Final published version
Research output: Contribution to Journal/Magazine › Journal article › peer-review
Automatic time series analysis for electric load forecasting via support vector regression. / Maldonado, S.; González, A.; Crone, S.
In: Applied Soft Computing Journal, Vol. 83, 105616, 01.10.2019.Research output: Contribution to Journal/Magazine › Journal article › peer-review
}
TY - JOUR
T1 - Automatic time series analysis for electric load forecasting via support vector regression
AU - Maldonado, S.
AU - González, A.
AU - Crone, S.
PY - 2019/10/1
Y1 - 2019/10/1
N2 - In this work, a strategy for automatic lag selection in time series analysis is proposed. The method extends the ideas of feature selection with support vector regression, a powerful machine learning tool that can identify nonlinear patterns effectively thanks to the introduction of a kernel function. The proposed approach follows a backward variable elimination procedure based on gradient descent optimisation, iteratively adjusting the widths of an anisotropic Gaussian kernel. Experiments on four electricity demand forecasting datasets demonstrate the virtues of the proposed approach in terms of predictive performance and correct identification of relevant lags and seasonal patterns, compared to well-known strategies for time series analysis designed for energy load forecasting and state-of-the-art strategies for automatic model selection.
AB - In this work, a strategy for automatic lag selection in time series analysis is proposed. The method extends the ideas of feature selection with support vector regression, a powerful machine learning tool that can identify nonlinear patterns effectively thanks to the introduction of a kernel function. The proposed approach follows a backward variable elimination procedure based on gradient descent optimisation, iteratively adjusting the widths of an anisotropic Gaussian kernel. Experiments on four electricity demand forecasting datasets demonstrate the virtues of the proposed approach in terms of predictive performance and correct identification of relevant lags and seasonal patterns, compared to well-known strategies for time series analysis designed for energy load forecasting and state-of-the-art strategies for automatic model selection.
KW - Analytics
KW - Feature selection
KW - Support vector regression
KW - Time series analysis
KW - Electric load forecasting
U2 - 10.1016/j.asoc.2019.105616
DO - 10.1016/j.asoc.2019.105616
M3 - Journal article
VL - 83
JO - Applied Soft Computing
JF - Applied Soft Computing
SN - 1568-4946
M1 - 105616
ER -