Electricity Consumption Forecasting Scheme via Improved LSSVM with Maximum Correntropy Criterion

被引:18
作者
Duan, Jiandong [1 ,2 ]
Qiu, Xinyu [1 ]
Ma, Wentao [1 ]
Tian, Xuan [1 ]
Shang, Di [1 ]
机构
[1] Xian Univ Technol, Sch Automat & Informat Engn, Xian 710048, Shaanxi, Peoples R China
[2] Xian Univ Technol, Dept Elect Engn, Xian 710048, Shaanxi, Peoples R China
关键词
electricity consumption forecasting; least-square support vector machine; maximum correntropy criterion; K-fold cross-validation; SUPPORT VECTOR REGRESSION; NEURAL-NETWORK; BUILDINGS; ALGORITHM;
D O I
10.3390/e20020112
中图分类号
O4 [物理学];
学科分类号
0702 ;
摘要
In recent years, with the deepening of China's electricity sales side reform and electricity market opening up gradually, the forecasting of electricity consumption (FoEC) becomes an extremely important technique for the electricity market. At present, how to forecast the electricity accurately and make an evaluation of results scientifically are still key research topics. In this paper, we propose a novel prediction scheme based on the least-square support vector machine (LSSVM) model with a maximum correntropy criterion (MCC) to forecast the electricity consumption (EC). Firstly, the electricity characteristics of various industries are analyzed to determine the factors that mainly affect the changes in electricity, such as the gross domestic product (GDP), temperature, and so on. Secondly, according to the statistics of the status quo of the small sample data, the LSSVM model is employed as the prediction model. In order to optimize the parameters of the LSSVM model, we further use the local similarity function MCC as the evaluation criterion. Thirdly, we employ the K-fold cross-validation and grid searching methods to improve the learning ability. In the experiments, we have used the EC data of Shaanxi Province in China to evaluate the proposed prediction scheme, and the results show that the proposed prediction scheme outperforms the method based on the traditional LSSVM model.
引用
收藏
页数:15
相关论文
共 27 条
[1]   Electricity consumption forecasting models for administration buildings of the UK higher education sector [J].
Amber, K. P. ;
Aslam, M. W. ;
Hussain, S. K. .
ENERGY AND BUILDINGS, 2015, 90 :127-136
[2]   Annual electricity consumption forecasting by neural network in high energy consuming industrial sectors [J].
Azadeh, A. ;
Ghaderi, S. F. ;
Sohrabkhani, S. .
ENERGY CONVERSION AND MANAGEMENT, 2008, 49 (08) :2272-2278
[3]   Entropy and Correntropy Against Minimum Square Error in Offline and Online Three-Day Ahead Wind Power Forecasting [J].
Bessa, Ricardo J. ;
Miranda, Vladimiro ;
Gama, Joao .
IEEE TRANSACTIONS ON POWER SYSTEMS, 2009, 24 (04) :1657-1666
[4]   Electricity consumption forecasting in Brazil: A spatial econometrics approach [J].
Cabral, Joilson de Assis ;
Loureiro Legey, Luiz Fernando ;
de Freitas Cabral, Maria Viviana .
ENERGY, 2017, 126 :124-131
[5]   Support vector regression with fruit fly optimization algorithm for seasonal electricity consumption forecasting [J].
Cao, Guohua ;
Wu, Lijuan .
ENERGY, 2016, 115 :734-745
[6]   Artificial neural network model for forecasting sub-hourly electricity usage in commercial buildings [J].
Chae, Young Tae ;
Horesh, Raya ;
Hwang, Youngdeok ;
Lee, Young M. .
ENERGY AND BUILDINGS, 2016, 111 :184-194
[7]   Kernel Risk-Sensitive Loss: Definition, Properties and Application to Robust Adaptive Filtering [J].
Chen, Badong ;
Xing, Lei ;
Xu, Bin ;
Zhao, Haiquan ;
Zheng, Nanning ;
Principe, Jose C. .
IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2017, 65 (11) :2888-2901
[8]   Maximum correntropy Kalman filter [J].
Chen, Badong ;
Liu, Xi ;
Zhao, Haiquan ;
Principe, Jose C. .
AUTOMATICA, 2017, 76 :70-77
[9]   Generalized Correntropy for Robust Adaptive Filtering [J].
Chen, Badong ;
Xing, Lei ;
Zhao, Haiquan ;
Zheng, Nanning ;
Principe, Jose C. .
IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2016, 64 (13) :3376-3387
[10]   Kernel least mean square with adaptive kernel size [J].
Chen, Badong ;
Liang, Junli ;
Zheng, Nanning ;
Principe, Jose C. .
NEUROCOMPUTING, 2016, 191 :95-106