中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 计算技术研究所
  3. 中国科学院计算技术研究所
AptEVS: Adaptive Edge-and-Vehicle Scheduling for Hierarchical Federated Learning over Vehicular Networks

文献类型：期刊论文

作者Tian, Yu2,3; Wang, Nina1,2,3,4; Zhang, Zongshuai1,2,4; Zou, Wenhao2,3; Zhao, Liangjie2,3; Liu, Shiyao2,3; Tian, Lin1,2,3
刊名ELECTRONICS
出版日期2026-01-22
卷号15期号:2页码:28
关键词hierarchical federated learning deep reinforcement learning edge-and-vehicle scheduling vehicular networks
ISSN号2079-9292
DOI10.3390/electronics15020479
英文摘要Hierarchical federated learning (HFL) has emerged as a promising paradigm for distributed machine learning over vehicular networks. Despite recent advances in vehicle selection and resource allocation, most still adopt a fixed Edge-and-Vehicle Scheduling (EVS) configuration that keeps the number of participating edge nodes and vehicles per node constant across training rounds. However, given the diverse training tasks and dynamic vehicular environments, our experiments confirm that such static configurations struggle to efficiently meet the task-specific requirements across model accuracy, time delay, and energy consumption. To address this, we first formulate a unified, long-term training cost metric that balances these conflicting objectives. We then propose AptEVS, an adaptive scheduling framework based on deep reinforcement learning (DRL), designed to minimize this cost. The core of AptEVS is its phase-aware design, which adapts the scheduling strategy by first identifying the current training phase and then switching to specialized strategies accordingly. Extensive simulations demonstrate that AptEVS learns an effective scheduling policy online from scratch, consistently outperforming baselines and and reducing the long-term training cost by up to 66.0%. Our findings demonstrate that phase-aware DRL is both feasible and highly effective for resource scheduling over complex vehicular networks.
资助项目National Natural Science Foundation of China[62120106007]
WOS研究方向Computer Science ; Engineering ; Physics
语种英语
WOS记录号WOS:001670325700001
出版者MDPI
源URL[http://119.78.100.204/handle/2XEOYT63/42853]  
专题中国科学院计算技术研究所
通讯作者Wang, Nina
作者单位1.Univ Chinese Acad Sci, Nanjing 211135, Peoples R China
2.Chinese Acad Sci, Inst Comp Technol, Beijing 100190, Peoples R China
3.Univ Chinese Acad Sci, Beijing 100049, Peoples R China
4.Nanjing Inst InforSuperBahn, Nanjing 211100, Peoples R China
推荐引用方式
GB/T 7714		 Tian, Yu,Wang, Nina,Zhang, Zongshuai,et al. AptEVS: Adaptive Edge-and-Vehicle Scheduling for Hierarchical Federated Learning over Vehicular Networks[J]. ELECTRONICS,2026,15(2):28.
APA Tian, Yu.,Wang, Nina.,Zhang, Zongshuai.,Zou, Wenhao.,Zhao, Liangjie.,...&Tian, Lin.(2026).AptEVS: Adaptive Edge-and-Vehicle Scheduling for Hierarchical Federated Learning over Vehicular Networks.ELECTRONICS,15(2),28.
MLA Tian, Yu,et al."AptEVS: Adaptive Edge-and-Vehicle Scheduling for Hierarchical Federated Learning over Vehicular Networks".ELECTRONICS 15.2(2026):28.

入库方式： OAI收割

来源：计算技术研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。