Short-term PV power forecasts based on a real-time irradiance monitoring network

Antonio T. Lorenzo, William F. Holmgren, Michael Leuthold, Chang Ki Kim, Alexander D Cronin, Eric Betterton

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

12 Citations (Scopus)

Abstract

We built an irradiance sensor network that we are now using to make operational, real-time, intra-hour forecasts of solar power at key locations. We developed reliable irradiance sensor hardware platforms to enable these sensor network forecasts. Using 19 of the 55 irradiance sensors we have throughout Tucson, we make retrospective forecasts of 26 days in April and evaluate their performance. We find that that our network forecasts outperform a persistence model for 1 to 28 minute time horizons as measured by the root mean squared error. The sensor hardware, our network forecasting method, error statistics, and future improvements to our forecasts are discussed.

Original languageEnglish (US)
Title of host publication2014 IEEE 40th Photovoltaic Specialist Conference, PVSC 2014
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages75-79
Number of pages5
ISBN (Print)9781479943982
DOIs
StatePublished - Oct 15 2014
Event40th IEEE Photovoltaic Specialist Conference, PVSC 2014 - Denver, United States
Duration: Jun 8 2014Jun 13 2014

Other

Other40th IEEE Photovoltaic Specialist Conference, PVSC 2014
CountryUnited States
CityDenver
Period6/8/146/13/14

Fingerprint

Sensor networks
Monitoring
Sensors
Error statistics
Solar energy
Computer hardware
Hardware

Keywords

  • data analysis
  • forecasting
  • real-time systems
  • sensors
  • solar energy

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Electronic, Optical and Magnetic Materials

Cite this

Lorenzo, A. T., Holmgren, W. F., Leuthold, M., Kim, C. K., Cronin, A. D., & Betterton, E. (2014). Short-term PV power forecasts based on a real-time irradiance monitoring network. In 2014 IEEE 40th Photovoltaic Specialist Conference, PVSC 2014 (pp. 75-79). [6925212] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/PVSC.2014.6925212

Short-term PV power forecasts based on a real-time irradiance monitoring network. / Lorenzo, Antonio T.; Holmgren, William F.; Leuthold, Michael; Kim, Chang Ki; Cronin, Alexander D; Betterton, Eric.

2014 IEEE 40th Photovoltaic Specialist Conference, PVSC 2014. Institute of Electrical and Electronics Engineers Inc., 2014. p. 75-79 6925212.

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

Lorenzo, AT, Holmgren, WF, Leuthold, M, Kim, CK, Cronin, AD & Betterton, E 2014, Short-term PV power forecasts based on a real-time irradiance monitoring network. in 2014 IEEE 40th Photovoltaic Specialist Conference, PVSC 2014., 6925212, Institute of Electrical and Electronics Engineers Inc., pp. 75-79, 40th IEEE Photovoltaic Specialist Conference, PVSC 2014, Denver, United States, 6/8/14. https://doi.org/10.1109/PVSC.2014.6925212
Lorenzo AT, Holmgren WF, Leuthold M, Kim CK, Cronin AD, Betterton E. Short-term PV power forecasts based on a real-time irradiance monitoring network. In 2014 IEEE 40th Photovoltaic Specialist Conference, PVSC 2014. Institute of Electrical and Electronics Engineers Inc. 2014. p. 75-79. 6925212 https://doi.org/10.1109/PVSC.2014.6925212
Lorenzo, Antonio T. ; Holmgren, William F. ; Leuthold, Michael ; Kim, Chang Ki ; Cronin, Alexander D ; Betterton, Eric. / Short-term PV power forecasts based on a real-time irradiance monitoring network. 2014 IEEE 40th Photovoltaic Specialist Conference, PVSC 2014. Institute of Electrical and Electronics Engineers Inc., 2014. pp. 75-79
@inproceedings{c16b41975ca84b5ea9fe14818cea3154,
title = "Short-term PV power forecasts based on a real-time irradiance monitoring network",
abstract = "We built an irradiance sensor network that we are now using to make operational, real-time, intra-hour forecasts of solar power at key locations. We developed reliable irradiance sensor hardware platforms to enable these sensor network forecasts. Using 19 of the 55 irradiance sensors we have throughout Tucson, we make retrospective forecasts of 26 days in April and evaluate their performance. We find that that our network forecasts outperform a persistence model for 1 to 28 minute time horizons as measured by the root mean squared error. The sensor hardware, our network forecasting method, error statistics, and future improvements to our forecasts are discussed.",
keywords = "data analysis, forecasting, real-time systems, sensors, solar energy",
author = "Lorenzo, {Antonio T.} and Holmgren, {William F.} and Michael Leuthold and Kim, {Chang Ki} and Cronin, {Alexander D} and Eric Betterton",
year = "2014",
month = "10",
day = "15",
doi = "10.1109/PVSC.2014.6925212",
language = "English (US)",
isbn = "9781479943982",
pages = "75--79",
booktitle = "2014 IEEE 40th Photovoltaic Specialist Conference, PVSC 2014",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Short-term PV power forecasts based on a real-time irradiance monitoring network

AU - Lorenzo, Antonio T.

AU - Holmgren, William F.

AU - Leuthold, Michael

AU - Kim, Chang Ki

AU - Cronin, Alexander D

AU - Betterton, Eric

PY - 2014/10/15

Y1 - 2014/10/15

N2 - We built an irradiance sensor network that we are now using to make operational, real-time, intra-hour forecasts of solar power at key locations. We developed reliable irradiance sensor hardware platforms to enable these sensor network forecasts. Using 19 of the 55 irradiance sensors we have throughout Tucson, we make retrospective forecasts of 26 days in April and evaluate their performance. We find that that our network forecasts outperform a persistence model for 1 to 28 minute time horizons as measured by the root mean squared error. The sensor hardware, our network forecasting method, error statistics, and future improvements to our forecasts are discussed.

AB - We built an irradiance sensor network that we are now using to make operational, real-time, intra-hour forecasts of solar power at key locations. We developed reliable irradiance sensor hardware platforms to enable these sensor network forecasts. Using 19 of the 55 irradiance sensors we have throughout Tucson, we make retrospective forecasts of 26 days in April and evaluate their performance. We find that that our network forecasts outperform a persistence model for 1 to 28 minute time horizons as measured by the root mean squared error. The sensor hardware, our network forecasting method, error statistics, and future improvements to our forecasts are discussed.

KW - data analysis

KW - forecasting

KW - real-time systems

KW - sensors

KW - solar energy

UR - http://www.scopus.com/inward/record.url?scp=84912091477&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84912091477&partnerID=8YFLogxK

U2 - 10.1109/PVSC.2014.6925212

DO - 10.1109/PVSC.2014.6925212

M3 - Conference contribution

AN - SCOPUS:84912091477

SN - 9781479943982

SP - 75

EP - 79

BT - 2014 IEEE 40th Photovoltaic Specialist Conference, PVSC 2014

PB - Institute of Electrical and Electronics Engineers Inc.

ER -