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.
N1 - Publisher Copyright:
© 2020 Elsevier Ltd
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
SN - 0960-1481
VL - 150
SP - 797
EP - 807
JO - Renewable Energy
JF - Renewable Energy
ER -