Forecasting of photovoltaic power yield using dynamic neural networks

Naji Al-Messabi, Yun Li, Ibrahim El-Amin, Cindy Goh

Research output: Chapter in Book/Report/Conference proceedingConference contribution book

22 Citations (Scopus)

Abstract

The importance of predicting the output power of Photovoltaic (PV) plants is crucial in modern power system applications. Predicting the power yield of a PV generation system helps the process of dispatching the power into a grid with improved efficiency in generation planning and operation. This work proposes the use of intelligent tools to forecast the real power output of PV units. These tools primarily comprise dynamic neural networks which are capable of time-series predictions with good reliability. This paper begins with a brief review of various methods of forecasting solar power reported in literature. Results of preliminary work on a 5kW PV panel at King Fahd University of Petroleum and Minerals, Dhahran, Saudi Arabia, is presented. Focused Time Delay and Distributed Time Delay Neural Networks were used as a forecasting tool for this study and their performance was compared with each other.

Original languageEnglish
Title of host publication2012 International Joint Conference on Neural Networks, IJCNN 2012
DOIs
Publication statusPublished - 10 Jun 2012
Event2012 Annual International Joint Conference on Neural Networks, IJCNN 2012, Part of the 2012 IEEE World Congress on Computational Intelligence, WCCI 2012 - Brisbane, QLD, Australia
Duration: 10 Jun 201215 Jun 2012

Conference

Conference2012 Annual International Joint Conference on Neural Networks, IJCNN 2012, Part of the 2012 IEEE World Congress on Computational Intelligence, WCCI 2012
CountryAustralia
CityBrisbane, QLD
Period10/06/1215/06/12

Fingerprint

Neural networks
Time delay
Solar energy
Time series
Minerals
Crude oil
Planning

Keywords

  • dynamic neural networks
  • irradiance
  • time-series forecasting

Cite this

Al-Messabi, N., Li, Y., El-Amin, I., & Goh, C. (2012). Forecasting of photovoltaic power yield using dynamic neural networks. In 2012 International Joint Conference on Neural Networks, IJCNN 2012 [6252406] https://doi.org/10.1109/IJCNN.2012.6252406
Al-Messabi, Naji ; Li, Yun ; El-Amin, Ibrahim ; Goh, Cindy. / Forecasting of photovoltaic power yield using dynamic neural networks. 2012 International Joint Conference on Neural Networks, IJCNN 2012. 2012.
@inproceedings{55f6874f1a994e8f9be519699ebaafc7,
title = "Forecasting of photovoltaic power yield using dynamic neural networks",
abstract = "The importance of predicting the output power of Photovoltaic (PV) plants is crucial in modern power system applications. Predicting the power yield of a PV generation system helps the process of dispatching the power into a grid with improved efficiency in generation planning and operation. This work proposes the use of intelligent tools to forecast the real power output of PV units. These tools primarily comprise dynamic neural networks which are capable of time-series predictions with good reliability. This paper begins with a brief review of various methods of forecasting solar power reported in literature. Results of preliminary work on a 5kW PV panel at King Fahd University of Petroleum and Minerals, Dhahran, Saudi Arabia, is presented. Focused Time Delay and Distributed Time Delay Neural Networks were used as a forecasting tool for this study and their performance was compared with each other.",
keywords = "dynamic neural networks, irradiance, time-series forecasting",
author = "Naji Al-Messabi and Yun Li and Ibrahim El-Amin and Cindy Goh",
year = "2012",
month = "6",
day = "10",
doi = "10.1109/IJCNN.2012.6252406",
language = "English",
isbn = "9781467314909",
booktitle = "2012 International Joint Conference on Neural Networks, IJCNN 2012",

}

Al-Messabi, N, Li, Y, El-Amin, I & Goh, C 2012, Forecasting of photovoltaic power yield using dynamic neural networks. in 2012 International Joint Conference on Neural Networks, IJCNN 2012., 6252406, 2012 Annual International Joint Conference on Neural Networks, IJCNN 2012, Part of the 2012 IEEE World Congress on Computational Intelligence, WCCI 2012, Brisbane, QLD, Australia, 10/06/12. https://doi.org/10.1109/IJCNN.2012.6252406

Forecasting of photovoltaic power yield using dynamic neural networks. / Al-Messabi, Naji; Li, Yun; El-Amin, Ibrahim; Goh, Cindy.

2012 International Joint Conference on Neural Networks, IJCNN 2012. 2012. 6252406.

Research output: Chapter in Book/Report/Conference proceedingConference contribution book

TY - GEN

T1 - Forecasting of photovoltaic power yield using dynamic neural networks

AU - Al-Messabi, Naji

AU - Li, Yun

AU - El-Amin, Ibrahim

AU - Goh, Cindy

PY - 2012/6/10

Y1 - 2012/6/10

N2 - The importance of predicting the output power of Photovoltaic (PV) plants is crucial in modern power system applications. Predicting the power yield of a PV generation system helps the process of dispatching the power into a grid with improved efficiency in generation planning and operation. This work proposes the use of intelligent tools to forecast the real power output of PV units. These tools primarily comprise dynamic neural networks which are capable of time-series predictions with good reliability. This paper begins with a brief review of various methods of forecasting solar power reported in literature. Results of preliminary work on a 5kW PV panel at King Fahd University of Petroleum and Minerals, Dhahran, Saudi Arabia, is presented. Focused Time Delay and Distributed Time Delay Neural Networks were used as a forecasting tool for this study and their performance was compared with each other.

AB - The importance of predicting the output power of Photovoltaic (PV) plants is crucial in modern power system applications. Predicting the power yield of a PV generation system helps the process of dispatching the power into a grid with improved efficiency in generation planning and operation. This work proposes the use of intelligent tools to forecast the real power output of PV units. These tools primarily comprise dynamic neural networks which are capable of time-series predictions with good reliability. This paper begins with a brief review of various methods of forecasting solar power reported in literature. Results of preliminary work on a 5kW PV panel at King Fahd University of Petroleum and Minerals, Dhahran, Saudi Arabia, is presented. Focused Time Delay and Distributed Time Delay Neural Networks were used as a forecasting tool for this study and their performance was compared with each other.

KW - dynamic neural networks

KW - irradiance

KW - time-series forecasting

UR - http://www.scopus.com/inward/record.url?scp=84865083895&partnerID=8YFLogxK

U2 - 10.1109/IJCNN.2012.6252406

DO - 10.1109/IJCNN.2012.6252406

M3 - Conference contribution book

SN - 9781467314909

BT - 2012 International Joint Conference on Neural Networks, IJCNN 2012

ER -

Al-Messabi N, Li Y, El-Amin I, Goh C. Forecasting of photovoltaic power yield using dynamic neural networks. In 2012 International Joint Conference on Neural Networks, IJCNN 2012. 2012. 6252406 https://doi.org/10.1109/IJCNN.2012.6252406