首页|基于代理双向竞拍的弹性云资源调度方案

基于代理双向竞拍的弹性云资源调度方案

扫码查看
针对跨云平台的资源调度问题,提出一种基于代理双向竞拍的弹性资源调度方案。该方案在拍卖过程中引入交易延时排队影响因子,排队轮数越多,排队影响因子值越大,竞价提交优先级越高,同时根据服务等级协议判定不合规交易的惩罚金数额,以惩罚金制度防范恶意竞拍交易的出现。每轮竞拍允许并发实现多项交易。仿真结果表明,该方案保证了竞拍成功率,并且与传统一次拍卖成交方案相比,其竞拍时间减少了 0。32 s,同时能提高16%的用户收益与9%的资源提供商利益。
ELASTIC CLOUD RESOURCE SCHEDULING SCHEME BASED ON AGENT TWO-WAY BIDDING
Aimed at the resource scheduling problem of cross-cloud platforms,a flexible resource scheduling scheme based on agent two-way bidding is proposed.This scheme introduced a transaction delay queuing influence factor in the auction process.The more queuing rounds,the larger the queuing influence factor value,and the higher the bid submission priority.At the same time,the penalty amount for non-compliant transactions was determined according to the service level agreement.The penalty system prevented the possibility of malicious auction transactions.Each round of auction allowed multiple transactions to be implemented concurrently.The simulation results show that the algorithm guarantees the success rate of bidding,and compared with the traditional once auction transaction scheme,the bidding time of this scheme is reduced by 0.32 s,and at the same time,it can increase 16%of the user's revenue and 9%of the resource provider's benefit.

Two-way biddingResource schedulingQueuing influence factorMalicious bidding

何望、林果园

展开 >

中国矿业大学计算机科学与技术学院 江苏徐州 221116

矿山数字化教育部工程研究中心 江苏徐州 221116

南京大学计算机软件新技术国家重点实验室 江苏南京 210023

双向竞拍 资源调度 排队影响因子 恶意竞拍

中央高校基本科研业务费专项

2017XKQY079

2024

计算机应用与软件
上海市计算技术研究所 上海计算机软件技术开发中心

计算机应用与软件

CSTPCD北大核心
影响因子:0.615
ISSN:1000-386X
年,卷(期):2024.41(3)
  • 15