| 研究課題/領域番号 |
20K11764
|
|---|
| 研究機関 | 茨城大学 |
|---|
研究代表者 |
王 瀟岩 茨城大学, 理工学研究科(工学野), 准教授 (10725667)
|
|---|
| 研究分担者 |
梅比良 正弘 茨城大学, 理工学研究科(工学野), 特命研究員 (00436239)
|
|---|
| 研究期間 (年度) |
2020-04-01 – 2023-03-31
|
| キーワード | wireless access / reinforcement learning / federated learning |
|---|
| 研究実績の概要 |
In FY2021, based on our previous results, we continued our research on achieving global optimization at low bandwidth consumption by integrating federated learning technique. To deal with the global non-independent and identically distributed environmental dataset and constrained bandwidth resources, we propose to integrate federated learning-based edge server upon intelligent BSs, to form a layered in-network learning framework. We compared the performance of the proposed approach with centralized optimal results, in terms of spectrum efficiency and bandwidth consumption through simulations.
|
| 現在までの達成度 (区分) |
現在までの達成度 (区分)
2: おおむね順調に進展している
理由
We consider that the research progresses smoothly. We have published 2 journal papers, 2 internal conference papers and multiple domestic conference papers in FY2021 under the support of this funding.
|
| 今後の研究の推進方策 |
In the following year, we will consider the problems with sophisticated and practical models. Meanwhile, we will perform the experiments by realizing the proposed scheme in testbeds.
|
| 次年度使用額が生じた理由 |
コロナウィルス感染防止のため、多数の国際・国内学会が中止するため、残額が生じてしまう。残りの助成金は２０２２年度の学会の参加費と学術論文の登録費として使用する予定である。
|
