普及運算是各種運算技術的延伸, 包含了行動運算,分散式運算以及無線感測網路技術. 然而目前並沒有一些標準或規定來定義普及運算的環境以及相關的技術. 所以在如此複雜的環境中, 我們建立了一個模型來描述資源管理的機制. 首先我們建立了一個集中式的資源管理的架構, 用來描述環境中的各種資源以及裝置. 接下來在模型中我們定義了適用於普及運算環境中裝置間溝通的格式. 根據現有裝置的特性和限制, 我們定義了一個排程的問題, 並試圖找到解決的方法. 然而根據我們的資料蒐集之後, 我們發現古典的排程理論已有類似的問題被探討過, 那就是JSSP (Job-Shop Scheduling Problems). 我們證明要排程普及運算環境中的服務的問題難度是一個NP-hard的難度. 最後我們提出討論, 說明基於各種裝置的特性, 我們無法即時得到一個最佳的排程 來安排資源給普及運算環境中的服務. 最後我們提出一個實例來驗證我們提出的模型的確可以描述資源管理的機制,
並安排資源給需要的服務.

We proposed a centralized model to manage all the resources in the ubiquitous computing environments, including device accessing time and heterogeneous network bandwidth utilization.We defined the ubiquitous service profile and analysed characteristics of smart device and wireless networks. We took advantages of each wireless networks in constructing our ubiquitous networking. We also found the linkage from our scheduling problem to Job-Shop scheduling Problem. Proposing model is consist of two parts: 3R and scheduling model. 3R is for information collection then establishing scheduling model for ubiquitous services. We provide a well-defined scheduling problem and mapping it to Job Shop Scheduling Problem. Further, we have proven our scheduling problem is a NP-hard problem. We also provide the discussion to the reason why our scheduling problem became a NP-hard problem.
A scenario to illustrate the detail of resource management will be present in the end

[1] MarkWeiser. The computer for the 21st century. In Scienti c American,
volume 265, pages 66{75, 1991.
[2] M. Satyanarayanan. Pervasive computing: Vision and challenges. In
IEEE Personal Communications, pages 10{17, 2001.
[3] Ian Foster, Carl Kesselman, Craig Lee, Bob Lindell, Klara Nahrstedt,
and Alain Roy. A distributed resource management architecture that
supports advance reservations and co-allocation. In IN PROCEEDINGS
OF THE INTERNATIONAL WORKSHOP ON QUALITY OF SER-
VICE, pages 27{36, 1999.
[4] Anandha Gopalan and Taieb Znati. Sara: A service architecture for
resource aware ubiquitous environments. Pervasive Mob. Comput., 6(1),
2010.
[5] Krzysztof Gajos, Luke Weisman, and Howard Shrobe. Design principles
for resource management systems for intelligent spaces. In In Proceedings
of The Second International Workshop on Self-Adaptive Software, pages
198{215, 2001.
[6] Ippokratis Pandis, John Soldatos, Alexander Paar, Jurgen Reuter,
Michael Carras, and Lazaros Polymenakos. An ontology-based frame-
work for dynamic resource management in ubiquitous computing envi-
ronments. In ICESS '05: Proceedings of the Second International Con-
ference on Embedded Software and Systems, pages 195{203, 2005.
[7] Ying-Hsiu Liao. A QoS-Driven Approach for Service-Oriented Device
Arrangement in Resource-Constrained Ubiquitous Environments. PhD
thesis, National Cheng Kung University, 2008.
[8] Peter Brucker. Scheduling Algorithms. Springer, 2007.
[9] Milo` `eda. Mathematical models of
ow shop and job shop scheduling
problems. In International Journal of Applied Mathematics and Com-
puter Sciences, volume 4, pages 241{246.
[10] Shakhlevich Sotskov. NP-hardness of shop-scheduling problems with
three jobs. 1995.
[11] Emma Hart and Peter Ross. A heuristic combination method for solving
job-shop scheduling problems. In PPSN V: Proceedings of the 5th In-
ternational Conference on Parallel Problem Solving from Nature, pages
845{854. Springer-Verlag, 1998.