| Project/Area Number |
16K12405
|
|---|
| Research Category |
Grant-in-Aid for Challenging Exploratory Research
|
| Allocation Type | Multi-year Fund |
|---|
| Research Field |
Computer system
|
|---|
| Research Institution | The University of Tokyo |
|---|
Principal Investigator |
NAKAMURA HIROSHI 東京大学, 大学院情報理工学系研究科, 教授 (20212102)
|
|---|
| Co-Investigator(Renkei-kenkyūsha) |
NAKADA Takashi 奈良先端科学技術大学院大学, 先端科学技術研究科, 准教授 (00452524)
|
|---|
| Project Period (FY) |
2016-04-01 – 2018-03-31
|
| Project Status |
Completed (Fiscal Year 2017)
|
| Budget Amount *help |
¥3,380,000 (Direct Cost: ¥2,600,000、Indirect Cost: ¥780,000)
Fiscal Year 2017: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
Fiscal Year 2016: ¥1,950,000 (Direct Cost: ¥1,500,000、Indirect Cost: ¥450,000)
|
|---|
| Keywords | コンピューティング / 低消費エネルギー / 実行モデル / スケジューリング / 計算機システム / 省電力 |
|---|
| Outline of Final Research Achievements |
Data processing and available energy heavily depend on environments in widely distributed sensing and computing systems. This research proposed execution model which optimize data processing both in temporal and spatial in such systems. Firstly, in case that processing time of task is determined during computation, task scheduling algorithm is proposed to minimize energy consumption while satisfying performance constraints. Its superiority to other existing methods is successfully shown. Secondly, in solar energy harvesting sensor node systems, an adaptive power manager is proposed by using reinforcement learning. The proposed manager successfully achieves higher performance without increasing wasted energy regardless the location of sensor nodes.
|
