Prediction of photovoltaic power output for microgrids using back-propagation neural network

Wei-Tzer Huang, Kai-chao Yao, Hao Chuan Luo, Hong Ting Chen, Yung Ruei Chang, Yih Der Lee, Yuan Hsiang Ho

Research output: Contribution to journalArticle

Abstract

The main purpose of this study is to predict photovoltaic (PV) power output using back-propagation neural network (BPNN). The mean relative error is used to evaluate the prediction accuracy. This study used the historical data of temperature, humidity, and PV power output to predict the day-ahead hourly power output. Eventually, the day-ahead hourly prediction results are applied to the energy management system of the microgrids (MGs) of the remote island of Taiwan. Results demonstrate that the proposed BPNN algorithm for prediction is accurate and effective. Outcomes are also beneficial for the day-ahead unit commitment of MGs.

Original languageEnglish
Pages (from-to)211-218
Number of pages8
JournalICIC Express Letters, Part B: Applications
Volume10
Issue number3
DOIs
Publication statusPublished - 2019 Mar 1

Fingerprint

Backpropagation
Neural networks
Energy management systems
Atmospheric humidity
Temperature

All Science Journal Classification (ASJC) codes

  • Computer Science(all)

Cite this

Huang, Wei-Tzer ; Yao, Kai-chao ; Luo, Hao Chuan ; Chen, Hong Ting ; Chang, Yung Ruei ; Lee, Yih Der ; Ho, Yuan Hsiang. / Prediction of photovoltaic power output for microgrids using back-propagation neural network. In: ICIC Express Letters, Part B: Applications. 2019 ; Vol. 10, No. 3. pp. 211-218.
@article{f84298d01bc14d1aae4dd8aaa5740492,
title = "Prediction of photovoltaic power output for microgrids using back-propagation neural network",
abstract = "The main purpose of this study is to predict photovoltaic (PV) power output using back-propagation neural network (BPNN). The mean relative error is used to evaluate the prediction accuracy. This study used the historical data of temperature, humidity, and PV power output to predict the day-ahead hourly power output. Eventually, the day-ahead hourly prediction results are applied to the energy management system of the microgrids (MGs) of the remote island of Taiwan. Results demonstrate that the proposed BPNN algorithm for prediction is accurate and effective. Outcomes are also beneficial for the day-ahead unit commitment of MGs.",
author = "Wei-Tzer Huang and Kai-chao Yao and Luo, {Hao Chuan} and Chen, {Hong Ting} and Chang, {Yung Ruei} and Lee, {Yih Der} and Ho, {Yuan Hsiang}",
year = "2019",
month = "3",
day = "1",
doi = "10.24507/icicelb.10.03.211",
language = "English",
volume = "10",
pages = "211--218",
journal = "ICIC Express Letters, Part B: Applications",
issn = "2185-2766",
publisher = "ICIC Express Letters Office",
number = "3",

}

Prediction of photovoltaic power output for microgrids using back-propagation neural network. / Huang, Wei-Tzer; Yao, Kai-chao; Luo, Hao Chuan; Chen, Hong Ting; Chang, Yung Ruei; Lee, Yih Der; Ho, Yuan Hsiang.

In: ICIC Express Letters, Part B: Applications, Vol. 10, No. 3, 01.03.2019, p. 211-218.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Prediction of photovoltaic power output for microgrids using back-propagation neural network

AU - Huang, Wei-Tzer

AU - Yao, Kai-chao

AU - Luo, Hao Chuan

AU - Chen, Hong Ting

AU - Chang, Yung Ruei

AU - Lee, Yih Der

AU - Ho, Yuan Hsiang

PY - 2019/3/1

Y1 - 2019/3/1

N2 - The main purpose of this study is to predict photovoltaic (PV) power output using back-propagation neural network (BPNN). The mean relative error is used to evaluate the prediction accuracy. This study used the historical data of temperature, humidity, and PV power output to predict the day-ahead hourly power output. Eventually, the day-ahead hourly prediction results are applied to the energy management system of the microgrids (MGs) of the remote island of Taiwan. Results demonstrate that the proposed BPNN algorithm for prediction is accurate and effective. Outcomes are also beneficial for the day-ahead unit commitment of MGs.

AB - The main purpose of this study is to predict photovoltaic (PV) power output using back-propagation neural network (BPNN). The mean relative error is used to evaluate the prediction accuracy. This study used the historical data of temperature, humidity, and PV power output to predict the day-ahead hourly power output. Eventually, the day-ahead hourly prediction results are applied to the energy management system of the microgrids (MGs) of the remote island of Taiwan. Results demonstrate that the proposed BPNN algorithm for prediction is accurate and effective. Outcomes are also beneficial for the day-ahead unit commitment of MGs.

UR - http://www.scopus.com/inward/record.url?scp=85065242990&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85065242990&partnerID=8YFLogxK

U2 - 10.24507/icicelb.10.03.211

DO - 10.24507/icicelb.10.03.211

M3 - Article

VL - 10

SP - 211

EP - 218

JO - ICIC Express Letters, Part B: Applications

JF - ICIC Express Letters, Part B: Applications

SN - 2185-2766

IS - 3

ER -