不考慮過期海量資料之約略集合規則歸納於再生節能設備推廣

Rough Set Based Rule Induction with Elimination of Outdated Big Data in Renewable Energy Equipment Promotion

王培安(Pei-An Wang)

指導教授 ： 黃俊哲

國立暨南國際大學/管理學院/資訊管理學系/碩士(2014年)

摘要

能源問題已成為了二十一世紀以來的重大挑戰，世界各國都在尋求解決方案，發展可再生能源是目前解決能源危機的重要手段之一。可再生能源的數據具有多屬性及跨不同領域的特性，許多研究透過資料探勘的方式從可再生能源數據中取得可行的規則歸納，藉此達到長遠可行的能源規劃方案。對於多屬性問題及規則歸納的解決方式，約略集合是一個非常適合的方法。此外，海量資料的出現，改變了以往的資料探勘模式，由於海量資料的特性，資料在重複利用時，應該避免不斷的重新計算造成資源的浪費，對於處理不斷變動的海量資料，動態資料庫的演算方式成為了不可或缺的一環，然而，過去對於海量資料動態資料庫的研究，往往著重在增量演算的方式，卻忽略了會有減量運算的情況發生。因此，本研究將會從海量資料的角度出發，探討以約略集合減量運算歸納規則應用於可再生能源的推廣評估方案，並提出案例佐證。

關鍵字

約略集合 ； 海量資料 ； 可再生能源 ； 減量演算法

並列摘要

Energy problem has become a major challenge in twenty-first century, countries around the world are looking for solutions. Development of renewable energy is one of the important means to solve the energy crisis. Renewable energy data has the characteristics of multi-attribute and across different areas, many studies use data mining from renewable energy data to get viable rule induction, thereby achieve a long-term energy planning. For multi-attribute problems and rule induction solution, rough set is a very suitable method.
In addition, appears of big data change the previous data mining mode. Because of the characteristics of big data, when data reuse should be avoided constantly recalculate. For handle the changing big data, dynamic database calculus became an integral part. However, past studies for big data dynamic database tend to focus on incremental manner, but has neglected decrement situation. Therefore, this study will be from the perspective of big data to explore rough set rule induction whit decrement operation assessment program used in the promotion of renewable energy sources and presents case evidence.

並列關鍵字

rough set ； big data ； renewable energy ； decremental algorithms

參考文獻

Abed-Elmdoust, A., & Kerachian, R. (2012). Wave height prediction using the rough set theory. Ocean Engineering, 54, 244-250.

Ackermann, T. (2005). Wind power in power systems (Vol. 140): Wiley Online Library.

Afshani, P., & Chan, T. M. (2006). Dynamic connectivity for axis-parallel rectangles Algorithms–ESA 2006 (pp. 16-27): Springer.

Aguado, E., Burt, J. E., Rohli, R. V., & Schmidlin, T. W. (2007). Understanding weather and climate: Pearson Prentice Hall.

An, A., Shan, N., Chan, C., Cercone, N., & Ziarko, W. (1996). Discovering rules for water demand prediction: an enhanced rough-set approach. Engineering Applications of Artificial Intelligence, 9(6), 645-653.