.png){kind=icon}
.png){kind=icon}
Return
Two-Phase Split Computing Framework in Edge-Cloud Continuum
.png){kind=icon}
PRE
AI
DOI：10.1109/JIOT.2024.3376977.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Split computing is a promising approach to reduce the inference latency of deep neural network (DNN) models. In this article, we propose a two-phase split computing framework (TSCF). In TSCF, for vertical interlayer splitting between the computing nodes at different levels (e.g., central and edge clouds), a shortest path problem in a directed graph is formulated and a pruning-based low-complexity solution is devised. In addition, for horizontal intralayer splitting between the computing nodes at the same level (e.g., edge clouds), the execution units of a specific layer are further divided and distributed to the computing nodes at the same level proportionally to their available resources. The evaluation results demonstrate that TSCF can reduce inference latency more than 38.8% compared to the traditional interlayer splitting scheme by efficiently using the resources of distributed computing nodes. In addition, it is demonstrated that near-optimal performance in terms of inference latency can be achieved even with a pruning-based low-complexity solution.
Keywords:
Cloud computing
Computational modeling
Mobile handsets
Internet of Things
Artificial neural networks
Performance evaluation
Optimization
Deep neural network (DNN)
inference latency
interlayer splitting
intralayer splitting
two-phase split computing
Journal
IF:
8.9
Papers:
1.4W
Citations:
7.8W