臺灣博碩士論文加值系統

資料發掘是近年來相當熱門的一個研究領域，因為自電腦發明以後，在電腦裡累積了大量的資料，如何從這些資料中發掘出有用的資訊，以提升企業競爭力、創造企業財富，日益受到重視。
OS/390是IBM電腦主機的作業系統，SMF(System Management Facility)則是OS/390上的一個系統管理工具，紀錄每項工作的重要資訊，並產生系統日誌。分析SMF資料可以了解系統的行為模式，讓系統工程師能分析並預測系統資源使用情形以提升系統效率。因為系統效率關係到一個企業的競爭力，所以如何提升系統效率殊為重要。
在本篇論文中提出以模糊灰色預測(FGP: Fuzzy Grey Prediction)，來預測系統資源的使用趨勢。即以OS/390的系統日誌資料做資料發掘，依系統日誌中資料的規律性先做事先分類，並模糊化，再用灰色系統理論來預測出電腦系統資源的使用趨勢，以供系統工程師調整系統資源分配之用。
根據實驗顯示，以模糊灰色預測對電腦日誌資料做資料發掘時，其準確率可達90%以上，由此可知，在對電腦主機系統資源做預測時，模糊灰色預測不失為一個可供選擇的好方法。

Data mining is quite generally discussed in the recent years. The data which stores in the computer increases. How to find useful information from these stored data becomes a very import mission, because successful data mining can create the enterprise’s commercial benefits and powerful advantages over its trade enemy.
The operating system performed in the mainframe of IBM is OS/390. SMF(System Management Facility) is the tool of system management for OS/390. It records the important information of every job to produce system log. By analyzing the data of SMF, the system engineer can realize the behavior model of OS/390 and predict the utilization of system resources in order to promote the system performance. The system efficiency is crucial to an enterprise’s commercial interests. Therefore, how to improve the system efficiency is quite important.
We mine the data of OS/390 system log to find its rule. And then the data can be classified and become fuzzy. Thereby, the system engineer can predict the utilization of system resources in order to allot the system resources.
According to the results of our experiments, the accuracy reaches as high as 90%, if we mine the data of computer system log with Fuzzy-Grey Prediction. Therefore, we can jump into the conclusion that Fuzzy-Grey Prediction is an efficient theory to predict the data on system resources of computer mainframe.

第一章緒論 1
1.1 前言 1
1.2 研究動機與目的 1
1.3 OS/390簡介 3
1.4 論文架構 5
第二章相關理論討探 6
2.1 資料發掘 6
2.1.1 資料發掘的意義 6
2.1.2 資料發掘架構 8
2.1.3 資料發掘的應用 9
2.1.4 資料發掘的技術 10
2.2 灰色預測 11
2.2.1 灰建模 12
2.2.2 動態灰色預測 17
2.2.3 灰色理論的應用 19
2.3 模糊理論 20
2.3.1 模糊集合、隸屬函數、隸屬度20
2.3.2 模糊理論的應用 22
2.4 模糊隨機預測 22
2.4.1 建模 23
第三章 模糊灰色預測 27
3.1 事先分類 30
3.2 模糊化 31
3.3 模糊灰色預測 32
第四章 實驗與結果分析 34
4.1 實驗 34
實驗1: 34
實驗2: 36
實驗3: 37
實驗4: 38
實驗5: 45
4.2 結果分析 46
第五章 總結 48
5.1 結論 48
5.2 未來展望 48
附 錄 50
以4筆歷史資料做預測 50
參考文獻 57

[1] Ming-Syan Chen、Senior Member、Jiawei Han、Senior Member、Philip S. Yu, “Data Mining: An Overview from a database Perspective”, IEEE trans. Knowledge and Data Engineering Vol. 8, No. 6, pp. 866-883, Dec. 1996.
[2] B. Cheng, “The grey control on industrial process”, Journal of Huangshi College, Vol. 1, pp.11-23, 1986.
[3] Ding-An Chiang, Louis R. Chow, Yi-Fan Wang, “Mining Time Series Data by A Fuzzy Linguistic Summary System”, Fuzzy Sets and Systems, 1998.
[4] Ding-An Chiang, Yi-Fan Wang, Wei Chen, “Knowledge Extraction by A Fuzzy Linguistic Summary Approach”, Computers and Artificial Intelligence, Vol. 17, No. 1, pp. 69-81, 1998.
[5] J. Deng, “Control problems of grey system”, System & Control Letters, Vol. 1, No. 5, pp.288-294, 1982.
[6] J. Deng, “Introduction to grey system theory”, The Journal of Grey System, Vol. 1, pp.1-24, 1989.
[7] U. Fayyad, G. Piatesky-Shapiro and P. Smyth,“The KDD Process for Extracting useful Knowledge from Volumes of Data,” ACM Comm.,Vol. 39, No. 11, pp. 27-34, 1996.
[8] W. Frawley, G. Picatetsky-Shapiro, and C. Matheus, “Knowledge discovery in databases: An overview,” AI Magazine, Fall issue, 1992.
[9] M. Holsheimer and A.P.M. Siebes, ”Data mining: the search for knowledge in database,” Technical Report CS-R9406, CWI, P.O. Box 94079, 1090 BG Amsterdam, The Netherlands, 1994.
[10] C.M.Hong, C.T. Chiang and S.C.Lin,”Design of grey prediction controller based on fuzzy reasoning”, The 2nd Natl. Conf. On Fuzzy Theory & Apple., pp.66-71, 1994.
[11] Yo-Pin Huang, Chi-Chang Huang, “The integration and application of fuzzy and grey modeling methods,” Fuzzy Sets and Systems v78, n1, Feb 26 1996, p107-119.
[12] Yo-Ping Huang, Hung-Chi Chu, “Ractical consideration for grey modeling and its application to image processing”, The Journal of Grey System, 1996, p. 217-233.
[13] J. Huang, H. Wakamatsu and J.F.Gao, “Snowfall prediction based on grey system theory,” The Journal of Grey System, 1991, pp. 141-153.
[14] Michael J. A. Berry Gordon Linoff，“Data Mining Techniques”.
[15] Rob Mattison，“Data Warehousing strategies,Technologies,and Techniques”，Computing MCGraw-Hill.
[16] Willi Meier, Richard Weber and Hans-Jurgen Zimmermann, “Fuzzy data analysis — Methods and industrial applications,” Fuzzy Sets Systems v61, n1, Jan 10 1994, p19-28.
[17] J. Ranade, “MVS Control Blocks”, Hank Murphy.
[18] Abraham Silberschatz、Peter B. Galvin, “Operating System Concepts”, Addison-Wesley Publishing Company.
[19] Munakata Toshinor, Jani Yashvant, “Fuzzy Systems: An Overview,” Communications of the ACM v37, n3, Mar 1994, p69-76.
[20] Hong-Tzer Yang, Tian-Chyi Liang, Kuang-Rong Shih and Ching-Lien Haug,”Power system yearly peak load forecasting: A grey system modeling approach”, Proceedings of the 1995 International Conference on Energy Management and Power Delivery, EMPD ’95, Part I(of 12), Singapore, 1995, IEEE, Piscataway, NJ, USA, pp261-266.
[21] Yi-Fan Wang,”Predicting CPU Utilization by Fuzzy Stochastic Prediction,” III-B1-1~ III-B1-11 實踐大學管理學院第一屆學術暨實務研討會，台北，台灣，1999年5月29日。
[22] 朱光啟，”IBM主機系統效率資料之圖形化”，淡江大學84年碩士論文。
[23] 陳嘉欉，”切換式灰色預測控制系統之設計”，淡江大學86年碩士論文。
[24] 蘇木春、張孝德，“機器學習:類神經網路、模糊系統以及基因演算法則”，全華出版。
[25] 吳漢雄、鄧聚龍、溫坤禮，“灰色分析入門”，高立出版。
[26] 郭洪、鄧聚龍，“灰預測原理與應用”，全華出版。
[27] 黃有評、吳國威、史開泉，“灰色信息關係論”，全華出版。
[28] 廖朝軒，徐世忠，李上畦，”灰色理論在中短期年需水量預測之應用”，第一屆灰色系統理論與應用研討會，第187-197頁，高雄，台灣，1996年11月。
[29] 陳志良、黃永發、溫志宏、溫志超，”GM(1,1)建模所需最少點數之評論”，1998年灰色系統理論與應用研討會，第117-126頁，彰化，台灣，1998年11月。
[30] 蔣定安、王亦凡、林丕靜、施奇宏、李紹綸，”IBM主機系統資源之動態模糊灰色預測”， 1998年灰色系統理論與應用研討會，第353-360頁，彰化，台灣，1998年11月。