检索结果-南通市图书馆

Throughput Servicing Time Allocation of Hybrid Storage System Based on client grouping Mechanism

Chinese Journal of Electronics 2019年第1期28卷 62-70页

作者： HUO Zhisheng XIAO Limin HE Zhenxue RONG Xiaoling State Key Laboratory of Software Development Environment School of Computer Science and Engineering Beihang University School of Information Science and Technology Hebei Agricultural University School of Communication Science Beijing Language and Culture University

The fair division theory has emerged as a promising approach for the throughput allocation of hybrid storage system. While most of them cause the unfair allocation of the throughput servicing time due to taking no consideration of clients’ request IO latencies. We propose one Servicing time allocation method based on the client grouping mechanism(STCG), STCG establishes fair allocation policies based on clients’ workload weights,which can achieve a fair throughput servicing time allocation, and can maximize the resource utilization. The experimental result shows that STCG’s allocation enjoys fair properties in each client group, and compared with the method proposd recently, STCG can improve the resource utilization about 12%–330%.

关键词： Hybrid storage system Throughput servicing time Fair allocation client grouping

来源：

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Federated Dynamic client Selection for Fairness Guarantee in Heterogeneous Edge Computing

引用

Journal of Computer Science & Technology 2024年第1期39卷 139-158页

作者：毛莺池沈莉娟吴俊平萍吴杰 Key Laboratory of Water Big Data Technology of Ministry of Water Resources Hohai UniversityNanjing 211100China College of Computer and Information Hohai UniversityNanjing 211100China Center of Networked Computing Temple UniversityPhiladelphiaPA 19122-6096U.S.A

Federated learning has emerged as a distributed learning paradigm by training at each client and aggregat-ing at a parameter *** heterogeneity hinders stragglers from responding to the server in time with huge com-munication *** client grouping in federated learning can solve the straggler problem,the stochastic selection strategy in client grouping neglects the impact of data distribution within each ***,current client grouping ap-proaches make clients suffer unfair participation,leading to biased performances for different *** order to guaran-tee the fairness of client participation and mitigate biased local performances,we propose a federated dynamic client selec-tion method based on data representativity(FedSDR).FedSDR clusters clients into groups correlated with their own lo-cal computational *** estimate the significance of client datasets,we design a novel data representativity evalua-tion scheme based on local data ***,the two most representative clients in each group are selected to optimize the global ***,the DYNAMIC-SELECT algorithm updates local computational efficiency and data representativity states to regroup clients after periodic average *** on real datasets show that FedS-DR improves client participation by 27.4%,37.9%,and 23.3%compared with FedAvg,TiFL,and FedSS,respectively,tak-ing fairness into account in federated *** addition,FedSDR surpasses FedAvg,FedGS,and FedMS by 21.32%,20.4%,and 6.90%,respectively,in local test accuracy variance,balancing the performance bias of the global model across clients.

关键词： federated learning fairness computational efficiency data distribution client selection client grouping

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

欢迎您,

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：