Short-term forecasting of rooftop retrofitted photovoltaic power generation using machine learning

This paper explores short-term forecasting of rooftop retrofitted photovoltaic (PV) power generation using a Neural Networks (NN) model, highlighting its importance for energy management and grid integration. The study used data from the Universiti Malaysia Pahang Al-Sultan Abdullah (UMPSA) of the F...

Full description

Bibliographic Details
Main Authors: Mohd Herwan, Sulaiman, Mohd Shawal, Jadin, Zuriani, Mustaffa, Hamdan, Daniyal, Mohd Nurulakla, Mohd Azlan
Format: Article
Language:English
English
Published: Elsevier Ltd 2024
Subjects:
Online Access:http://umpir.ump.edu.my/id/eprint/42350/
http://umpir.ump.edu.my/id/eprint/42350/1/Short-term%20forecasting%20of%20rooftop%20retrofitted%20photovoltaic_ABST.pdf
http://umpir.ump.edu.my/id/eprint/42350/2/Short-term%20forecasting%20of%20rooftop%20retrofitted%20photovoltaic.pdf
_version_ 1848826587344011264
author Mohd Herwan, Sulaiman
Mohd Shawal, Jadin
Zuriani, Mustaffa
Hamdan, Daniyal
Mohd Nurulakla, Mohd Azlan
author_facet Mohd Herwan, Sulaiman
Mohd Shawal, Jadin
Zuriani, Mustaffa
Hamdan, Daniyal
Mohd Nurulakla, Mohd Azlan
author_sort Mohd Herwan, Sulaiman
building UMP Institutional Repository
collection Online Access
description This paper explores short-term forecasting of rooftop retrofitted photovoltaic (PV) power generation using a Neural Networks (NN) model, highlighting its importance for energy management and grid integration. The study used data from the Universiti Malaysia Pahang Al-Sultan Abdullah (UMPSA) of the Faculty of Electrical & Electronics Engineering Technology (FTKEE), capturing a 570.4 kWp rooftop PV system. The data, collected at 15-min intervals from January 29 to February 4, 2024, included thirty-three input features such as ambient temperature, horizontal irradiation, AC voltages, AC currents, and Maximum Power Point Trackers (MPPTs). The target was the total active power in kilowatts. The methodology involved partitioning the data into a training set covering the first five days and a testing set for the last two days. The NN model was compared with other machine learning approaches, including Long Short-Term Memory Networks (LSTM), Gated Recurrent Units (GRU), Random Forest (RF), and k-Nearest Neighbors (k-NN). Performance metrics: Root Mean Square Error (RMSE), Mean Absolute Error (MAE), Maximum Error, and Standard Deviation were used to evaluate the models. The results showed that the NN model outperformed all other models, achieving an RMSE of 0.7098, an MAE of 0.3629, a Maximum Error of 3.901, and a Standard Deviation of 0.7076. These findings suggest that NN effectively capture complex patterns in rooftop PV system data, contributing to enhanced reliability and efficiency in short-term solar power forecasting. The study's implications extend to improved grid management and energy efficiency, underlining the significance of advanced machine learning techniques in renewable energy forecasting.
first_indexed 2025-11-15T03:47:11Z
format Article
id ump-42350
institution Universiti Malaysia Pahang
institution_category Local University
language English
English
last_indexed 2025-11-15T03:47:11Z
publishDate 2024
publisher Elsevier Ltd
recordtype eprints
repository_type Digital Repository
spelling ump-423502024-08-14T04:18:00Z http://umpir.ump.edu.my/id/eprint/42350/ Short-term forecasting of rooftop retrofitted photovoltaic power generation using machine learning Mohd Herwan, Sulaiman Mohd Shawal, Jadin Zuriani, Mustaffa Hamdan, Daniyal Mohd Nurulakla, Mohd Azlan TK Electrical engineering. Electronics Nuclear engineering This paper explores short-term forecasting of rooftop retrofitted photovoltaic (PV) power generation using a Neural Networks (NN) model, highlighting its importance for energy management and grid integration. The study used data from the Universiti Malaysia Pahang Al-Sultan Abdullah (UMPSA) of the Faculty of Electrical & Electronics Engineering Technology (FTKEE), capturing a 570.4 kWp rooftop PV system. The data, collected at 15-min intervals from January 29 to February 4, 2024, included thirty-three input features such as ambient temperature, horizontal irradiation, AC voltages, AC currents, and Maximum Power Point Trackers (MPPTs). The target was the total active power in kilowatts. The methodology involved partitioning the data into a training set covering the first five days and a testing set for the last two days. The NN model was compared with other machine learning approaches, including Long Short-Term Memory Networks (LSTM), Gated Recurrent Units (GRU), Random Forest (RF), and k-Nearest Neighbors (k-NN). Performance metrics: Root Mean Square Error (RMSE), Mean Absolute Error (MAE), Maximum Error, and Standard Deviation were used to evaluate the models. The results showed that the NN model outperformed all other models, achieving an RMSE of 0.7098, an MAE of 0.3629, a Maximum Error of 3.901, and a Standard Deviation of 0.7076. These findings suggest that NN effectively capture complex patterns in rooftop PV system data, contributing to enhanced reliability and efficiency in short-term solar power forecasting. The study's implications extend to improved grid management and energy efficiency, underlining the significance of advanced machine learning techniques in renewable energy forecasting. Elsevier Ltd 2024-10-01 Article PeerReviewed pdf en http://umpir.ump.edu.my/id/eprint/42350/1/Short-term%20forecasting%20of%20rooftop%20retrofitted%20photovoltaic_ABST.pdf pdf en http://umpir.ump.edu.my/id/eprint/42350/2/Short-term%20forecasting%20of%20rooftop%20retrofitted%20photovoltaic.pdf Mohd Herwan, Sulaiman and Mohd Shawal, Jadin and Zuriani, Mustaffa and Hamdan, Daniyal and Mohd Nurulakla, Mohd Azlan (2024) Short-term forecasting of rooftop retrofitted photovoltaic power generation using machine learning. Journal of Building Engineering, 94 (109948). pp. 1-16. ISSN 2352-7102. (Published) https://doi.org/10.1016/j.jobe.2024.109948 https://doi.org/10.1016/j.jobe.2024.109948
spellingShingle TK Electrical engineering. Electronics Nuclear engineering
Mohd Herwan, Sulaiman
Mohd Shawal, Jadin
Zuriani, Mustaffa
Hamdan, Daniyal
Mohd Nurulakla, Mohd Azlan
Short-term forecasting of rooftop retrofitted photovoltaic power generation using machine learning
title Short-term forecasting of rooftop retrofitted photovoltaic power generation using machine learning
title_full Short-term forecasting of rooftop retrofitted photovoltaic power generation using machine learning
title_fullStr Short-term forecasting of rooftop retrofitted photovoltaic power generation using machine learning
title_full_unstemmed Short-term forecasting of rooftop retrofitted photovoltaic power generation using machine learning
title_short Short-term forecasting of rooftop retrofitted photovoltaic power generation using machine learning
title_sort short-term forecasting of rooftop retrofitted photovoltaic power generation using machine learning
topic TK Electrical engineering. Electronics Nuclear engineering
url http://umpir.ump.edu.my/id/eprint/42350/
http://umpir.ump.edu.my/id/eprint/42350/
http://umpir.ump.edu.my/id/eprint/42350/
http://umpir.ump.edu.my/id/eprint/42350/1/Short-term%20forecasting%20of%20rooftop%20retrofitted%20photovoltaic_ABST.pdf
http://umpir.ump.edu.my/id/eprint/42350/2/Short-term%20forecasting%20of%20rooftop%20retrofitted%20photovoltaic.pdf