透過您的圖書館登入
IP:13.59.82.167
  • 學位論文

基於雲端電器辨識模型之電力特徵值權重傳輸方法

Power Features Weight Transmission Method of Electrical Identification Model Based on Cloud

指導教授 : 賴槿峰
若您是本文的作者,可授權文章由華藝線上圖書館中協助推廣。

摘要


近年來隨著智慧聯網的發達,智慧家庭越來越受到重視,廠商致力於開發智慧家電,一般使用者也樂見其成。但由於一般使用者家中,太多電器仍屬於傳統電器,無法與其他智慧家電溝通,構成智慧化系統。雖然可以透過智慧插座讓傳統電器智慧化,解決這個問題,但是卻又會產生電器種類辨識之問題。智慧插座雖可透過使用者人工設定電器名稱,但是卻可能發生電器名稱不一致、輸入錯誤等問題,所以智慧插座擁有自動辨識電器之能力是相當重要的。鑑此,本論文提出一電力負載辨識架構,將電力資料轉換成實功率與其他16項電力特徵值,利用各特徵值之相異以辨識電器,另外,在透過電力特徵值權重加權公式,將特徵值區分,以過濾對某一電器而言,較不重要之特徵值,以減少資料量並提高辨識率。

並列摘要


As the Internet of Things’ development in the recent years, smart home is more highly valued. Manufacturers are devoted to create smart appliances and users in general are glad to see it happen.But most the appliances in usual user’s house are traditional. They can’t communicate with other smart appliances to make a smart system.Although this problem can be solved by using smart outlet, another problem about identifying appliances’ type happen. The appliances’ name can be set in the smart outlet by manual, but some problem may happen like input error or names not consistent. So it is important to let smart outlet has the ability to identify appliance automatically.Due to these circumstances, this thesis gives an architecture about electrical load identify. The power information will be converted to real power and the other 16 kinds of power features and the differences will be used to identify the appliance. Moreover, by power features weighted formula ,we can raise the identifying rate by reduce the information from those features and removing the unimportant ones for some appliances.

參考文獻


[20] 陳瑋哲,“動態電力特徵值之區段選取與負載辨識度關係研究”,國立成功大學工程科學系
[5] Muhammad RaisulAlam, Mamun Bin IbneReaz,MohdAlauddinMohd Ali, “A Review of Smart Homes—Past, Present, and Future”,inSystems, Man, and Cybernetics, Part C: Applications and Reviews, IEEE Transactions on,pp.1190-1203,Nov. 2012
[9] Goran Horvat, DavorVinko, Drago Zagar, “Household power outlet overload protection and monitoring using cost effective embedded solution”, in Embedded Computing (MECO), 2013 2nd Mediterranean Conference on,pp.242-246,15-20 June 2013
[10] W. Frawley, G. Piatetsky-Shapiro and C. Matheus, “Knowledge Discovery inDatabases: An Overview,”AAAI/MIT Press, 1991.
[11] D. Hand, H. Mannila and P. Smyth, “Principles of Data Mining,” MIT Press, 2003.

延伸閱讀