Journal
IEEE NETWORK
Volume 35, Issue 4, Pages 167-175Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/MNET.011.2000651
Keywords
-
Categories
Funding
- National Key R&D Program of China [2018YFB1800800]
- National Natural Science Foundation of China [61931011, 62072303, 61801505, 61872195, 61872240]
- Fundamental Research Funds for the Central Universities [14380059]
- National Postdoctoral Program for Innovative Talents of China [BX20190202]
- Open Project Program of the Key Laboratory of Dynamic Cognitive System of Electromagnetic Spectrum Space [KF20202105]
- Natural Science Foundation for Distinguished Young Scholars of Jiangsu Province, China [BK20200038]
- Natural Science Foundation of Jiangsu Province [BK20181251]
Ask authors/readers for more resources
The research proposes a novel architecture named UaalS, utilizing UAVs as a key enabler to boost edge intelligence with machine learning techniques, achieving seamless super-connectivity service. A case study demonstrates the efficiency and low energy consumption of UAVs participating in distributed machine learning model training.
The air-ground integrated network is a key component of future sixth generation (6G) networks to support seamless and near-instant super-connectivity. There is a pressing need to intelligently provision various services in 6G networks, which is challenging. To meet this need, in this article, we propose a novel architecture called UaalS, that is, unmanned aerial vehicles (UAVs) as a intelligent service for the air-ground integrated network, featuring the UAV as a key enabler to boost edge intelligence with the help of machine learning (ML) techniques. We envision that the proposed UaalS architecture could intelligently provision wireless communication service, edge computing service, and edge caching service by a network of UAVs, making full use of UAVs' flexible deployment and diverse ML techniques. We also conduct a case study where UAVs participate in the model training of distributed ML among multiple terrestrial users, whose result shows that the model training is efficient with low energy consumption of UAVs. Finally, we discuss the challenges and some open research issues in UaaIS.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available