Probabilistic Load Forecasting Using an Improved Wavelet Neural Network Trained by Generalized Extreme Learning Machine

被引:129
作者
Rafiei, Mehdi [1 ]
Niknam, Taher [1 ]
Aghaei, Jamshid [1 ,2 ]
Shafie-Khah, Miadreza [3 ]
Catalao, Joao P. S. [3 ,4 ,5 ,6 ]
机构
[1] Shiraz Univ Technol, Dept Elect & Elect Engn, Shiraz 71555313, Iran
[2] Norwegian Univ Sci & Technol, Dept Elect Power Engn, N-7491 Trondheim, Norway
[3] Univ Beira Interior, C MAST, P-6201001 Covilha, Portugal
[4] Univ Porto, INESC TEC, P-4200465 Porto, Portugal
[5] Univ Porto, Fac Engn, P-4200465 Porto, Portugal
[6] Univ Lisbon, INESC ID, Inst Super Tecn, P-1049001 Lisbon, Portugal
基金
欧盟第七框架计划;
关键词
Probabilistic forecasting; improved wavelet neural network; generalized extreme learning machine; bootstrapping; wavelet processing; ELECTRICITY LOAD;
D O I
10.1109/TSG.2018.2807845
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
Competitive transactions resulting from recent restructuring of the electricity market, have made achieving a precise and reliable load forecasting, especially probabilistic load forecasting, an important topic. Hence, this paper presents a novel hybrid method of probabilistic electricity load forecasting, including generalized extreme learning machine fin- training an improved wavelet neural network, wavelet preprocessing and bootstrapping. In the proposed method, the forecasting model and data noise uncertainties are taken into account while the output of the model is the load probabilistic interval. In order to validate the method, it is implemented on the Ontario and Australian electricity markets data. Also, in order to remove the influence of model parameters and data on performance validation, Friedman and post-hoc tests, which are non-parametric tests, are applied to the proposed method. The results demonstrate the high performance, accuracy, and reliability of the proposed method.
引用
收藏
页码:6961 / 6971
页数:11
相关论文
共 30 条
[1]  
[Anonymous], 1992, BREAKTHROUGHS STAT
[2]  
[Anonymous], INT J FORECAST
[3]   Effects of load forecast uncertainty on bulk electric system reliability evaluation [J].
Billinton, Roy ;
Huang, Dange .
IEEE TRANSACTIONS ON POWER SYSTEMS, 2008, 23 (02) :418-425
[4]   PROBABILISTIC LOAD FLOW [J].
BORKOWSKA, B .
IEEE TRANSACTIONS ON POWER APPARATUS AND SYSTEMS, 1974, PA93 (03) :752-759
[5]   A Strategy for Short-Term Load Forecasting by Support Vector Regression Machines [J].
Ceperic, Ervin ;
Ceperic, Vladimir ;
Baric, Adrijan .
IEEE TRANSACTIONS ON POWER SYSTEMS, 2013, 28 (04) :4356-4364
[6]   Clustering-Based Improvement of Nonparametric Functional Time Series Forecasting: Application to Intra-Day Household-Level Load Curves [J].
Chaouch, Mohamed .
IEEE TRANSACTIONS ON SMART GRID, 2014, 5 (01) :411-419
[7]   SHORT-TERM LOAD FORECASTING USING GENERAL EXPONENTIAL SMOOTHING [J].
CHRISTIAANSE, WR .
IEEE TRANSACTIONS ON POWER APPARATUS AND SYSTEMS, 1971, PA90 (02) :900-+
[8]   Forecasting day-ahead electricity load using a multiple equation time series approach [J].
Clements, A. E. ;
Hurn, A. S. ;
Li, Z. .
EUROPEAN JOURNAL OF OPERATIONAL RESEARCH, 2016, 251 (02) :522-530
[9]   Day-ahead electricity price forecasting using the wavelet transform and ARIMA models [J].
Conejo, AJ ;
Plazas, MA ;
Espínola, R ;
Molina, AB .
IEEE TRANSACTIONS ON POWER SYSTEMS, 2005, 20 (02) :1035-1042
[10]   Deep belief network based electricity load forecasting: An analysis of Macedonian case [J].
Dedinec, Aleksandra ;
Filiposka, Sonja ;
Dedinec, Aleksandar ;
Kocarev, Ljupco .
ENERGY, 2016, 115 :1688-1700