| 基于用户QoS预测的任务流调度算法 |
| |
| 引用本文： | 杨丽蕴,张绍林,韩宏,秦科.基于用户QoS预测的任务流调度算法[J].电视技术,2016,40(6):91-97. |
| |
| 作者姓名： | 杨丽蕴 张绍林 韩宏 秦科 |
| |
| 作者单位： | 1. 中国电子技术标准化研究院,北京,100007;2. 电子科技大学 计算机科学与工程学院,四川 成都,611731 |
| |
| 基金项目： | 工信部智能制造专项：工业云服务模型标准化与试验验证系统 |
| |
| 摘 要： | 提出在云计算数据中心环境下,节省开销并保障用户QoS的调度算法,用预测的方式来判断QoS走势,用任务流调度开规避不利的QoS情况.通过ARIMA预测模型对任务的QoS进行预测,根据预测结果得到有潜在QoS危险的任务预警,并利用一个粒子群(PSO)和引力搜索(GSA)的混合算法求得最终的调度策略,最后通过任务调度保障用户的QoS,同时在调度算法中根据网络拥塞控制的思想添加了一个保留虚拟机的方案.实验表明该算法能有效保障用户QoS,比原混合算法减少时间开销9.26％.
|
| 关 键 词： | 云计算数据中心 服务质量 任务流调度 ARIMA预测模型 粒子群优化算法 引力搜索算法 |
| 收稿时间： | 2016/5/19 0:00:00 |
| 修稿时间： | 2016/5/23 0:00:00 |
Workflow scheduling algorithm based on forecast of users' QoS |
| |
| Yang Liyun,Zhang Shaolin,Han Hong and Qin Ke.Workflow scheduling algorithm based on forecast of users' QoS[J].Tv Engineering,2016,40(6):91-97. |
| |
| Authors: | Yang Liyun Zhang Shaolin Han Hong and Qin Ke |
| |
| Affiliation: | China Electronics Standardization Institute,University of Electronic Science and Technology of China,University of Electronic Science and Technology of China,University of Electronic Science and Technology of China |
| |
| Abstract: | Presenting a model to save the consumption and assure the users QoS in the data center environment of cloud computing. It analyzes the current state of the running tasks according to the results of the QoS prediction assigned by the ARIMA forecasting model. Then we calculate the scheduling policy with the algorithm combined particle swarm optimization(PSO) and gravitational search algorithm(GSA) according to the analyses of QoS status. This thesis proposes a retaining virtual machine algorithm On the basis of the original algorithm. The retaining algorithm takes the reference to the network congestion control algorithm. Experiment shows that the algorithm could reduce the energy consumption of 9.26% than the original hybrid algorithm. |
| |
| Keywords: | data center of cloud computing QoS workflow scheduling ARIMA PSO GSA |
| 本文献已被 万方数据 等数据库收录！ |
| 点击此处可从《电视技术》浏览原始摘要信息 |
|
点击此处可从《电视技术》下载全文 |
