Abstract

Recently, along with the rapid development of mobile communication\ntechnology, edge computing theory and techniques have been attracting more and\nmore attentions from global researchers and engineers, which can significantly\nbridge the capacity of cloud and requirement of devices by the network edges,\nand thus can accelerate the content deliveries and improve the quality of\nmobile services. In order to bring more intelligence to the edge systems,\ncompared to traditional optimization methodology, and driven by the current\ndeep learning techniques, we propose to integrate the Deep Reinforcement\nLearning techniques and Federated Learning framework with the mobile edge\nsystems, for optimizing the mobile edge computing, caching and communication.\nAnd thus, we design the "In-Edge AI" framework in order to intelligently\nutilize the collaboration among devices and edge nodes to exchange the learning\nparameters for a better training and inference of the models, and thus to carry\nout dynamic system-level optimization and application-level enhancement while\nreducing the unnecessary system communication load. "In-Edge AI" is evaluated\nand proved to have near-optimal performance but relatively low overhead of\nlearning, while the system is cognitive and adaptive to the mobile\ncommunication systems. Finally, we discuss several related challenges and\nopportunities for unveiling a promising upcoming future of "In-Edge AI".\n

Keywords

Computer scienceEnhanced Data Rates for GSM EvolutionEdge computingMobile edge computingEdge deviceComputer networkMobile computingServerMobile telephonyDistributed computingMultimediaArtificial intelligenceOperating systemMobile radioCloud computing

Affiliated Institutions

Related Publications

CloneCloud

Mobile applications are becoming increasingly ubiquitous and provide ever richer functionality on mobile devices. At the same time, such devices often enjoy strong connectivity ...

2011 1871 citations

Publication Info

Year
2019
Type
article
Volume
33
Issue
5
Pages
156-165
Citations
1008
Access
Closed

External Links

Social Impact

Social media, news, blog, policy document mentions

Citation Metrics

1008
OpenAlex

Cite This

Xiaofei Wang, Yiwen Han, Chenyang Wang et al. (2019). In-Edge AI: Intelligentizing Mobile Edge Computing, Caching and Communication by Federated Learning. IEEE Network , 33 (5) , 156-165. https://doi.org/10.1109/mnet.2019.1800286

Identifiers

DOI
10.1109/mnet.2019.1800286