| 講演抄録/キーワード |
| 講演名 |
2025-03-07 15:35
知識伝達を活用した強化学習によるモバイルエッジコンピューティングにおける計算オフロード手法 ○劉 子為・中山雅哉(東大) SC2024-46 |
| 抄録 |
(和) |
(まだ登録されていません) |
| (英) |
Mobile Edge Computing (MEC) addresses the growing demand for low-latency and efficient computation in mobile devices by enabling task offloading to edge servers. Effective offloading strategies are critical for optimizing resource utilization and reducing energy consumption. This paper proposes a reinforcement learning-based offloading method enhanced with bidirectional knowledge transfer to accelerate learning and improve decision accuracy. Extensive simulations were conducted on the PureEdgeSim platform. The results indicate that the proposed method outperforms other methods in terms of task success rate and energy consumption especially in scenarios with varying edge device counts. |
| キーワード |
(和) |
/ / / / / / / |
| (英) |
Mobile Edge Computing / Computation Offloading / Reinforcement Learning / / / / / |
| 文献情報 |
信学技報, vol. 124, no. 425, SC2024-46, pp. 25-30, 2025年3月. |
| 資料番号 |
SC2024-46 |
| 発行日 |
2025-02-28 (SC) |
| ISSN |
Online edition: ISSN 2432-6380 |
著作権に ついて |
技術研究報告に掲載された論文の著作権は電子情報通信学会に帰属します.(許諾番号:10GA0019/12GB0052/13GB0056/17GB0034/18GB0034) |
| PDFダウンロード |
SC2024-46 |