摘要(英) |
The most common method for complementing the missing value of the equipment in the energy management system is linear interpolation. In view of this method, the data value (power consumption, timely power consumption, power factor, etc.) will be presented when the disconnection time is long. The waveform or slope is smoothed, which is used for subsequent demand calculation and contract capacity setting, which in turn affects the results of electricity cost analysis calculation and regression model establishment and subsequent energy conservation performance prediction.
This study uses KNN Regression, SVR, MLP Regression , and ARIMA method supplements the energy data collected by the energy management system. The purpose is to compare and compare the above methods with the linear interpolation method. The results of the four methods are compared and analyzed using MAPE, and then the algorithm performs future system complement value improvement.
The results of this experiment use the K-nearest neighbor regression method to obtain a better complement method for the continuous 1 day training data set.
The voltage uses KNN Regression K=140, the current uses SVR cost =30, epsilon 0.3, the power factor uses SVR cost =60, epsilon 0.1, the power consumption uses X-12-ARIMA, and the immediate power consumption uses SVR cost =90. Epsilon 0.2 gets a better complement than the original LI.
|
參考文獻 |
中文文獻
[1]. 上報快訊陳婕翎(December 26 19:40:00, 2017),【2017國內十大新聞Top 7】815全台大停電仍不停下推動能源轉型的腳步,Retrieved December 2 17:30:00,2018,from https://www.upmedia.mg/news_info.php?SerialNo=31389
[2]. MBA lib 智庫.百科,能源管理系統,from https://wiki.mbalib.com/zh-tw/%E8%83%BD%E6%BA%90%E7%AE%A1%E7%90%86%E7%B3%BB%E7%BB%9F
[3]. 曾憲威(任教於德霖技術學院電腦與通訊工程系)、李揚漢、顏良祐(以上兩位任教於淡江大學電機工程學系)(March 27,2014) ,節能監控系統應用, Retrieved December 2 17:30:00, 2018,from http://scimonth.blogspot.com/2014/03/blog-post_6415.html
[14]. 黃瀞萱,支援向量迴歸結合真實波動分類預測 股票指數,臺北市立大學資訊科學系碩士班碩 士論文,2013。
[20]. 台灣電力公司,導線失竊與違章用電整合系統建置 與示範研究https://www.taipower.com.tw/upload/314/2017112317030772035.pdf
英文文獻
[4]. Little, Roderick J. A., and Rubin, Donald B. 2002. Statistical Analysis with Missing Data 2nd ed. New York: John Wiley & Sons.
[5]. Little, R.J.A. and Rubin, D.B. (1987) Statistical Analysis with Missing Data. John Wiley & Sons, New York.
[6]. Taiwan Power Company, http://www.taipower.com.tw, 2019
[7]. H. Junninen, H. Niska, K. Tuppurainen, J. Ruuskanen, M. Kolehmainen, "Methods for imputation of missing values in air quality data sets", Atmos. Environ., vol. 38, no. 18, Jun. 2004.
[8]. "Uniform Business Practices for Unbundled Electricity Metering-Volume 2", Edision Electric Institute, Dec. 2000.
[9]. Jakub Langhammer and Julius Česák. 2016. Applicability of a Nu-Support Vector Regression Model for the Completion of Missing Data in Hydrological Time Series
[10]. Minkyung Kim 1 ID , Sangdon Park 1 , Joohyung Lee 2,*, Yongjae Joo 3 and Jun Kyun Choi 1.Learning-Based Adaptive Imputation Method with kNN Algorithm for Missing Power Data
[11]. Peppanen, Jouni, Reno, Matthew J., Zhang, Xiaochen, and Grijalva, Santiago. Handling Bad or Missing Smart Meter Data through Advanced Data Imputation.. United States: N. p., 2016. Web. doi:10.1109/ISGT.2016.7781213.
[12]. Vladimir N. Vapnik. The Nature of Statistical Learning Theory. New York: Springer, 1995
[13]. Vladimir Vapnik , Steven E. Golowich , Alex Smola. Support Vector Method for Function Approximation, Regression Estimation, and
Signal Processing. Neural Information Processing Systems Conference, 1997.
[15]. Alex J. Smola and Bernhand Sch ̈lkopf. A tutorial on support vector regression. Statistics and Computing: Springer, 2003.
[16]. Bishop, C.M. (1995). Neural Networks for Pattern Recognition. Oxford University Press, Oxford, United Kingdom
[17]. Chambers, R. (2003). Overview of the methods investigated by the EUREDIT project. http://www.cs.york.ac.uk/euredit/
[18]. H. Tram, Technical and operation considerations in using Smart Metering for outage management. Transmissions and Distribution Conference and Exposition, 2008, T&D. IEEE/PES, pp. 1-3
[19]. K. Sridharan ; N. Schulz, Outage Management through AMR Systems Using an Intelligent Data Filter. IEEE Transactions on Power Delivery, 2001, Vol. 16(4), pp. 669-675
[21]. Alex J. Smola and BernhardScholkopf, August 2004 ,“A tutorial on support vector regression”, Statistics and Computing, Volume 14 Issue 3 pp. 199-222
[22]. "Support vector machines experts for time series forecasting" ,Pages 199-222
[23]. Minkyung Kim 1 ID , Sangdon Park 1 , Joohyung Lee 2,*, Yongjae Joo 3 and Jun Kyun Choi 1 “Learning-Based Adaptive Imputation Method with kNN Algorithm for Missing Power Data”, Korea Electric Power Research Institute, Daejeon 305-760, Korea
[24] US Census Bureau, X-12-ARIMA Reference Manual Version 0.2.10
http://www.census.gov/srd/www/x12a/, 2013
|