Load and Price Forecasting in Smart Grids Using Enhanced Support Vector Machine
In this paper, an enhanced model for electricity load and price forecasting is proposed. This model consists of feature engineering and classification. Feature engineering consists of feature selection and extraction. For feature selection a hybrid feature selector is used which consists of Decision Tree (DT) and Recursive Feature Elimination (RFE) to remove redundancy. Furthermore, Singular Value Decomposition (SVD) is used for feature extraction to reduce the dimensionality of features. To forecast load and price, two classifiers Stochastic Gradient Descent (SGD) and Support Vector Machine (SVM) is used and for better accuracy an enhanced framework of SVM is proposed. Dataset is taken from NYISO and month wise forecasting is being conducted by proposed classifiers. To evaluate performance RMSE, MAPE, MAE, MSE is used.
- 1.Oren, S.S.: Demand response: a historical perspective and business models for load control aggregation. In: Presented at the Power System Engineering Research Center Public Webinar, 1 February 2011Google Scholar
- 2.Ghatikar, G., Mathieu, J.L., Piette, M.A., Liliccote, S.: Open automated demand response technologies for dynamic pricing and smartgrid. In: Presented at Grid-Interop Conference 2010, Chicago, IL, 13 December 2010. http://drrc.lbl.gov/sites/drrc.lbl.gov/files/lbnl-4028e.pdf
- 6.Wang, K., et al.: Robust big data analytics for electricity price forecasting in the smart grid. IEEE Trans. Big Data (2017)Google Scholar
- 12.Jindal, A., Singh, M., Kumar, N.: Consumption-aware data analytical demand response scheme for peak load reduction in smart grid. IEEE Trans. Industr. Electron. (2018)Google Scholar
- 13.Marcjasz, G., Uniejewski, B., Weron, R.: On the importance of the long-term seasonal component in day-ahead electricity price forecasting with NARX neural networks. Int. J. Forecast. (2018)Google Scholar
- 16.Rafiei, M., et al.: Probabilistic load forecasting using an improved wavelet neural network trained by generalized extreme learning machine. IEEE Trans. Smart Grid (2018)Google Scholar