What question did this study set out to answer?

The aim is to enhance mobile edge systems by integrating deep reinforcement learning and federated learning for better performance.

July 24, 2019IEEE NetworkOpen Access

In-Edge AI: Intelligentizing Mobile Edge Computing, Caching and Communication by Federated Learning

View Full Paper

Ask AI

Bookmark

Authors

Randomized trial demonstrates improved mobile edge computing performance in communication systems, suggesting advanced optimization methods.

The aim is to enhance mobile edge systems by integrating deep reinforcement learning and federated learning for better performance.
Developed the In-Edge AI framework integrating deep reinforcement learning with federated learning.
Evaluated the system's performance regarding communication efficiency and learning overhead.
Implemented dynamic optimization techniques at system and application levels.
In-Edge AI achieved near-optimal performance with significantly reduced learning overhead.
The framework effectively improved content delivery and user experience in mobile communications.
Challenges and opportunities for future development of In-Edge AI were identified.

Wang et al. (2019) studied this question.

View Full Paper

Ask AI

Bookmark

Randomized trial demonstrates improved mobile edge computing performance in communication systems, suggesting advanced optimization methods.