FEU Institute of Technology

Educational Innovation and Technology Hub

Loading...

Assessment of Reanalysis Data for Solar PV Output Forecasting in the Philippines: Case of Pangasinan, Negros Occidental, and Davao Del Norte

The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences

(2024), Vol. XLVIII-4/W8-2023, pp. 279-284

C. J. A. Gavina a , J. A. Ibañez b , Ian B. Benitez b,c , C. D. Lumabad III b,d , J. A. Principe e

a Department of Electrical Engineering, Pamantasan ng Lungsod ng Maynila, Manila City, Philippines

b National Engineering Center, University of the Philippines Diliman, Quezon City, Philippines

c Electrical Engineering Department, FEU Institute of Technology, Manila City, Philippines

d Department of Computer, Electronics, and Electrical Engineering, Cavite State University, Don Severino Delas Alas Campus, Indang, Philippines

e Department of Geodetic Engineering, University of the Philippines Diliman, Quezon City, Philippines

Abstract: Abstract. The sustainable energy transition in the Philippines requires accurate forecasting of solar PV output to optimize energy efficiency and grid management. While existing studies have emphasized the positive correlation between solar irradiance and PV production, this study aims to explore whether forecasting improves with the inclusion of weather data. This research conducts a comparative analysis between relying solely on solar irradiance against integrating various weather parameters to enhance solar PV output forecasting. The study focuses on three distinct locations (Pangasinan, Negros Occidental, and Davao Del Norte) and employs two models per each site: Model 1 (M1), which relies only on solar irradiance as predictors, and Model 2 (M2), which incorporates solar irradiance and weather parameters. Using Fifth Generation ECMWF Reanalysis (ERA5) Data, Principal Component Analysis (PCA) is conducted on the significant weather parameters. Extreme Gradient Boosting (XGBoost) with 5-fold nested cross-validation is applied for solar PV output forecasting. Models are assessed using Mean Absolute Percentage Error (MAPE) and skill scores. Results showthat while solar irradiance alone suffices for predicting solar PV output in Negros Occidental, incorporating weather parameters improves forecasting accuracy in Davao Del Norte and Pangasinan. This paper recommends caution in generalizing the findings to different regions with varying weather patterns, as the forecasting performance of the models is influenced by data quality, specific location, and prevailing weather conditions.

Recommended APA Citation:

Gavina, C. J. A., Ibañez, J. A., Benitez, I. B., III, C. D. L., & Principe, J. A. (2024). Assessment of Reanalysis Data for Solar PV Output Forecasting in the Philippines: Case of Pangasinan, Negros Occidental, and Davao Del Norte. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, XLVIII-4/W8-2023, 279-284. https://doi.org/10.5194/isprs-archives-XLVIII-4-W8-2023-279-2024

A Time Capsule Where Research Rests, Legends Linger, and PDFs Live Forever

Repository is the home for every research paper and capstone project created across our institution. It’s where knowledge kicks back, ideas live on, and your hard work finds the spotlight it deserves.

© 2025 Educational Innovation and Technology Hub. All Rights Reserved.