Forecasting Natural Gas Consumption by User Type Using Machine Learning: A Comparative Study

Süleyman Tekin; Serhat Peker; Nurhan Dudaklı

Makale detayları

Forecasting Natural Gas Consumption by User Type Using Machine Learning: A Comparative Study

Yazarlar:

Süleyman Tekin | Serhat Peker | Nurhan Dudaklı

Yayıncı:

Gazi University

Ana Başlıklar:

Data Mining and Knowledge Discovery

Dergi:

Gazi University Journal of Science Part A: Engineering and Innovation Vol.12 Issue 2, pp.632-651

Belge Tipi:

Makale

Yayın Tarihi:

6/2025

Belge Dili:

İngilizce

Document ID (Org No.):

2001348252

pISSN:

2147-9542

Anahtar kelimeler:

Özet:

 This study aims to develop user-type-specific machine learning models to forecast natural gas consumption for residential and commercial user groups in İzmir, Turkey. Multiple Linear Regression, Random Forest, LightGBM, and XGBoost algorithms were implemented, and model performance was enhanced through hyperparameter optimization. The models were evaluated using MAE and RMSE metrics. Results indicate that LightGBM and Random Forest provided the most accurate forecasts overall, with LightGBM performing best in the residential group and Random Forest slightly outperforming others in the commercial group. In contrast, MLR underperformed due to the non-linear nature of the data. Residential consumption patterns were found to be more predictable, leading to lower error rates, whereas the commercial group exhibited higher variability and forecast challenges. The study highlights the importance of distinguishing user types and employing well-tuned machine learning algorithms for improved energy demand forecasting.

 This study aims to develop user-type-specific machine learning models to forecast natural gas consumption for residential and commercial user groups in İzmir, Turkey. Multiple Linear Regression, Random Forest, LightGBM, and XGBoost algorithms were implemented, and model performance was enhanced through hyperparameter optimization. The models were evaluated using MAE and RMSE metrics. Results indicate that LightGBM and Random Forest provided the most accurate forecasts overall, with LightGBM performing best in the residential group and Random Forest slightly outperforming others in the commercial group. In contrast, MLR underperformed due to the non-linear nature of the data. Residential consumption patterns were found to be more predictable, leading to lower error rates, whereas the commercial group exhibited higher variability and forecast challenges. The study highlights the importance of distinguishing user types and employing well-tuned machine learning algorithms for improved energy demand forecasting.

 This study aims to develop user-type-specific machine learning models to forecast natural gas consumption for residential and commercial user groups in İzmir, Turkey. Multiple Linear Regression, Random Forest, LightGBM, and XGBoost algorithms were implemented, and model performance was enhanced through hyperparameter optimization. The models were evaluated using MAE and RMSE metrics. Results indicate that LightGBM and Random Forest provided the most accurate forecasts overall, with LightGBM performing best in the residential group and Random Forest slightly outperforming others in the commercial group. In contrast, MLR underperformed due to the non-linear nature of the data. Residential consumption patterns were found to be more predictable, leading to lower error rates, whereas the commercial group exhibited higher variability and forecast challenges. The study highlights the importance of distinguishing user types and employing well-tuned machine learning algorithms for improved energy demand forecasting.

 This study aims to develop user-type-specific machine learning models to forecast natural gas consumption for residential and commercial user groups in İzmir, Turkey. Multiple Linear Regression, Random Forest, LightGBM, and XGBoost algorithms were implemented, and model performance was enhanced through hyperparameter optimization. The models were evaluated using MAE and RMSE metrics. Results indicate that LightGBM and Random Forest provided the most accurate forecasts overall, with LightGBM performing best in the residential group and Random Forest slightly outperforming others in the commercial group. In contrast, MLR underperformed due to the non-linear nature of the data. Residential consumption patterns were found to be more predictable, leading to lower error rates, whereas the commercial group exhibited higher variability and forecast challenges. The study highlights the importance of distinguishing user types and employing well-tuned machine learning algorithms for improved energy demand forecasting.

Makale detayları

Forecasting Natural Gas Consumption by User Type Using Machine Learning: A Comparative Study

Yazarlar:

Süleyman Tekin | Serhat Peker | Nurhan Dudaklı

Yayıncı:

Gazi University

Ana Başlıklar:

Data Mining and Knowledge Discovery

Dergi:

Gazi University Journal of Science Part A: Engineering and Innovation Vol.12 Issue 2, pp.632-651

Belge Tipi:

Makale

Yayın Tarihi:

6/2025

Belge Dili:

İngilizce

Document ID (Org No.):

2001348252

pISSN:

2147-9542

Natural Gas Consumption

Energy Forecasting

Machine Learning

User-Type Analysis

Data Science

Hyperparameter Optimization

Sayı

Makale detayları

Forecasting Natural Gas Consumption by User Type Using Machine Learning: A Comparative Study

Yazarlar: Süleyman Tekin | Serhat Peker | Nurhan Dudaklı

Yayıncı: Gazi University

Ana Başlıklar: Data Mining and Knowledge Discovery

Dergi: Gazi University Journal of Science Part A: Engineering and Innovation Vol.12 Issue 2, pp.632-651

Belge Tipi: Makale

Yayın Tarihi: 6/2025

Belge Dili: İngilizce

Document ID (Org No.): 2001348252

pISSN: 2147-9542

Natural Gas Consumption

Energy Forecasting

Machine Learning

User-Type Analysis

Data Science

Hyperparameter Optimization

Sayı

Yazarlar:

Süleyman Tekin | Serhat Peker | Nurhan Dudaklı

Yayıncı:

Gazi University

Ana Başlıklar:

Data Mining and Knowledge Discovery

Dergi:

Gazi University Journal of Science Part A: Engineering and Innovation Vol.12 Issue 2, pp.632-651

Belge Tipi:

Makale

Yayın Tarihi:

6/2025

Belge Dili:

İngilizce

Document ID (Org No.):

2001348252

pISSN:

2147-9542