报告详情
An Energy-Aware Onboard Edge Intelligence Framework for Small Satellite Earth Observation
编号：40
访问权限：仅限参会人
更新：2026-10-04 23:23:11 浏览：8次
Online
报告开始：2026年10月13日 11:45（Asia/Ho_Chi_Minh）
报告时间：15min
所在会场：[S2] Track 2: IoT and applications [S2-3] Track 2: IoT and applications
暂无文件
摘要
Small satellites and Earth observation missions are producing more image data as the time goes on, without their onboard power, storage and computing capability as well as satellite-to-ground communication keeping up. Because of this, it is often not worthwhile for missions to send all collected data down to the ground station where it must be processed anyway. In this paper, we propose an energy-aware onboard edge intelligence framework to conduct image analysis in a lightweight fashion directly on the satellite as well as prioritize observations before transmitting. High-value observations are first transmitted at a higher quality whereas the lower-priority data may be either compressed or stored and transmitted later. When selecting the tasks, the framework takes into account not only the image significance but also the onboard processing, communication energy, and the link availability. Simulation results show that our approach can decrease the data amount from 5.80 to 2.85 GB as well as the consumption of energy from 21.4 Wh to 14.2 Wh with the classification accuracy staying at a remarkable 93.1% level. Thus it is seen that the integration of on-the-fly processing on the board and priority-based scheduling can significantly enhance the efficiency of small-satellite Earth observation systems in a practical manner.
关键词
Space Technologies,Satelite Systems,Predictive Machine Learning
报告人
Phani Monogya Katikireddi
Senior AI/ML Enginee Citizens bank稿件作者
全部评论
重要日期
-
会议日期
10月11日
2026
至10月14日
2026
-
12月30日 2025
报告提交截止日期
-
09月28日 2026
提前注册日期
-
10月10日 2026
初稿截稿日期
-
10月14日 2026
注册截止日期
主办单位
United Societies of Science
承办单位
Posts and Telecommunications Institute of Technology
协办单位
IEEE Section
IEEE Vietnam Section
IEEE Vietnam Section
联系方式
- ASIANComNet 2026
- as******@usssociety.org
发表评论