EdgeServe: Efficient Deep Learning Model Caching at the Edge

Tian Guo; Robert J. Walls; Samuel S. Ogden

doi:10.1145/3318216.3363370

EdgeServe: Efficient Deep Learning Model Caching at the Edge

Tian Guo, Robert J. Walls, Samuel S. Ogden

Research output: Contribution to journal › Article › peer-review

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.

Original language	American English
Journal	SEC '19: Proceedings of the 4th ACM/IEEE Symposium on Edge Computing
DOIs	https://doi.org/10.1145/3318216.3363370
State	Published - 2019
Externally published	Yes

Keywords

Caching Algorithm
Deep Learning Inference
Edge Computing
Performance Optimization

Disciplines

Computer Sciences

Access to Document

10.1145/3318216.3363370License: Unspecified

Cite this

@article{3a84feab37684dc481b572be48c65d0e,

title = "EdgeServe: Efficient Deep Learning Model Caching at the Edge",

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 = "Caching Algorithm, Deep Learning Inference, Edge Computing, Performance Optimization",

author = "Tian Guo and Walls, {Robert J.} and Ogden, {Samuel S.}",

note = "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.",

year = "2019",

doi = "10.1145/3318216.3363370",

language = "American English",

journal = "SEC '19: Proceedings of the 4th ACM/IEEE Symposium on Edge Computing",

}

TY - JOUR

T1 - EdgeServe: Efficient Deep Learning Model Caching at the Edge

AU - Guo, Tian

AU - Walls, Robert J.

AU - Ogden, Samuel S.

N1 - 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.

PY - 2019

Y1 - 2019

N2 - 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.

AB - 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.

KW - Caching Algorithm

KW - Deep Learning Inference

KW - Edge Computing

KW - Performance Optimization

UR - https://doi.org/10.1145/3318216.3363370

U2 - 10.1145/3318216.3363370

DO - 10.1145/3318216.3363370

M3 - Article

JO - SEC '19: Proceedings of the 4th ACM/IEEE Symposium on Edge Computing

JF - SEC '19: Proceedings of the 4th ACM/IEEE Symposium on Edge Computing

ER -

EdgeServe: Efficient Deep Learning Model Caching at the Edge

Abstract

Keywords

Disciplines

Access to Document

Other files and links

Cite this