电子学报2025，Vol.53Issue(9)：3060-3077,18.DOI:10.12263/DZXB.20250494
基于大模型辅助的云边协同工作流调度算法
Large Language Model-Assisted Cloud-Edge Collaborative Workflow Scheduling Algorithm
摘要
Abstract
Executing workflows in cloud-edge collaborative environments can reduce data transmission latency be-tween the cloud and terminal devices.Significant differences exist between cloud computing nodes and edge devices in terms of computational capability,storage resources,and communication latency.Furthermore,the computational resources of edge servers exhibit dynamicity due to factors like workload pressure and performance degradation.The complex topo-logical dependencies within workflow applications introduce additional scheduling constraints.These combined factors ren-der the workflow scheduling problem in this context NP-hard.To address these challenges,this paper proposes large lan-guage model-assisted cloud-edge collaborative workflow scheduling algorithm(LAWS).The algorithm employs a knowl-edge graph to structurally represent the chain-of-thought(CoT)reasoning process.It decomposes the scheduling problem in-to multiple sub-problems and extracts sub-knowledge graphs to serve as chain-of-thought guides for the large model,facili-tating collaborative reasoning for scheduling decisions.Experimental results demonstrate that compared with traditional al-gorithms,the proposed algorithm achieves a reduction in workflow execution latency of 3%to 83%and a decrease in com-putational energy consumption of 2.4%to 66.0%.关键词
工作流调度/云边协同/大模型/知识图谱/思维链/问题分解Key words
workflow scheduling/cloud-edge collaboration/large language models/knowledge graph/chain-of-thought/problem decomposition分类
信息技术与安全科学引用本文复制引用
黎广镕,李广军,尚晶,吴文泰,王泽平,龙赛琴..基于大模型辅助的云边协同工作流调度算法[J].电子学报,2025,53(9):3060-3077,18.基金项目
国家自然科学基金(No.U23B2027) （No.U23B2027）
广东基础与应用基础研究基金(No.2024A1515010214) National Natural Science Foundation of China(No.U23B2027) （No.2024A1515010214）
Guangdong Basic and Applied Basic Research Foundation(No.2024A1515010214) （No.2024A1515010214）
