Sequential grid approach based support vector regression for short-term electric load forecasting. (15th March 2019)

• Record Type: Journal Article
• Authors: Yang, Youlong; Che, Jinxing; Deng, Chengzhi; Li, Li
• Is Part Of: Applied energy. Volume 238(2019)
• Page Start: 1010
• Page End: 1021
• Publication Date: 2019-03-15
• Subjects: Electric load forecasting -- Support vector regression -- Subsampling -- Sequential grid approach -- Model selection; Power (Mechanics) -- Periodicals; Energy conservation -- Periodicals; Energy conversion -- Periodicals; 621.042
• DOI: 10.1016/j.apenergy.2019.01.127
• Languages: English
• ISSNs: 0306-2619

Abstract

Graphical abstract: Highlights: Electric load forecasting is important for evaluating the power utility performance. The subsampling method is used to speed up the SVR modeling process. The SVR is sequentially built by introducing parameter regression surface. The obtained results confirm the applicability and superiority of the model. Abstract: Short-term electric load forecasting is important for evaluating the power utility performance in terms of price and income elasticities, energy transfer scheduling, unit commitment and load dispatch. Support vector regression (SVR) approach applies a simple linear regression in the high-dimensional feature space (Hilbert space) by using kernel functions and has many attractive features and profound empirical performances for small sample, nonlinearity and high dimensional dataset. However, the SVR modeling processing has computation complexity of order O ( K × N 3 ) (where N is the size of the training dataset, and K is the evaluation number of the parameter selection process). To forecast short-term power load accurately, quickly and efficiently, a sequential grid approach based support vector regression (SGA-SVR) is proposed in this work. Specifically, for a given data set, parameter regression surface is conducted in SVR modeling processing with its forecasting performance as dependent variable and the three parameters ( ε, C, γ ) as independent variables. Then, a novel grid algorithm is presented to provide a new way for fitting the parameter regression surface. The statistical inference is also given by introducing the asymptotic normality of a fixed grid point of parameters. The numerical experiments using SGA-SVR model demonstrate the superiority over the standard SVR model and accuracy of forecast is greatly improved especially for short-term forecasts.