RRTO: A High-Performance Transparent Offloading System for Model Inference in Mobile Edge Computing

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Sun, Zekai, Guan, Xiuxian, Lin, Zheng, Qing, Yuhao, Song, Haoze, Fang, Zihan, Chen, Zhe, Liu, Fangming, Cui, Heming, Ni, Wei, Luo, Jun
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911081729884160
author Sun, Zekai
Guan, Xiuxian
Lin, Zheng
Qing, Yuhao
Song, Haoze
Fang, Zihan
Chen, Zhe
Liu, Fangming
Cui, Heming
Ni, Wei
Luo, Jun
author_facet Sun, Zekai
Guan, Xiuxian
Lin, Zheng
Qing, Yuhao
Song, Haoze
Fang, Zihan
Chen, Zhe
Liu, Fangming
Cui, Heming
Ni, Wei
Luo, Jun
contents Deploying Machine Learning (ML) applications on resource-constrained mobile devices remains challenging due to limited computational resources and poor platform compatibility. While Mobile Edge Computing (MEC) offers offloading-based inference paradigm using GPU servers, existing approaches are divided into non-transparent and transparent methods, with the latter necessitating modifications to the source code. Non-transparent offloading achieves high performance but requires intrusive code modification, limiting compatibility with diverse applications. Transparent offloading, in contrast, offers wide compatibility but introduces significant transmission delays due to per-operator remote procedure calls (RPCs). To overcome this limitation, we propose RRTO, the first high-performance transparent offloading system tailored for MEC inference. RRTO introduces a record/replay mechanism that leverages the static operator sequence in ML models to eliminate repetitive RPCs. To reliably identify this sequence, RRTO integrates a novel Operator Sequence Search algorithm that detects repeated patterns, filters initialization noise, and accelerates matching via a two-level strategy. Evaluation demonstrates that RRTO achieves substantial reductions of up to 98% in both per-inference latency and energy consumption compared to state-of-the-art transparent methods and yields results comparable to non-transparent approaches, all without necessitating any source code modification.
format Preprint
id arxiv_https___arxiv_org_abs_2507_21739
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle RRTO: A High-Performance Transparent Offloading System for Model Inference in Mobile Edge Computing
Sun, Zekai
Guan, Xiuxian
Lin, Zheng
Qing, Yuhao
Song, Haoze
Fang, Zihan
Chen, Zhe
Liu, Fangming
Cui, Heming
Ni, Wei
Luo, Jun
Networking and Internet Architecture
Deploying Machine Learning (ML) applications on resource-constrained mobile devices remains challenging due to limited computational resources and poor platform compatibility. While Mobile Edge Computing (MEC) offers offloading-based inference paradigm using GPU servers, existing approaches are divided into non-transparent and transparent methods, with the latter necessitating modifications to the source code. Non-transparent offloading achieves high performance but requires intrusive code modification, limiting compatibility with diverse applications. Transparent offloading, in contrast, offers wide compatibility but introduces significant transmission delays due to per-operator remote procedure calls (RPCs). To overcome this limitation, we propose RRTO, the first high-performance transparent offloading system tailored for MEC inference. RRTO introduces a record/replay mechanism that leverages the static operator sequence in ML models to eliminate repetitive RPCs. To reliably identify this sequence, RRTO integrates a novel Operator Sequence Search algorithm that detects repeated patterns, filters initialization noise, and accelerates matching via a two-level strategy. Evaluation demonstrates that RRTO achieves substantial reductions of up to 98% in both per-inference latency and energy consumption compared to state-of-the-art transparent methods and yields results comparable to non-transparent approaches, all without necessitating any source code modification.
title RRTO: A High-Performance Transparent Offloading System for Model Inference in Mobile Edge Computing
topic Networking and Internet Architecture
url https://arxiv.org/abs/2507.21739