# Short-term power load probability density forecasting method using kernel-based support vector quantile regression and Copula theory

Research output: Contribution to journal › Article › peer-review

## Standard

**Short-term power load probability density forecasting method using kernel-based support vector quantile regression and Copula theory.** / He, Yaoyao; Liu, Rui; Li, Haiyan; Wang, Shuo; Lu, Xiaofen.

Research output: Contribution to journal › Article › peer-review

## Harvard

*Applied Energy*, vol. 185, pp. 254-266. https://doi.org/10.1016/j.apenergy.2016.10.079

## APA

*Applied Energy*,

*185*, 254-266. https://doi.org/10.1016/j.apenergy.2016.10.079

## Vancouver

## Author

## Bibtex

}

## RIS

TY - JOUR

T1 - Short-term power load probability density forecasting method using kernel-based support vector quantile regression and Copula theory

AU - He, Yaoyao

AU - Liu, Rui

AU - Li, Haiyan

AU - Wang, Shuo

AU - Lu, Xiaofen

PY - 2017/1/1

Y1 - 2017/1/1

N2 - Penetration of smart grid prominently increases the complexity and uncertainty in scheduling and operation of power systems. Probability density forecasting methods can effectively quantify the uncertainty of power load forecasting. The paper proposes a short-term power load probability density forecasting method using kernel-based support vector quantile regression (KSVQR) and Copula theory. As the kernel function can influence the prediction performance, three kernel functions are compared in this work to select the best one for the learning target. The paper evaluates the accuracy of the prediction intervals considering two criteria, prediction interval coverage probability (PICP) and prediction interval normalized average width (PINAW). Considering uncertainty factors and the correlation of explanatory variables for power load prediction accuracy are of great importance. A probability density forecasting method based on Copula theory is proposed in order to achieve the relational diagram of electrical load and real-time price. The electrical load forecast accuracy of the proposed method is assessed by means of real datasets from Singapore. The simulation results show that the proposed method has great potential for power load forecasting by selecting appropriate kernel function for KSVQR model.

AB - Penetration of smart grid prominently increases the complexity and uncertainty in scheduling and operation of power systems. Probability density forecasting methods can effectively quantify the uncertainty of power load forecasting. The paper proposes a short-term power load probability density forecasting method using kernel-based support vector quantile regression (KSVQR) and Copula theory. As the kernel function can influence the prediction performance, three kernel functions are compared in this work to select the best one for the learning target. The paper evaluates the accuracy of the prediction intervals considering two criteria, prediction interval coverage probability (PICP) and prediction interval normalized average width (PINAW). Considering uncertainty factors and the correlation of explanatory variables for power load prediction accuracy are of great importance. A probability density forecasting method based on Copula theory is proposed in order to achieve the relational diagram of electrical load and real-time price. The electrical load forecast accuracy of the proposed method is assessed by means of real datasets from Singapore. The simulation results show that the proposed method has great potential for power load forecasting by selecting appropriate kernel function for KSVQR model.

KW - Short-term power load probability density forecasting

KW - Support vector quantile regression

KW - PI coverage probability

KW - PI normalized average width

KW - Copula theory

KW - Real-time price

U2 - 10.1016/j.apenergy.2016.10.079

DO - 10.1016/j.apenergy.2016.10.079

M3 - Article

VL - 185

SP - 254

EP - 266

JO - Applied Energy

JF - Applied Energy

SN - 0306-2619

ER -