移动通信2026，Vol.50Issue(8)：41-55,15.DOI:10.3969/j.issn.1006-1010.20260604-0002
面向边端协同推理的模型分割与无线资源分配方法研究
Joint Model Partitioning and Wireless Resource Allocation for Edge-End Collaborative Inference
摘要
Abstract
For multi-user device-edge collaborative inference in the 6G intelligent air interface,fixed model partitioning and static spectrum allocation are unable to effectively accommodate heterogeneous model loads and inter-user resource competition.In this paper,we first develop a device-edge collaborative inference model that accounts for spectrum overlapping and co-channel interference.Then model partitioning and wireless spectrum allocation are jointly formulated as an optimization problem aimed at minimizing the total system latency,and accordingly we propose an interference-aware action-decomposed proximal policy optimization(IAAD-PPO)algorithm.The proposed algorithm employs three conditional actions to determine the model partition point,the starting position of the allocated spectrum,and the spectrum occupancy length,respectively.Action masking is introduced to ensure the validity of the selected actions,while a system-level reward is designed to coordinate resource competition among multiple users.A device-edge collaborative inference testbed is implemented using AlexNet,MobileNetV2,ResNet50,and VGG16.Experimental results show that,in a four-user concurrent inference scenario,the average end-to-end latency of IAAD-PPO is 55.5 ms,representing reductions of 13.8％,67.8％,and 60.6％compared with DQN,local execution,and full edge execution,respectively.关键词
边端协同推理/模型分割/无线资源分配/近端策略优化/6G智能空口Key words
edge-end collaborative inference/model partitioning/wireless resource allocation/proximal policy optimization/6G intelligent air interface分类
信息技术与安全科学引用本文复制引用
黄文康,姜宁,贺家乐,闫实..面向边端协同推理的模型分割与无线资源分配方法研究[J].移动通信,2026,50(8):41-55,15.基金项目
国家科技重大专项"6G无线接入网智能化关键技术研究、标准推进与验证"(GXB-2-2025-5) （GXB-2-2025-5）
国家自然科学基金项目"面向差异化服务的通信-感知-计算融合无线组网理论与方法"(62371067) （62371067）
