Evaluation of data-driven models for predicting solar photovoltaics power output

Salim Moslehi, T. Agami Reddy, Srinivas Katipamula

Research output: Contribution to journalArticle

  • 1 Citations

Abstract

This research was undertaken to evaluate different inverse models for predicting power output of solar photovoltaic (PV) systems under different practical scenarios. In particular, we have investigated whether PV power output prediction accuracy can be improved if module/cell temperature was measured in addition to climatic variables, and also the extent to which prediction accuracy degrades if solar irradiation is not measured on the plane of array but only on a horizontal surface. We have also investigated the significance of different independent or regressor variables, such as wind velocity and incident angle modifier in predicting PV power output and cell temperature. We found wind velocity and module temperature measurements are too unreliable for use in inverse solar PV models. The inverse regression model forms have been evaluated both in terms of their goodness-of-fit, and their accuracy and robustness in terms of their predictive performance. Given the accuracy of the measurements, expected CV-RMSE of hourly power output prediction over the year varies between 3.2% and 8.6% when only climatic data are used. Depending on what type of measured climatic and PV performance data is available, different scenarios have been identified and the appropriate modeling pathways have been proposed. These models are to be implemented on a controller platform for optimum operational planning of microgrids and integrated energy systems.

LanguageEnglish (US)
Pages1057-1065
Number of pages9
JournalEnergy
Volume142
DOIs
StatePublished - Jan 1 2018

Fingerprint

Temperature measurement
Irradiation
Planning
Temperature
Controllers

Keywords

  • Data-driven modeling
  • PV power prediction
  • Renewable energy
  • Solar photovoltaics
  • Sustainable energy

ASJC Scopus subject areas

  • Civil and Structural Engineering
  • Building and Construction
  • Pollution
  • Energy(all)
  • Mechanical Engineering
  • Industrial and Manufacturing Engineering
  • Electrical and Electronic Engineering

Cite this

Evaluation of data-driven models for predicting solar photovoltaics power output. / Moslehi, Salim; Reddy, T. Agami; Katipamula, Srinivas.

In: Energy, Vol. 142, 01.01.2018, p. 1057-1065.

Research output: Contribution to journalArticle

Moslehi, Salim ; Reddy, T. Agami ; Katipamula, Srinivas. / Evaluation of data-driven models for predicting solar photovoltaics power output. In: Energy. 2018 ; Vol. 142. pp. 1057-1065
@article{676d45a7df924272b8feb03f504040bd,
title = "Evaluation of data-driven models for predicting solar photovoltaics power output",
abstract = "This research was undertaken to evaluate different inverse models for predicting power output of solar photovoltaic (PV) systems under different practical scenarios. In particular, we have investigated whether PV power output prediction accuracy can be improved if module/cell temperature was measured in addition to climatic variables, and also the extent to which prediction accuracy degrades if solar irradiation is not measured on the plane of array but only on a horizontal surface. We have also investigated the significance of different independent or regressor variables, such as wind velocity and incident angle modifier in predicting PV power output and cell temperature. We found wind velocity and module temperature measurements are too unreliable for use in inverse solar PV models. The inverse regression model forms have been evaluated both in terms of their goodness-of-fit, and their accuracy and robustness in terms of their predictive performance. Given the accuracy of the measurements, expected CV-RMSE of hourly power output prediction over the year varies between 3.2\{%} and 8.6\{%} when only climatic data are used. Depending on what type of measured climatic and PV performance data is available, different scenarios have been identified and the appropriate modeling pathways have been proposed. These models are to be implemented on a controller platform for optimum operational planning of microgrids and integrated energy systems.",
keywords = "Data-driven modeling, PV power prediction, Renewable energy, Solar photovoltaics, Sustainable energy",
author = "Salim Moslehi and Reddy, {T. Agami} and Srinivas Katipamula",
year = "2018",
month = "1",
day = "1",
doi = "10.1016/j.energy.2017.09.042",
language = "English (US)",
volume = "142",
pages = "1057--1065",
journal = "Energy",
issn = "0360-5442",
publisher = "Elsevier Limited",

}

TY - JOUR

T1 - Evaluation of data-driven models for predicting solar photovoltaics power output

AU - Moslehi,Salim

AU - Reddy,T. Agami

AU - Katipamula,Srinivas

PY - 2018/1/1

Y1 - 2018/1/1

N2 - This research was undertaken to evaluate different inverse models for predicting power output of solar photovoltaic (PV) systems under different practical scenarios. In particular, we have investigated whether PV power output prediction accuracy can be improved if module/cell temperature was measured in addition to climatic variables, and also the extent to which prediction accuracy degrades if solar irradiation is not measured on the plane of array but only on a horizontal surface. We have also investigated the significance of different independent or regressor variables, such as wind velocity and incident angle modifier in predicting PV power output and cell temperature. We found wind velocity and module temperature measurements are too unreliable for use in inverse solar PV models. The inverse regression model forms have been evaluated both in terms of their goodness-of-fit, and their accuracy and robustness in terms of their predictive performance. Given the accuracy of the measurements, expected CV-RMSE of hourly power output prediction over the year varies between 3.2% and 8.6% when only climatic data are used. Depending on what type of measured climatic and PV performance data is available, different scenarios have been identified and the appropriate modeling pathways have been proposed. These models are to be implemented on a controller platform for optimum operational planning of microgrids and integrated energy systems.

AB - This research was undertaken to evaluate different inverse models for predicting power output of solar photovoltaic (PV) systems under different practical scenarios. In particular, we have investigated whether PV power output prediction accuracy can be improved if module/cell temperature was measured in addition to climatic variables, and also the extent to which prediction accuracy degrades if solar irradiation is not measured on the plane of array but only on a horizontal surface. We have also investigated the significance of different independent or regressor variables, such as wind velocity and incident angle modifier in predicting PV power output and cell temperature. We found wind velocity and module temperature measurements are too unreliable for use in inverse solar PV models. The inverse regression model forms have been evaluated both in terms of their goodness-of-fit, and their accuracy and robustness in terms of their predictive performance. Given the accuracy of the measurements, expected CV-RMSE of hourly power output prediction over the year varies between 3.2% and 8.6% when only climatic data are used. Depending on what type of measured climatic and PV performance data is available, different scenarios have been identified and the appropriate modeling pathways have been proposed. These models are to be implemented on a controller platform for optimum operational planning of microgrids and integrated energy systems.

KW - Data-driven modeling

KW - PV power prediction

KW - Renewable energy

KW - Solar photovoltaics

KW - Sustainable energy

UR - http://www.scopus.com/inward/record.url?scp=85032682989&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85032682989&partnerID=8YFLogxK

U2 - 10.1016/j.energy.2017.09.042

DO - 10.1016/j.energy.2017.09.042

M3 - Article

VL - 142

SP - 1057

EP - 1065

JO - Energy

T2 - Energy

JF - Energy

SN - 0360-5442

ER -