行動計算網格環境下資源覺知工作排程演算法

Resource-Aware Task Scheduling Algorithm on Mobile Computational Grid Environment

張閎翔(Hung-Hsiang Chang)

指導教授 ： 莊東穎

共同指導教授 ： 張玉山

國立臺北大學/電機資訊學院/通訊工程研究所/碩士(2008年)

摘要

因無線通訊與網格技術的進步，行動網格已成為重要的研究議題。而計算網格在
行動計算中經常扮演著重要的角色。由於行動設備的特性，如：有限的電能、間歇
性斷線、不穩定的頻寬…等特性，使得行動計算網格針對上述特性，提出一個高效
率及可靠的機制來處理行動應用。目前計算網格中的工作排程方法，並未考慮行動
設備的特性，故無法進一步提供穩定及快速處理行動計算應用。
此篇論文中提出一個以行動代理人為基礎的行動計算網格架構，並在此架構下提
出一個工作排程演算法。希望用戶端可以透過行動計算網格，處理用戶端的行動計
算應用。我們所提出的工作排程演算法目希望達到1.透過此演算法，找到適合的工
作順序，並且選出較穩定且快速的行動網格節點處理行動應用。2.透過此演算法，
選擇出較穩定的行動網格節點，避免處理工作時發生錯誤，導致不必要電能與時間
消耗，進而提升工作效率。3.避免連續使用特定行動網格節點，造成特定行動網格
節點嚴重的電能損耗，提升整體行動網格節點的存活率。

關鍵字

工作排程演算法 ； 行動網格

並列摘要

As advance of wireless communication technology and grid technology, mobile grid
becomes increasingly important research topics. Computational grid usually plays an
important role in mobile-computing application. As well known, mobile device has some
inherent characteristics, such as limited energy, intermittent connection, and versatile
bandwidth. Mobile computational grid need to take these issues into account. Existing task
scheduling algorithm proposed for wired networks did not consider these issues mentioned
above, then it did not provide stable and fast execution mobile-computing application.
In the paper, we propose a Resource-Aware Task Scheduling algorithm, named RATS,
on the mobile computational grid environment for mobile clients executing
mobile-computing application. Based on RATS, mobile clients find suitable order of task
and choose stable and fast mobile grid node to execute mobile-computing application;
mobile clients choose stable mobile gird node to avoid time of fault execution; mobile
clients avoid to successively use specific mobile grid node that consumes energy seriously,
then entire mobile grid node improve survival rate.

並列關鍵字

Mobile Grid ； Task Scheduling

參考文獻

[1] Foster, C. Kesselman and S. Tuecke,　“The Anatomy of the Grid: Enabling Scalable Virtual Organizations”,　International Journal of High Performance Computing Applications,　2001,　pp.200-222.

[3] Agarwal, D. Norman and A. Gupta,　“Wireless grids: approaches, architectures and technical challenges”,　MIT Sloan School of Management,　2004.

[4] D. Chu and M. Humphrey,　“Mobile OGSI.NET: grid computing on mobile devices”,　IEEE/ACM International Workshop on Grid Computing,　2004,　pp.182-191.

[7] L. McKnight, J. Howison and S. Bradner,　“Wireless Grids--Distributed Resource Sharing by Mobile, Nomadic, and Fixed Devices”,　IEEE INTERNET COMPUTING,　2004,　pp. 24-31.

[8] Huang Chang-Qin; Zhu Zhi-Ting; Wu Yong-He; Xiao Zheng-Hong,　“Power-Aware Hierarchical Scheduling with Respect to Resource Intermittence in Wireless Grids”,　Machine Learning and Cybernetics, 2006 International Conference on,　2006,　pp. 693-698.