Probabilistic Forecasting of Photovoltaic Generation: An Efficient Statistical Approach

Can Wan; Jin Lin; Yonghua Song; Zhao Xu; Guangya Yang

doi:10.1109/TPWRS.2016.2608740

Probabilistic Forecasting of Photovoltaic Generation: An Efficient Statistical Approach

Can Wan, Jin Lin, Yonghua Song, Zhao Xu, Guangya Yang

Research output: Contribution to journal › Journal article › Research › peer-review

1008 Downloads (Pure)

Abstract

This letter proposes a novel efficient probabilistic forecasting approach to accurately quantify the variability and uncertainty of the power production from photovoltaic (PV) systems. Distinguished from most existing models, a linear programming based prediction interval construction model for PV power generation is proposed based on extreme learning machine and quantile regression, featuring high reliability and computational efficiency. The proposed approach is validated through the numerical studies on PV data from Denmark.

Original language	English
Journal	IEEE Transactions on Power Systems
Volume	32
Issue number	3
Pages (from-to)	2471 - 2472
ISSN	0885-8950
DOIs	https://doi.org/10.1109/TPWRS.2016.2608740
Publication status	Published - 2017

Keywords

PV power
Forecasting
Prediction intervals
Extreme learning machine
Quantile regression

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1109/TPWRS.2016.2608740

S1 ln23419218120869617 1939656818Hwf 248298202IdV 40585418523419218PDF HI0001Accepted author manuscript, 267 KB

OpenUrl availability

Full text

Cite this

@article{0b2bed9bfe504920af2672a85c22d9f8,

title = "Probabilistic Forecasting of Photovoltaic Generation: An Efficient Statistical Approach",

abstract = "This letter proposes a novel efficient probabilistic forecasting approach to accurately quantify the variability and uncertainty of the power production from photovoltaic (PV) systems. Distinguished from most existing models, a linear programming based prediction interval construction model for PV power generation is proposed based on extreme learning machine and quantile regression, featuring high reliability and computational efficiency. The proposed approach is validated through the numerical studies on PV data from Denmark. ",

keywords = "PV power, Forecasting, Prediction intervals, Extreme learning machine, Quantile regression",

author = "Can Wan and Jin Lin and Yonghua Song and Zhao Xu and Guangya Yang",

year = "2017",

doi = "10.1109/TPWRS.2016.2608740",

language = "English",

volume = "32",

pages = "2471 -- 2472",

journal = "IEEE Transactions on Power Systems",

issn = "0885-8950",

publisher = "Institute of Electrical and Electronics Engineers",

number = "3",

}

TY - JOUR

T1 - Probabilistic Forecasting of Photovoltaic Generation: An Efficient Statistical Approach

AU - Wan, Can

AU - Lin, Jin

AU - Song, Yonghua

AU - Xu, Zhao

AU - Yang, Guangya

PY - 2017

Y1 - 2017

N2 - This letter proposes a novel efficient probabilistic forecasting approach to accurately quantify the variability and uncertainty of the power production from photovoltaic (PV) systems. Distinguished from most existing models, a linear programming based prediction interval construction model for PV power generation is proposed based on extreme learning machine and quantile regression, featuring high reliability and computational efficiency. The proposed approach is validated through the numerical studies on PV data from Denmark.

AB - This letter proposes a novel efficient probabilistic forecasting approach to accurately quantify the variability and uncertainty of the power production from photovoltaic (PV) systems. Distinguished from most existing models, a linear programming based prediction interval construction model for PV power generation is proposed based on extreme learning machine and quantile regression, featuring high reliability and computational efficiency. The proposed approach is validated through the numerical studies on PV data from Denmark.

KW - PV power

KW - Forecasting

KW - Prediction intervals

KW - Extreme learning machine

KW - Quantile regression

U2 - 10.1109/TPWRS.2016.2608740

DO - 10.1109/TPWRS.2016.2608740

M3 - Journal article

SN - 0885-8950

VL - 32

SP - 2471

EP - 2472

JO - IEEE Transactions on Power Systems

JF - IEEE Transactions on Power Systems

IS - 3

ER -

Probabilistic Forecasting of Photovoltaic Generation: An Efficient Statistical Approach

Abstract

Keywords

UN SDGs

Access to Document

OpenUrl availability

Fingerprint

Cite this