Article
EdgeServe: Efficient Deep Learning Model Caching at the Edge
SEC '19: Proceedings of the 4th ACM/IEEE Symposium on Edge Computing
(2019)
Abstract
In this work, we look at how to effectively manage and utilize deep learning models at each edge location, to provide performance guarantees to inference requests. We identify challenges to use these deep learning models at resource-constrained edge locations, and propose to adapt existing cache algorithms to effectively manage these deep learning models.
Keywords
- Deep Learning Inference,
- Caching Algorithm,
- Edge Computing,
- Performance Optimization
Disciplines
Publication Date
2019
DOI
10.1145/3318216.3363370
Citation Information
Tian Guo, Robert J. Walls and Samuel S. Ogden. "EdgeServe: Efficient Deep Learning Model Caching at the Edge" SEC '19: Proceedings of the 4th ACM/IEEE Symposium on Edge Computing (2019) p. 313 - 315 Available at: http://works.bepress.com/sam-ogden/6/