计算机应用 ›› 2012, Vol. 32 ›› Issue (12): 3291-3294.DOI: 10.3724/SP.J.1087.2012.03291

• 先进计算 • 上一篇    下一篇

云计算中虚拟资源的智能多代理设计

王留洋,俞扬信,周淮   

  1. 淮阴工学院 计算机工程学院,江苏 淮安 223003
  • 收稿日期:2012-06-21 修回日期:2012-08-07 发布日期:2012-12-29 出版日期:2012-12-01
  • 通讯作者: 王留洋
  • 作者简介:王留洋(1974-),男,江苏淮阴人,副教授,硕士,主要研究方向:信息管理、信息系统、智能化信息处理;〓俞扬信(1970-),男,江苏泰州人,副教授,硕士,主要研究方向:信息管理、信息系统、智能化信息处理、知识组织;〓周淮(1973-),男,江苏淮安人,副研究馆员,硕士,主要研究方向:信息管理、信息系统、数字图书馆。
  • 基金资助:
    淮安市工业支撑计划

Design of intelligent multi-Agent for virtual resource in cloud computing

WANG Liu-yang,YU Yang-xin,ZHOU Huai   

  1. Faculty of Computer Engineering, Huaiyin Institute of Technology, Huai’an Jiangsu 223003,China
  • Received:2012-06-21 Revised:2012-08-07 Online:2012-12-29 Published:2012-12-01
  • Contact: WANG Liu-yang

摘要: 针对随着网络数据传输速度和复杂性的不断增加,网络管理变得更加困难的现状,提出了一种虚拟资源的智能多代理模型。描述了虚拟资源的智能多代理的处理过程,讨论了不同代理的处理机制。通过分析用户上下文和系统状态,可实时地分析社会媒体资源。根据虚拟资源的使用类型,对用户上下信息的需求进行分析和推断,自动地给用户分配资源。采用云计算中虚拟资源动态调度方法及MovieLens系统评估该模型,结果证明所提出的模型具有较好的性能,可实现虚拟资源的动态调度,动态地实现负载均衡,使云计算中的虚拟资源得到高效的利用。

关键词: 虚拟资源, 智能多代理, 云计算, 动态调度

Abstract: Network management becomes more difficult for the increase of data transmission speed and network complexity, so the paper presented an intelligent multi-Agent model for virtual resource, described the process of the multi-Agent to virtual resource, and discussed the processing mechanism of different Agent. The proposed model was able to analyze social media resources in real-time by user context and system state. It automatically allocated resources suitable for users according to the virtual resource usage type and the information demand analysis of user context. The model was evaluated by dynamic scheduling method of virtual resources in cloud computing and the MovieLens system. The results show that the proposed model has better performance, can achieve the dynamic scheduling and load balancing of virtual resource, so that users can utilize efficiently virtual resource in the cloud computing.

Key words: virtual resource, intelligent multi-Agent, cloud computing, dynamic scheduling