Time series forecasting of solar power generation for large-scale photovoltaic plants

Hussein Sharadga, Shima Hajimirza, Robert S. Balog

Research output: Contribution to journalArticle

Abstract

Accurate solar power forecasting is essential for grid-connected photovoltaic (PV) systems especially in case of fluctuating environmental conditions. The prediction of PV power output is critical to secure grid operation, scheduling and grid energy management. One of the key elements in PV output prediction is time series analysis especially in locations where the historical solar radiation measurements or other weather parameters have not been recorded. In this work, several time series prediction methods including the statistical methods and those based on artificial intelligence are introduced and compared rigorously for PV power output prediction. Moreover, the effect of prediction time horizon variation for all the algorithms is investigated. Hourly solar power forecasting is carried out to verify the effectiveness of different models. The data utilized in the current work comprises 3640 h of operation data taken from a 20 MW grid-connected PV station in China.

Original languageEnglish
Pages (from-to)797-807
Number of pages11
JournalRenewable Energy
Volume150
DOIs
Publication statusPublished - May 2020

Fingerprint

Solar power generation
Time series
Solar energy
Time series analysis
Energy management
Solar radiation
Artificial intelligence
Statistical methods
Scheduling

Keywords

  • Deep learning
  • Grid-connected PV plant
  • Neural network
  • PV power forecasting
  • Statistical methods
  • Time series analysis

ASJC Scopus subject areas

  • Renewable Energy, Sustainability and the Environment

Cite this

Time series forecasting of solar power generation for large-scale photovoltaic plants. / Sharadga, Hussein; Hajimirza, Shima; Balog, Robert S.

In: Renewable Energy, Vol. 150, 05.2020, p. 797-807.

Research output: Contribution to journalArticle

@article{39701c953251459daf95638fa38260ed,
title = "Time series forecasting of solar power generation for large-scale photovoltaic plants",
abstract = "Accurate solar power forecasting is essential for grid-connected photovoltaic (PV) systems especially in case of fluctuating environmental conditions. The prediction of PV power output is critical to secure grid operation, scheduling and grid energy management. One of the key elements in PV output prediction is time series analysis especially in locations where the historical solar radiation measurements or other weather parameters have not been recorded. In this work, several time series prediction methods including the statistical methods and those based on artificial intelligence are introduced and compared rigorously for PV power output prediction. Moreover, the effect of prediction time horizon variation for all the algorithms is investigated. Hourly solar power forecasting is carried out to verify the effectiveness of different models. The data utilized in the current work comprises 3640 h of operation data taken from a 20 MW grid-connected PV station in China.",
keywords = "Deep learning, Grid-connected PV plant, Neural network, PV power forecasting, Statistical methods, Time series analysis",
author = "Hussein Sharadga and Shima Hajimirza and Balog, {Robert S.}",
year = "2020",
month = "5",
doi = "10.1016/j.renene.2019.12.131",
language = "English",
volume = "150",
pages = "797--807",
journal = "Renewable Energy",
issn = "0960-1481",
publisher = "Elsevier BV",

}

TY - JOUR

T1 - Time series forecasting of solar power generation for large-scale photovoltaic plants

AU - Sharadga, Hussein

AU - Hajimirza, Shima

AU - Balog, Robert S.

PY - 2020/5

Y1 - 2020/5

N2 - Accurate solar power forecasting is essential for grid-connected photovoltaic (PV) systems especially in case of fluctuating environmental conditions. The prediction of PV power output is critical to secure grid operation, scheduling and grid energy management. One of the key elements in PV output prediction is time series analysis especially in locations where the historical solar radiation measurements or other weather parameters have not been recorded. In this work, several time series prediction methods including the statistical methods and those based on artificial intelligence are introduced and compared rigorously for PV power output prediction. Moreover, the effect of prediction time horizon variation for all the algorithms is investigated. Hourly solar power forecasting is carried out to verify the effectiveness of different models. The data utilized in the current work comprises 3640 h of operation data taken from a 20 MW grid-connected PV station in China.

AB - Accurate solar power forecasting is essential for grid-connected photovoltaic (PV) systems especially in case of fluctuating environmental conditions. The prediction of PV power output is critical to secure grid operation, scheduling and grid energy management. One of the key elements in PV output prediction is time series analysis especially in locations where the historical solar radiation measurements or other weather parameters have not been recorded. In this work, several time series prediction methods including the statistical methods and those based on artificial intelligence are introduced and compared rigorously for PV power output prediction. Moreover, the effect of prediction time horizon variation for all the algorithms is investigated. Hourly solar power forecasting is carried out to verify the effectiveness of different models. The data utilized in the current work comprises 3640 h of operation data taken from a 20 MW grid-connected PV station in China.

KW - Deep learning

KW - Grid-connected PV plant

KW - Neural network

KW - PV power forecasting

KW - Statistical methods

KW - Time series analysis

UR - http://www.scopus.com/inward/record.url?scp=85077932436&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85077932436&partnerID=8YFLogxK

U2 - 10.1016/j.renene.2019.12.131

DO - 10.1016/j.renene.2019.12.131

M3 - Article

AN - SCOPUS:85077932436

VL - 150

SP - 797

EP - 807

JO - Renewable Energy

JF - Renewable Energy

SN - 0960-1481

ER -