1. NCCU Academic Hub
  2. Publications
  3. College of Science
  4. Theses
  5. Item

Publications-Theses

Article View/Open

Publication Export

Google ScholarTM

NCCU Library

Citation Infomation

Related Publications in TAIR

題名 基於EEMD之倒傳遞類神經網路方法對用電量及黃金價格之預測
Forecasting electricity consumption as well as gold price by using an EEMD-based Back-propagation Neural Network Learning Paradigm
作者 蔡羽青
Tsai, Yu Ching
貢獻者 蕭又新
Shiau, Yuo Hsien
蔡羽青
Tsai, Yu Ching
關鍵詞 總體經驗模態分解法
倒傳遞類神經網路
用電量預測
黃金價格預測
超短時間負荷預測
Ensemble Empirical Mode Decomposition
Back-propagation Neural Network
electricity consumption forecasting
gold price forecasting
very-short term load forecasting
日期 2011
上傳時間 4-Sep-2013 15:28:15 (UTC+8)
摘要 本研究主要應用基於總體經驗模態分解法(EEMD)之倒傳遞類神經網路(BPNN)預測兩種不同的非線性時間序列數據，包括政大逐時用電量以及逐日歷史黃金價格。透過EEMD，這兩種資料會分別被拆解為數條具有不同物理意義的本徵模態函數(IMF)，而這讓我們可以將這些IMF視為各種影響資料的重要因子，並且可將拆解過後的IMF放入倒傳遞類神經網路中做訓練。

另外在本文中，我們也採用移動視窗法作為預測過程中的策略，另外也應用內插法和外插法於逐時用電量的預測。內插法主要是用於補點以及讓我們的數據變平滑，外插法則可以在某個範圍內準確預測後續的趨勢，此兩種方法皆對提升預測準確度占有重要的影響。

利用本文的方法，可在預測的結果上得到不錯的準確性，但為了進一步提升精確度，我們利用多次預測的結果加總平均，然後和只做一次預測的結果比較，結果發現多次加總平均後的精確度的確大幅提升，這是因為倒傳遞類神經網路訓練過程中其目標為尋找最小誤差函數的關係所致。
In this paper, we applied the Ensemble Empirical Mode Decomposition (EEMD) based Back-propagation Neural Network (BPNN) learning paradigm to two different topics for forecasting: the hourly electricity consumption in NCCU and the historical daily gold price. The two data series are both non-linear and non-stationary. By applying EEMD, they were decomposed into a finite, small number of meaningful Intrinsic Mode Functions (IMFs). Depending on the physical meaning of IMFs, they can be regarded as important variables which are input into BPNN for training.

We also use moving-window method in the prediction process. In addition, cubic spline interpolation as well as extrapolation as our strategy is applied to electricity consumption forecasting, these two methods are used for smoothing the data and finding local trend to improve accuracy of results.

The prediction results using our methods and strategy resulted in good accuracy. However, for further accuracy, we used the ensemble average method, and compared the results with the data produced without applying the ensemble average method. By using the ensemble average, the outcome was more precise with a smaller error, it results from the procedure of finding minimum error function in the BPNN training.
參考文獻 Ajay Shekhar Pandey, Devender Singh, and Sunil Kumar Sinha, 2010. Intelligent Hybrid Wavelet Models for Short-Term Load Forecasting. IEEE transactions on power systems, VOL. 25, NO. 3, August 2010.

Akgiray, V., G.G. Booth, J.J. Hatem, and C. Mustafa, 1991. Conditional Dependence in Precious Metal Prices. The Financial Review, 26, 367-386.

Chen, M.-C., Wei, Y, 2010. Exploring time variants for short-term passenger flow. J. Transp. Geogr. doi:10.1016/j.jtrangeo.2010.04.003

Cummings, D.A.T., Irizarry, R.A., Huang, N.E., Endy, T.P.,
Nisalak, A., Ungchusak, K., Burke, D.S., 2004. Travelling waves in the occurrence of dengue haemorrhagic fever in Thailand. Nature 427 (6972), 344–347.

En Tzu Li, 2011. TAIEX Option Trading by using EEMD-based Neural Network Learning Paradigm. Master Thesis of Graduate Institute of Applied Physics, College of Science NCCU.

FENG Ping, DING Zhi-hong, HAN Rui-guang, ZHANG Jian-wei. 2009. Precipitation-runo forecasting ANN model based on EMD. Systems Engineering-Theory & Practice, Vol.29, No.1, Jan., 2009.

G.A. Adepoju, M.Sc., S.O.A. Ogunjuyigbe, M.Sc., and K.O. Alawode, B.Tech. Application of Neural Network to Load Forecasting in Nigerian Electrical Power System. The Pacific Journal of Science and Technology Volume 8. Number 1. May 2007 (Spring).

Hwang, P.A., Huang, N.E., Wang, D.W., 2003. A note on analyzing nonlinear and non-stationary ocean wave data. Applied Ocean Research 25 (4), 187–193.

Huang, N.E., Shen, Z., Long, S.R., Wu, M.C., Shih, H.H., Zheng, Q., Yen, N.-C., Tung, C.C., Liu, H.H., 1998. The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis. Proceedings of the Royal Society of London A 454 (1971), 903–995.

Huang, N.E., Wu, M.L., Qu, W.D., Long, S.R., Shen, S.S.P., 2003b. Applications of Hilbert–Huang transform to nonstationary financial time series analysis. Applied Stochastic Models in Business and Industry 19, 245–268.

Hari Seetha and R. Saravanan, 2007. Short Term Electric Load Prediction Using Fuzzy BP. Journal of Computing and Information Technology - CIT 15, 2007, 3, 267–282.

Hong Ying Yang, Hao Ye, Guizeng Wang, Junaid Khan, Tongfu Hu, 2005. Fuzzy neural very-short-term load forecasting based on chaotic dynamics reconstruction. Chaos, Solitons & Fractals Volume 29, Issue 2, July 2006, Pages 462-469

Hamid S. A. and Iqbal Z., Using neural networks for
forecasting volatility of S&P 500 Index futures prices, Journal of Business Research, 2004, 57: 1116-112

James W. Taylor. An evaluation of methods for very short-term load forecasting using minute-by-minute British data, 2008. International Journal of Forecasting, 24 (4). pp. 645-658. ISSN 0169-2070

K.Hornik, M.Stinchocombe, 1989. H.White, Multilayer feedforward networks are universal approximators,NeuralNetworks2 (1989) 359–366.

Li, Q.S., Wu, J.R., 2007. Time–frequency analysis of typhoon effects on a 79-storey tall building. Journal of Wind Engineering and Industrial Aerodynamics 95 (12), 1648–1666.

Liang, H., Lin, Q.-H., Chen, J.D.Z., 2005. Application of the empirical mode decomposition to the analysis of esophageal manometric data in gastro esophageal reflux disease. IEEE Transactions on Biomedical Engineering 52 (10), 1692–1701.

Lean Yu, Shouyang Wang, Kin Keung Lai., 2008. Forecasting crude oil price with an EMD-based neural network ensemble learning paradigm. Energy Economics 30 (2008) 2623–2635.

Lean Yu, ShouyangWanga, KinKeungLai, FenghuaWenc, 2010. A multiscale neural network learning paradigm for financial crisis forecasting. Neuro computing, 73:716-725

Liu, K. Subbarayan, S. Shoults, R.R. Manry, M.T. Kwan, C. Lewis, F.I. Naccarino, J. Autom. & Robotics Res. Inst., Texas Univ., Arlington, TX, 1996. Comparison of very short-term load forecasting techniques. IEEE Transactions on Power Systems. Vol. 11. No. 2. May 1996

Mirmirani, S. and H.C. L, 2004. Gold Price, Neural Networks and Genetic Algorithm, Computational Economics, 23, 193-200.

Mendelsohn L., Preprocessing data for Neural Networks, 1993. Tech Anal Stocks Commod, 1993:52-58

Mohsen Hayati and Yazdan Shirvany, 2007. Artificial Neural Network Approach for Short Term Load Forecasting for Illam Region. World Academy of Science, Engineering and Technology 28 2007

N.X. Jia, R. Yokoyamaa, Y.C. Zhoub, Z.Y. Gaoc, 2001. A flexible long-term load forecasting approach based on new dynamic simulation theory — GSIM. International Journal of Electrical Power & Energy Systems Volume 23, Issue 7, October 2001, Pages 549-556

Nahi Kandil, Rene´ Wamkeue, Maarouf Saad, Semaan Georges, 2006. An efficient approach for short term load forecasting using artificial neural networks. International Journal of Electrical Power & Energy Systems Volume 28, Issue 8, October 2006, Pages 525-530.

Ray Ruichong Zhang, M.ASCE; Shuo Ma; Erdal Safak, M.ASCE; and Stephen Hartzell., 2003. Hilbert-Huang Transform Analysis of Dynamic and earthquake motion recordings. Journal of Engineering Mechanics, Vol. 129, No. 8, pp. 861-875.

Ray Ruichong Zhang, Shuo Ma, and Stephen Hartzell., 2003. Signatures of the Seismic Source in EMD-Based Characterization of the 1994 Northridge, California, Earthquake Recordings. Bulletin of the Seismological Society of America; February 2003; v. 93; no. 1; p. 501-518.

Ruqiang Yan, Student Member, IEEE, and Robert X. Gao, Senior Member,IEEE., 2006. Hilbert–Huang Transform-Based Vibration Signal Analysis for Machine Health Monitoring. IEEE Transactions on instrumentation and measurement, Vol. 55, No. 6.

Ruey-Hsun Liang, Ching-Chi Cheng, 2002. Short-term load forecasting by a neuro-fuzzy based approach. International Journal of Electrical Power & Energy Systems Volume 24, Issue 2, February 2002, Pages 103-111

Shahriar Shafiee and ErkanTopal, 2010. An overview of global gold market and gold price forecasting. Resources Policy Volume 35, Issue 3, September 2010, Pages 178-189.

Stephen A. Baker and Roger C. van Tassel, 1985. Forecasting the price of gold: A fundamentalist approach Atlantic Economic Journal Volume 13, No. 4, 43-51

Wu, Z., and N. E Huang, 2009. Ensemble Empirical Mode Decomposition: a noise-assisted data analysis method. Advances in Adaptive Data Analysis. Vol.1, No.1. 1-41.

Wei SUN, 2010. Research on GA-SVM Model for Short Term Load Forecasting Based on LDM-PCA Technique. Journal of Computational Information Systems 6:10 (2010) 3183-3189.

Yen-Rue Chang, 2011. Non-stationary time series analysis by using Hilbert-Huang transform: electricity consumption and gold price volatility. Master Thesis of Graduate Institute of Applied Physics, College of Science NCCU.
描述 碩士
國立政治大學
應用物理研究所
98755011
100
資料來源 http://thesis.lib.nccu.edu.tw/record/#G0098755011
資料類型 thesis
dc.contributor.advisor 蕭又新zh_TW
dc.contributor.advisor Shiau, Yuo Hsienen_US
dc.contributor.author (Authors) 蔡羽青zh_TW
dc.contributor.author (Authors) Tsai, Yu Chingen_US
dc.creator (作者) 蔡羽青zh_TW
dc.creator (作者) Tsai, Yu Chingen_US
dc.date (日期) 2011en_US
dc.date.accessioned 4-Sep-2013 15:28:15 (UTC+8)-
dc.date.available 4-Sep-2013 15:28:15 (UTC+8)-
dc.date.issued (上傳時間) 4-Sep-2013 15:28:15 (UTC+8)-
dc.identifier (Other Identifiers) G0098755011en_US
dc.identifier.uri (URI) http://nccur.lib.nccu.edu.tw/handle/140.119/60096-
dc.description (描述) 碩士zh_TW
dc.description (描述) 國立政治大學zh_TW
dc.description (描述) 應用物理研究所zh_TW
dc.description (描述) 98755011zh_TW
dc.description (描述) 100zh_TW
dc.description.abstract (摘要) 本研究主要應用基於總體經驗模態分解法(EEMD)之倒傳遞類神經網路(BPNN)預測兩種不同的非線性時間序列數據，包括政大逐時用電量以及逐日歷史黃金價格。透過EEMD，這兩種資料會分別被拆解為數條具有不同物理意義的本徵模態函數(IMF)，而這讓我們可以將這些IMF視為各種影響資料的重要因子，並且可將拆解過後的IMF放入倒傳遞類神經網路中做訓練。

另外在本文中，我們也採用移動視窗法作為預測過程中的策略，另外也應用內插法和外插法於逐時用電量的預測。內插法主要是用於補點以及讓我們的數據變平滑，外插法則可以在某個範圍內準確預測後續的趨勢，此兩種方法皆對提升預測準確度占有重要的影響。

利用本文的方法，可在預測的結果上得到不錯的準確性，但為了進一步提升精確度，我們利用多次預測的結果加總平均，然後和只做一次預測的結果比較，結果發現多次加總平均後的精確度的確大幅提升，這是因為倒傳遞類神經網路訓練過程中其目標為尋找最小誤差函數的關係所致。		zh_TW
dc.description.abstract (摘要) In this paper, we applied the Ensemble Empirical Mode Decomposition (EEMD) based Back-propagation Neural Network (BPNN) learning paradigm to two different topics for forecasting: the hourly electricity consumption in NCCU and the historical daily gold price. The two data series are both non-linear and non-stationary. By applying EEMD, they were decomposed into a finite, small number of meaningful Intrinsic Mode Functions (IMFs). Depending on the physical meaning of IMFs, they can be regarded as important variables which are input into BPNN for training.

We also use moving-window method in the prediction process. In addition, cubic spline interpolation as well as extrapolation as our strategy is applied to electricity consumption forecasting, these two methods are used for smoothing the data and finding local trend to improve accuracy of results.

The prediction results using our methods and strategy resulted in good accuracy. However, for further accuracy, we used the ensemble average method, and compared the results with the data produced without applying the ensemble average method. By using the ensemble average, the outcome was more precise with a smaller error, it results from the procedure of finding minimum error function in the BPNN training.		en_US
dc.description.tableofcontents 1. Introduction..........................................7
2. Methodology..........................................12
2.1 Empirical mode decomposition........................12
2.2 Ensemble EMD........................................15
2.3 Artificial neural networks..........................17
2.4 Cubic spline interpolation and extrapolation........23
2.5 EEMD-based neural network learning paradigm.........24
3. Forecasting experiments..............................26
3.1 Data description....................................26
3.1.1. Electricity load data from NCCU..................26
3.1.2. Gold price daily data............................27
3.2 Experiment design...................................29
3.3 Statistical measures................................33
4. Results and discussion...............................37
4.1 Benchmark study.....................................37
4.2 The meaning of IMFs.................................40
4.3 Forecasting performance.............................45
4.4 Performance of ensemble average.....................48
4.4.1. Electricity load data from NCCU..................48
4.4.2. Gold price daily data............................53
5. Conclusion and outlook...............................56
APPENDIX................................................57
Reference...............................................59		zh_TW
dc.format.extent 1327711 bytes-
dc.format.mimetype application/pdf-
dc.language.iso en_US-
dc.source.uri (資料來源) http://thesis.lib.nccu.edu.tw/record/#G0098755011en_US
dc.subject (關鍵詞) 總體經驗模態分解法zh_TW
dc.subject (關鍵詞) 倒傳遞類神經網路zh_TW
dc.subject (關鍵詞) 用電量預測zh_TW
dc.subject (關鍵詞) 黃金價格預測zh_TW
dc.subject (關鍵詞) 超短時間負荷預測zh_TW
dc.subject (關鍵詞) Ensemble Empirical Mode Decompositionen_US
dc.subject (關鍵詞) Back-propagation Neural Networken_US
dc.subject (關鍵詞) electricity consumption forecastingen_US
dc.subject (關鍵詞) gold price forecastingen_US
dc.subject (關鍵詞) very-short term load forecastingen_US
dc.title (題名) 基於EEMD之倒傳遞類神經網路方法對用電量及黃金價格之預測zh_TW
dc.title (題名) Forecasting electricity consumption as well as gold price by using an EEMD-based Back-propagation Neural Network Learning Paradigmen_US
dc.type (資料類型) thesisen
dc.relation.reference (參考文獻) Ajay Shekhar Pandey, Devender Singh, and Sunil Kumar Sinha, 2010. Intelligent Hybrid Wavelet Models for Short-Term Load Forecasting. IEEE transactions on power systems, VOL. 25, NO. 3, August 2010.

Akgiray, V., G.G. Booth, J.J. Hatem, and C. Mustafa, 1991. Conditional Dependence in Precious Metal Prices. The Financial Review, 26, 367-386.

Chen, M.-C., Wei, Y, 2010. Exploring time variants for short-term passenger flow. J. Transp. Geogr. doi:10.1016/j.jtrangeo.2010.04.003

Cummings, D.A.T., Irizarry, R.A., Huang, N.E., Endy, T.P.,
Nisalak, A., Ungchusak, K., Burke, D.S., 2004. Travelling waves in the occurrence of dengue haemorrhagic fever in Thailand. Nature 427 (6972), 344–347.

En Tzu Li, 2011. TAIEX Option Trading by using EEMD-based Neural Network Learning Paradigm. Master Thesis of Graduate Institute of Applied Physics, College of Science NCCU.

FENG Ping, DING Zhi-hong, HAN Rui-guang, ZHANG Jian-wei. 2009. Precipitation-runo forecasting ANN model based on EMD. Systems Engineering-Theory & Practice, Vol.29, No.1, Jan., 2009.

G.A. Adepoju, M.Sc., S.O.A. Ogunjuyigbe, M.Sc., and K.O. Alawode, B.Tech. Application of Neural Network to Load Forecasting in Nigerian Electrical Power System. The Pacific Journal of Science and Technology Volume 8. Number 1. May 2007 (Spring).

Hwang, P.A., Huang, N.E., Wang, D.W., 2003. A note on analyzing nonlinear and non-stationary ocean wave data. Applied Ocean Research 25 (4), 187–193.

Huang, N.E., Shen, Z., Long, S.R., Wu, M.C., Shih, H.H., Zheng, Q., Yen, N.-C., Tung, C.C., Liu, H.H., 1998. The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis. Proceedings of the Royal Society of London A 454 (1971), 903–995.

Huang, N.E., Wu, M.L., Qu, W.D., Long, S.R., Shen, S.S.P., 2003b. Applications of Hilbert–Huang transform to nonstationary financial time series analysis. Applied Stochastic Models in Business and Industry 19, 245–268.

Hari Seetha and R. Saravanan, 2007. Short Term Electric Load Prediction Using Fuzzy BP. Journal of Computing and Information Technology - CIT 15, 2007, 3, 267–282.

Hong Ying Yang, Hao Ye, Guizeng Wang, Junaid Khan, Tongfu Hu, 2005. Fuzzy neural very-short-term load forecasting based on chaotic dynamics reconstruction. Chaos, Solitons & Fractals Volume 29, Issue 2, July 2006, Pages 462-469

Hamid S. A. and Iqbal Z., Using neural networks for
forecasting volatility of S&P 500 Index futures prices, Journal of Business Research, 2004, 57: 1116-112

James W. Taylor. An evaluation of methods for very short-term load forecasting using minute-by-minute British data, 2008. International Journal of Forecasting, 24 (4). pp. 645-658. ISSN 0169-2070

K.Hornik, M.Stinchocombe, 1989. H.White, Multilayer feedforward networks are universal approximators,NeuralNetworks2 (1989) 359–366.

Li, Q.S., Wu, J.R., 2007. Time–frequency analysis of typhoon effects on a 79-storey tall building. Journal of Wind Engineering and Industrial Aerodynamics 95 (12), 1648–1666.

Liang, H., Lin, Q.-H., Chen, J.D.Z., 2005. Application of the empirical mode decomposition to the analysis of esophageal manometric data in gastro esophageal reflux disease. IEEE Transactions on Biomedical Engineering 52 (10), 1692–1701.

Lean Yu, Shouyang Wang, Kin Keung Lai., 2008. Forecasting crude oil price with an EMD-based neural network ensemble learning paradigm. Energy Economics 30 (2008) 2623–2635.

Lean Yu, ShouyangWanga, KinKeungLai, FenghuaWenc, 2010. A multiscale neural network learning paradigm for financial crisis forecasting. Neuro computing, 73:716-725

Liu, K. Subbarayan, S. Shoults, R.R. Manry, M.T. Kwan, C. Lewis, F.I. Naccarino, J. Autom. & Robotics Res. Inst., Texas Univ., Arlington, TX, 1996. Comparison of very short-term load forecasting techniques. IEEE Transactions on Power Systems. Vol. 11. No. 2. May 1996

Mirmirani, S. and H.C. L, 2004. Gold Price, Neural Networks and Genetic Algorithm, Computational Economics, 23, 193-200.

Mendelsohn L., Preprocessing data for Neural Networks, 1993. Tech Anal Stocks Commod, 1993:52-58

Mohsen Hayati and Yazdan Shirvany, 2007. Artificial Neural Network Approach for Short Term Load Forecasting for Illam Region. World Academy of Science, Engineering and Technology 28 2007

N.X. Jia, R. Yokoyamaa, Y.C. Zhoub, Z.Y. Gaoc, 2001. A flexible long-term load forecasting approach based on new dynamic simulation theory — GSIM. International Journal of Electrical Power & Energy Systems Volume 23, Issue 7, October 2001, Pages 549-556

Nahi Kandil, Rene´ Wamkeue, Maarouf Saad, Semaan Georges, 2006. An efficient approach for short term load forecasting using artificial neural networks. International Journal of Electrical Power & Energy Systems Volume 28, Issue 8, October 2006, Pages 525-530.

Ray Ruichong Zhang, M.ASCE; Shuo Ma; Erdal Safak, M.ASCE; and Stephen Hartzell., 2003. Hilbert-Huang Transform Analysis of Dynamic and earthquake motion recordings. Journal of Engineering Mechanics, Vol. 129, No. 8, pp. 861-875.

Ray Ruichong Zhang, Shuo Ma, and Stephen Hartzell., 2003. Signatures of the Seismic Source in EMD-Based Characterization of the 1994 Northridge, California, Earthquake Recordings. Bulletin of the Seismological Society of America; February 2003; v. 93; no. 1; p. 501-518.

Ruqiang Yan, Student Member, IEEE, and Robert X. Gao, Senior Member,IEEE., 2006. Hilbert–Huang Transform-Based Vibration Signal Analysis for Machine Health Monitoring. IEEE Transactions on instrumentation and measurement, Vol. 55, No. 6.

Ruey-Hsun Liang, Ching-Chi Cheng, 2002. Short-term load forecasting by a neuro-fuzzy based approach. International Journal of Electrical Power & Energy Systems Volume 24, Issue 2, February 2002, Pages 103-111

Shahriar Shafiee and ErkanTopal, 2010. An overview of global gold market and gold price forecasting. Resources Policy Volume 35, Issue 3, September 2010, Pages 178-189.

Stephen A. Baker and Roger C. van Tassel, 1985. Forecasting the price of gold: A fundamentalist approach Atlantic Economic Journal Volume 13, No. 4, 43-51

Wu, Z., and N. E Huang, 2009. Ensemble Empirical Mode Decomposition: a noise-assisted data analysis method. Advances in Adaptive Data Analysis. Vol.1, No.1. 1-41.

Wei SUN, 2010. Research on GA-SVM Model for Short Term Load Forecasting Based on LDM-PCA Technique. Journal of Computational Information Systems 6:10 (2010) 3183-3189.

Yen-Rue Chang, 2011. Non-stationary time series analysis by using Hilbert-Huang transform: electricity consumption and gold price volatility. Master Thesis of Graduate Institute of Applied Physics, College of Science NCCU.		zh_TW