progress |
Current Status of Research Progress
2: Research has progressed on the whole more than it was originally planned.
Reason
To achieve the goals of this project. I aimed to research the first and the second questions and make preliminary preparations for the third questions. That is, [Q1] Joint dynamic spectrum access and multiplexing techniques for optimizing the spectrum and energy efficiency. [Q2] Automatic communication parameter decision based on AI in a practical uncertain wireless environment. [Q3] Development of lightweight AI algorithms to improve energy efficiency.
Moreover, at least two journal papers and two international conference papers are expected to be submitted. Regarding [Q1] and [Q2], two journal papers have been published, while two journal papers are under revision. Regarding [Q3], the proposed algorithm has been presented at a domestic conference and international workshop.
|
| Strategy for Future Research Activity |
1) Compare the energy efficiency by jointly considering the dynamic spectrum access and multiplexing techniques and without a joint consideration to clarify how much energy efficiency can be improved. Moreover, more efficient multiplexing techniques will be considered.
2) Improve the spectrum and energy efficiency of the proposed AI algorithm by considering more transmission parameters.
3) Joint optimization of AI and wireless communications. Specifically, the object optimization problem of the joint optimization of AI and wireless communications will be formulated. Then, quantum annealing-based high-speed optimization algorithms will be proposed to solve the formulated objective optimization problem.
|
Report
(2 results)
Research Products
(13 results)
