Fast and fair split computing for accelerating deep neural network (DNN) inference
- 주제(키워드) Split computingSplit point decisionDeep neural network inferenceJain’s fairness index
- 발행기관 한국통신학회
- 발행년도 2025
- 총서유형 Journal
- DOI http://dx.doi.org/10.1016/j.icte.2024.09.013
- KCI ID ART003173253
- 본문언어 영어
초록/요약
Conventional split computing approaches for AI models that generate large outputs suffer from long transmission and inference times. Due to the limited resources of the edge server and selfish MDs, some MDs cannot offload their tasks and sacrifice their performance. To address these issues, we formulate an optimization problem to determine one or two split points that minimize inference latency while ensuring fair offloading among MDs. Additionally, we devise a low-complexity heuristic algorithm called fast and fair split computing (F2SC). Evaluation results demonstrate that F2SC reduces inference time by 3.8%~20.1% compared to the conventional approaches while maintaining fairness.
more