基于边缘智能的分布式协同推理策略  

Distributed collaborative reasoning strategy based on edge intelligence

作　　者：赵宏伟[1,2] 柴海龙 李思 董昌林 潘志伟 ZHAO Hong-wei;CHAI Hai-long;LI Si;DONG Chang-lin;PAN Zhi-wei(School of Information Engineering,Shenyang University,Shenyang 110044,China;Institute of Carbon Neutrality Technology and Policy,Shenyang University,Shenyang 110044,China)

机构地区：[1]沈阳大学信息工程学院,辽宁沈阳110044 [2]沈阳大学碳中和技术与政策研究所,辽宁沈阳110044

出　　处：《计算机工程与设计》2023年第11期3320-3327,共8页Computer Engineering and Design

基　　金：国家自然科学基金面上基金项目(71672117);国家博士后基金项目(2019M651142);辽宁省高校优秀人才基金项目(2020389);沈阳市科技计划基金项目(21108915)。

摘　　要：为解决在资源受限的边缘设备上部署和执行深度学习模型问题,提出一种结合模型分区和数据并行执行的分布式协同推理策略(DecDNN),通过层粒度自适应模型分割算法(AMCA)在边云之间实现模型的并行推理。为避免数据的隐私泄露,在边端之间提出基于全局置乱切分的分布式随机梯度下降算法对数据进行分区,提出一种聚合方案,以产生具有最佳整体推理延迟的分布式并行策略。仿真结果表明,与现有推理策略相比,该策略减少了20%的通信开销和9%的执行延迟,支持多种深度学习模型的推理。To solve the problem of deploying and executing deep learning models on resource-constrained edge devices,a distributed collaborative reasoning strategy(DecDNN)that combining model partitioning and data parallel execution was proposed.The parallel reasoning of the model between the edge and the cloud was realized through the layer granularity adaptive model cutting algorithm(AMCA).To avoid data privacy leakage,a distributed stochastic gradient descent algorithm based on global scrambling and splitting was proposed between the edges to partition the data,and an aggregation scheme was proposed to produce a distribution with the best overall inference latency parallel strategy.Simulation results show that,compared with existing infe-rence strategies,this strategy reduces communication overhead by 20%and execution delay by 9%,and supports the inference of various deep learning models.

关 键 词：边缘计算 分布式边缘环境 深度学习 边云协同 边缘智能 模型分割 数据分区 

分 类 号：TP311.1[自动化与计算机技术—计算机软件与理论]