| Project/Area Number |
20K19794
|
|---|
| Research Category |
Grant-in-Aid for Early-Career Scientists
|
| Allocation Type | Multi-year Fund |
|---|
| Review Section |
Basic Section 60060:Information network-related
|
|---|
| Research Institution | Osaka Metropolitan University (2022)
Osaka Prefecture University (2020-2021) |
|---|
Principal Investigator |
Chiang Yi-Han 大阪公立大学, 大学院工学研究科, 助教 (10824196)
|
|---|
| Project Period (FY) |
2020-04-01 – 2023-03-31
|
| Project Status |
Completed (Fiscal Year 2022)
|
| Budget Amount *help |
¥4,160,000 (Direct Cost: ¥3,200,000、Indirect Cost: ¥960,000)
Fiscal Year 2022: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000)
Fiscal Year 2021: ¥1,820,000 (Direct Cost: ¥1,400,000、Indirect Cost: ¥420,000)
Fiscal Year 2020: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
|
|---|
| Keywords | エッジコンピューティング / IoT / 情報鮮度 / Edge computing / Internet of Things / Age of information / Serverless computing / Information freshness / Task offloading / Task scheduling / Deep learning / Nonlinear programming / Edge Computing / Task Offloading / Task Scheduling / Integer Programming / Machine Learning |
|---|
| Outline of Research at the Start |
In the light of the mixed clairvoyance of processing times and access delays in MEC systems, the applicant plans to leverage combinatorial optimization (CO) to jointly characterize task offloading and scheduling, and then apply machine learning (ML) to accommodate the mixed-clairvoyance feature.
|
| Outline of Final Research Achievements |
In this research, we address the grant assignment and transmission scheduling (GATS) problem for Internet of Things (IoT) applications in multi-access edge computing (MEC) systems. To this end, we formulate it as an integer linear program (ILP) to minimize a weighted sum of coage of information (CoI). Due to the intractability of the original GATS problem, we transform it to an equivalent problem of the maximization of the number of the eliminated age blocks. Then, we propose the CoI-aware age block elimination (CABEL) algorithm in which information updates are selected progressively according to their coage efficiency (CE) values and prove that the achieved approximation factor depends on the relative service costs and uplink delays. Our simulation results demonstrate that the proposed solution can effectively perform information updates and utilize service budgets, thereby achieving low CoI compared with the existing solutions under various parameter settings.
|
| Academic Significance and Societal Importance of the Research Achievements |
超スマート社会を実現するために、産業、医療、交通、環境など広範囲にわたってAIやIoTなどの技術が応用される。スマートフォンやウェアラブル電子機器などのモバイル機器の普及は、人々の日常生活に変革をもたらしているため、エッジコンピューティング技術の開発がかつてないほどの注目を集めている。本研究では、エッジコンピューティングシステムにおけるIoTアプリケーションのため、効率的なタスクオフローディング及びグラント割り当て、情報鮮度の高いスケジューリングを提案することで、今後の自動運転、AIによるヘルスケア、クロスリアリティ（X-Reality）などのアプリケーションの実現に貢献するものである。
|
