Identifying working day and rest day data based on machine learning method for more accurate transformer load forecasting

We present in this paper an algorithm for identifying the working day load and the rest day load. The proposed algorithm based on Support Vector Machines (SVM) can be used to characterize working day and rest day load. It combines the six feature quantities that can classify the two types of loads very well and has high precision. The application of the trained model and other load data can also be well recognized, which has good versatility and is of great significance in the classification prediction of short-term load forecasting.

[1]  Angelos K. Marnerides,et al.  Short term power load forecasting using Deep Neural Networks , 2017, 2017 International Conference on Computing, Networking and Communications (ICNC).

[2]  Yuanying Qiu,et al.  Short-Term Power Load Forecasting Method Based on Improved Exponential Smoothing Grey Model , 2018 .

[3]  Yongyi Yang,et al.  Improving SVM classifier with prior knowledge in microcalcification detection1 , 2012, 2012 19th IEEE International Conference on Image Processing.

[4]  Jun Hu,et al.  Short-Term Load Forecasting With Deep Residual Networks , 2018, IEEE Transactions on Smart Grid.

[5]  Vladimir Ceperic,et al.  A Strategy for Short-Term Load Forecasting by Support Vector Regression Machines , 2013, IEEE Transactions on Power Systems.

[6]  Giles M. Foody,et al.  Multiclass and Binary SVM Classification: Implications for Training and Classification Users , 2008, IEEE Geoscience and Remote Sensing Letters.

[7]  Bo Li,et al.  An improved binary tree SVM for multi-classification , 2017, 2017 Chinese Automation Congress (CAC).

[8]  G. Jang,et al.  Short-term load forecasting for the holidays using fuzzy linear regression method , 2005, IEEE Transactions on Power Systems.

[9]  Shu-Xia Lu,et al.  Improved Fuzzy Multicategory Support Vector Machines Classifier , 2006, 2006 International Conference on Machine Learning and Cybernetics.

[10]  P. McSharry,et al.  A comparison of univariate methods for forecasting electricity demand up to a day ahead , 2006 .

[11]  Silja Meyer-Nieberg,et al.  Electric load forecasting methods: Tools for decision making , 2009, Eur. J. Oper. Res..