Evaluating Recursive Blind Forecast Against API and Baseline: A Puerto Rican Case Study on Solar Irradiance for Normal and Extreme Weather

Aditya Sundararajan; Mohammed Olama; Maximiliano Ferrari; Ben Ollis; Arturo Massol; Guodong Liu; Yang Chen

doi:10.1109/ECCE53617.2023.10362867

Evaluating Recursive Blind Forecast Against API and Baseline: A Puerto Rican Case Study on Solar Irradiance for Normal and Extreme Weather

Aditya Sundararajan, Mohammed Olama, Maximiliano Ferrari, Ben Ollis, Arturo Massol, Guodong Liu, Yang Chen

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Scopus citations

Abstract

This paper leverages ongoing work in a community microgrid in Adjuntas, Puerto Rico to forecast global horizontal irradiance (GHI) and compare performance in normal and extreme weather. Given a positive correlation of 0.98 between GHI and PV power, forecasting GHI can be an effective, indirect forecast of photovoltaic (PV) power, especially in microgrids where the end-users, owners, operators, or other stakeholders are reluctant to share data for training or validation due to privacy and security concerns. A recursive one-shot (termed as 'blind') forecast is, hence, formulated, wherein a gradient-boosted regression tree (GBR) is built to forecast GHI for a 7-day horizon in normal weather, and a 2-day horizon in extreme weather. To demonstrate its resilience, the architecture is trained on normal and hurricane weather GHI from 2002-2022. It is generalized on February 9-16, 2023, and on the landfall of Hurricane Nicole (Nov 4-5, 2022), respectively. Forecasts from GBR are compared against that from a satellite-based API resource and three baselines: persistence, averaging, and exponential smoothing. Results show GBR and persistence outperform sophisticated API in both types of weather for this case study.

Original language	English
Title of host publication	2023 IEEE Energy Conversion Congress and Exposition, ECCE 2023
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	1265-1270
Number of pages	6
ISBN (Electronic)	9798350316445
DOIs	https://doi.org/10.1109/ECCE53617.2023.10362867
State	Published - 2023
Event	2023 IEEE Energy Conversion Congress and Exposition, ECCE 2023 - Nashville, United States Duration: Oct 29 2023 → Nov 2 2023

Publication series

Name	2023 IEEE Energy Conversion Congress and Exposition, ECCE 2023

Conference

Conference	2023 IEEE Energy Conversion Congress and Exposition, ECCE 2023
Country/Territory	United States
City	Nashville
Period	10/29/23 → 11/2/23

Funding

This research work is based upon work supported by the U.S. Department of Energyâs Office of Energy Efficiency and Renewable Energy (EERE) under the Solar Energy Technologies Office Award Number (CID or WBS): DE-EE 37771. This manuscript has been authored by UT-Battelle, LLC, under contract DE-AC05-00OR22725 with the US Department of Energy (DOE). The US government retains and the publisher, by accepting the article for publication, acknowledges that the US government retains a nonexclusive, paid-up, irrevocable, worldwide license to publish or reproduce the published form of this manuscript, or allow others to do so, for US government purposes. DOE will provide public access to these results of federally sponsored research in accordance with the DOE Public Access Plan (https://www.energy.gov/doe-public-access-plan).

Keywords

GHI forecast
Gradient boosted trees
energy resilience
hurricane weather
microgrids

Access to Document

10.1109/ECCE53617.2023.10362867

Cite this

Sundararajan, A., Olama, M., Ferrari, M., Ollis, B., Massol, A., Liu, G., & Chen, Y. (2023). Evaluating Recursive Blind Forecast Against API and Baseline: A Puerto Rican Case Study on Solar Irradiance for Normal and Extreme Weather. In 2023 IEEE Energy Conversion Congress and Exposition, ECCE 2023 (pp. 1265-1270). (2023 IEEE Energy Conversion Congress and Exposition, ECCE 2023). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ECCE53617.2023.10362867

Sundararajan, Aditya ; Olama, Mohammed ; Ferrari, Maximiliano et al. / Evaluating Recursive Blind Forecast Against API and Baseline : A Puerto Rican Case Study on Solar Irradiance for Normal and Extreme Weather. 2023 IEEE Energy Conversion Congress and Exposition, ECCE 2023. Institute of Electrical and Electronics Engineers Inc., 2023. pp. 1265-1270 (2023 IEEE Energy Conversion Congress and Exposition, ECCE 2023).

@inproceedings{da796010e0054a6bb51c13f759d48230,

title = "Evaluating Recursive Blind Forecast Against API and Baseline: A Puerto Rican Case Study on Solar Irradiance for Normal and Extreme Weather",

abstract = "This paper leverages ongoing work in a community microgrid in Adjuntas, Puerto Rico to forecast global horizontal irradiance (GHI) and compare performance in normal and extreme weather. Given a positive correlation of 0.98 between GHI and PV power, forecasting GHI can be an effective, indirect forecast of photovoltaic (PV) power, especially in microgrids where the end-users, owners, operators, or other stakeholders are reluctant to share data for training or validation due to privacy and security concerns. A recursive one-shot (termed as 'blind') forecast is, hence, formulated, wherein a gradient-boosted regression tree (GBR) is built to forecast GHI for a 7-day horizon in normal weather, and a 2-day horizon in extreme weather. To demonstrate its resilience, the architecture is trained on normal and hurricane weather GHI from 2002-2022. It is generalized on February 9-16, 2023, and on the landfall of Hurricane Nicole (Nov 4-5, 2022), respectively. Forecasts from GBR are compared against that from a satellite-based API resource and three baselines: persistence, averaging, and exponential smoothing. Results show GBR and persistence outperform sophisticated API in both types of weather for this case study.",

keywords = "GHI forecast, Gradient boosted trees, energy resilience, hurricane weather, microgrids",

author = "Aditya Sundararajan and Mohammed Olama and Maximiliano Ferrari and Ben Ollis and Arturo Massol and Guodong Liu and Yang Chen",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 2023 IEEE Energy Conversion Congress and Exposition, ECCE 2023 ; Conference date: 29-10-2023 Through 02-11-2023",

year = "2023",

doi = "10.1109/ECCE53617.2023.10362867",

language = "English",

series = "2023 IEEE Energy Conversion Congress and Exposition, ECCE 2023",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "1265--1270",

booktitle = "2023 IEEE Energy Conversion Congress and Exposition, ECCE 2023",

}

Sundararajan, A , Olama, M, Ferrari, M, Ollis, B, Massol, A, Liu, G & Chen, Y 2023, Evaluating Recursive Blind Forecast Against API and Baseline: A Puerto Rican Case Study on Solar Irradiance for Normal and Extreme Weather. in 2023 IEEE Energy Conversion Congress and Exposition, ECCE 2023. 2023 IEEE Energy Conversion Congress and Exposition, ECCE 2023, Institute of Electrical and Electronics Engineers Inc., pp. 1265-1270, 2023 IEEE Energy Conversion Congress and Exposition, ECCE 2023, Nashville, United States, 10/29/23. https://doi.org/10.1109/ECCE53617.2023.10362867

Evaluating Recursive Blind Forecast Against API and Baseline: A Puerto Rican Case Study on Solar Irradiance for Normal and Extreme Weather. / Sundararajan, Aditya ; Olama, Mohammed; Ferrari, Maximiliano et al.
2023 IEEE Energy Conversion Congress and Exposition, ECCE 2023. Institute of Electrical and Electronics Engineers Inc., 2023. p. 1265-1270 (2023 IEEE Energy Conversion Congress and Exposition, ECCE 2023).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Evaluating Recursive Blind Forecast Against API and Baseline

T2 - 2023 IEEE Energy Conversion Congress and Exposition, ECCE 2023

AU - Sundararajan, Aditya

AU - Olama, Mohammed

AU - Ferrari, Maximiliano

AU - Ollis, Ben

AU - Massol, Arturo

AU - Liu, Guodong

AU - Chen, Yang

PY - 2023

Y1 - 2023

N2 - This paper leverages ongoing work in a community microgrid in Adjuntas, Puerto Rico to forecast global horizontal irradiance (GHI) and compare performance in normal and extreme weather. Given a positive correlation of 0.98 between GHI and PV power, forecasting GHI can be an effective, indirect forecast of photovoltaic (PV) power, especially in microgrids where the end-users, owners, operators, or other stakeholders are reluctant to share data for training or validation due to privacy and security concerns. A recursive one-shot (termed as 'blind') forecast is, hence, formulated, wherein a gradient-boosted regression tree (GBR) is built to forecast GHI for a 7-day horizon in normal weather, and a 2-day horizon in extreme weather. To demonstrate its resilience, the architecture is trained on normal and hurricane weather GHI from 2002-2022. It is generalized on February 9-16, 2023, and on the landfall of Hurricane Nicole (Nov 4-5, 2022), respectively. Forecasts from GBR are compared against that from a satellite-based API resource and three baselines: persistence, averaging, and exponential smoothing. Results show GBR and persistence outperform sophisticated API in both types of weather for this case study.

AB - This paper leverages ongoing work in a community microgrid in Adjuntas, Puerto Rico to forecast global horizontal irradiance (GHI) and compare performance in normal and extreme weather. Given a positive correlation of 0.98 between GHI and PV power, forecasting GHI can be an effective, indirect forecast of photovoltaic (PV) power, especially in microgrids where the end-users, owners, operators, or other stakeholders are reluctant to share data for training or validation due to privacy and security concerns. A recursive one-shot (termed as 'blind') forecast is, hence, formulated, wherein a gradient-boosted regression tree (GBR) is built to forecast GHI for a 7-day horizon in normal weather, and a 2-day horizon in extreme weather. To demonstrate its resilience, the architecture is trained on normal and hurricane weather GHI from 2002-2022. It is generalized on February 9-16, 2023, and on the landfall of Hurricane Nicole (Nov 4-5, 2022), respectively. Forecasts from GBR are compared against that from a satellite-based API resource and three baselines: persistence, averaging, and exponential smoothing. Results show GBR and persistence outperform sophisticated API in both types of weather for this case study.

KW - GHI forecast

KW - Gradient boosted trees

KW - energy resilience

KW - hurricane weather

KW - microgrids

UR - http://www.scopus.com/inward/record.url?scp=85180004482&partnerID=8YFLogxK

U2 - 10.1109/ECCE53617.2023.10362867

DO - 10.1109/ECCE53617.2023.10362867

M3 - Conference contribution

AN - SCOPUS:85180004482

T3 - 2023 IEEE Energy Conversion Congress and Exposition, ECCE 2023

SP - 1265

EP - 1270

BT - 2023 IEEE Energy Conversion Congress and Exposition, ECCE 2023

PB - Institute of Electrical and Electronics Engineers Inc.

Y2 - 29 October 2023 through 2 November 2023

ER -

Sundararajan A , Olama M, Ferrari M, Ollis B, Massol A, Liu G et al. Evaluating Recursive Blind Forecast Against API and Baseline: A Puerto Rican Case Study on Solar Irradiance for Normal and Extreme Weather. In 2023 IEEE Energy Conversion Congress and Exposition, ECCE 2023. Institute of Electrical and Electronics Engineers Inc. 2023. p. 1265-1270. (2023 IEEE Energy Conversion Congress and Exposition, ECCE 2023). doi: 10.1109/ECCE53617.2023.10362867

Evaluating Recursive Blind Forecast Against API and Baseline: A Puerto Rican Case Study on Solar Irradiance for Normal and Extreme Weather

Abstract

Publication series

Conference

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this