Short-Term Electricity Load Forecasting Using Artificial Intelligence (Artificial Neural Networks) Method and Meteorological Data for Sivas-Central 1st Organized Industrial Zone

Seyit Ahmet Keklikci; Yunis Torun

Makale detayları

Short-Term Electricity Load Forecasting Using Artificial Intelligence (Artificial Neural Networks) Method and Meteorological Data for Sivas-Central 1st Organized Industrial Zone

Yazarlar:

Seyit Ahmet Keklikci | Yunis Torun

Yayıncı:

Sivas Cumhuriyet University

Ana Başlıklar:

Elektrik Mühendisliği (Diğer)

Dergi:

Sivas Cumhuriyet Üniversitesi Mühendislik Fakültesi Dergisi Vol.3 Issue 1, pp.20-31

Belge Tipi:

Makale

Yayın Tarihi:

6/2025

Belge Dili:

İngilizce

Document ID (Org No.):

2001353115

pISSN:

3023-7203

Anahtar kelimeler:

Özet:

 The effective use of electricity, accurate prediction methods are becoming important for energy planning and prevention of imbalance costs. Efficient, high-quality, and safe electricity supply processes are also crucial for maintaining the supply-demand balance in the electricity market. Therefore, it is necessary for electricity producers and suppliers to make good planning, and there is a need to predict unrealized consumption values for planning activities. The aim of this study is to make short-term electricity load forecasting for Sivas-Central 1st Organized Industrial Zone using meteorological data and past consumption values. It has been observed in the literature that artificial intelligence, especially Long Short Term Memory LSTM architectures, are effectively used in the energy forecasting field. In this study, an LSTM architecture was created using MatlabSimulink to make load forecasts. In this architecture, four cases are used using different data sets for input data. In the first case, only days of the year are used as input data sets. For the second case, Month, Day of Month, Working Day and Days of Year are used. For the third case, additional Holiday Days, Holiday, Weekend, Normal Day, Dollar data is used in the second case. In the fourth case, additional Meteorology data is used in the third case. As a result, the RMSE values for the four cases are as follows; RMSE1: 1501.897, RMSE2: 1005.312, RMSE3: 1343.179, RMSE4: 9342.352. This study aims to provide effective solutions in supply-demand balance and energy management. This study deeply analyzes the effect of different data combinations on LSTM-based consumption estimation and offers an original contribution in terms of showing that using more data does not always provide better estimation accuracy. The aim is to provide significant contribution to energy suppliers and industrial zones for accurate energy management through the predictions made.

 The effective use of electricity, accurate prediction methods are becoming important for energy planning and prevention of imbalance costs. Efficient, high-quality, and safe electricity supply processes are also crucial for maintaining the supply-demand balance in the electricity market. Therefore, it is necessary for electricity producers and suppliers to make good planning, and there is a need to predict unrealized consumption values for planning activities. The aim of this study is to make short-term electricity load forecasting for Sivas-Central 1st Organized Industrial Zone using meteorological data and past consumption values. It has been observed in the literature that artificial intelligence, especially Long Short Term Memory LSTM architectures, are effectively used in the energy forecasting field. In this study, an LSTM architecture was created using MatlabSimulink to make load forecasts. In this architecture, four cases are used using different data sets for input data. In the first case, only days of the year are used as input data sets. For the second case, Month, Day of Month, Working Day and Days of Year are used. For the third case, additional Holiday Days, Holiday, Weekend, Normal Day, Dollar data is used in the second case. In the fourth case, additional Meteorology data is used in the third case. As a result, the RMSE values for the four cases are as follows; RMSE1: 1501.897, RMSE2: 1005.312, RMSE3: 1343.179, RMSE4: 9342.352. This study aims to provide effective solutions in supply-demand balance and energy management. This study deeply analyzes the effect of different data combinations on LSTM-based consumption estimation and offers an original contribution in terms of showing that using more data does not always provide better estimation accuracy. The aim is to provide significant contribution to energy suppliers and industrial zones for accurate energy management through the predictions made.

 The effective use of electricity, accurate prediction methods are becoming important for energy planning and prevention of imbalance costs. Efficient, high-quality, and safe electricity supply processes are also crucial for maintaining the supply-demand balance in the electricity market. Therefore, it is necessary for electricity producers and suppliers to make good planning, and there is a need to predict unrealized consumption values for planning activities. The aim of this study is to make short-term electricity load forecasting for Sivas-Central 1st Organized Industrial Zone using meteorological data and past consumption values. It has been observed in the literature that artificial intelligence, especially Long Short Term Memory LSTM architectures, are effectively used in the energy forecasting field. In this study, an LSTM architecture was created using MatlabSimulink to make load forecasts. In this architecture, four cases are used using different data sets for input data. In the first case, only days of the year are used as input data sets. For the second case, Month, Day of Month, Working Day and Days of Year are used. For the third case, additional Holiday Days, Holiday, Weekend, Normal Day, Dollar data is used in the second case. In the fourth case, additional Meteorology data is used in the third case. As a result, the RMSE values for the four cases are as follows; RMSE1: 1501.897, RMSE2: 1005.312, RMSE3: 1343.179, RMSE4: 9342.352. This study aims to provide effective solutions in supply-demand balance and energy management. This study deeply analyzes the effect of different data combinations on LSTM-based consumption estimation and offers an original contribution in terms of showing that using more data does not always provide better estimation accuracy. The aim is to provide significant contribution to energy suppliers and industrial zones for accurate energy management through the predictions made.

 Elektrik enerjisinin efektif bir şekilde kullanılması, enerji planlaması ve dengesizlik maliyetlerinin önlenmesi için doğru tahminleme metotları önem kazanmaktadır. Verimli, kaliteli ve güvenli elektrik tedarik süreçleri elektrik piyasasındaki arz - talep dengesinin korunması için de oldukça önemlidir. Bu nedenle elektrik üretici ve tedarikçilerinin iyi planlama yapması, planlama çalışmaları için de gerçekleşmemiş tüketim değerlerinin tahminlenmesi ihtiyacı doğmaktadır. Bu çalışmanın amacı, meteoroloji verileri ve geçmiş tüketim değerlerini kullanarak Sivas-Merkez 1. Organize Sanayi Bölgesinin kısa dönem elektrik yük tahminini yapmaktır. Literatürde yapay zeka ve özellikle Uzun Kısa Süreli Bellek Long Short Term Memory-LSTM mimarilerinin enerji tahmini alanında etkin bir şekilde kullanıldığı görülmüştür. Bu çalışmada yük tahmini yapabilmek için MatlabSimulink aracılığıyla LSTM mimarisi oluşturulmuştur. Bu mimaride giriş verileri için farklı veri setleri kullanılarak dört durum incelenmiştir. Birinci durumda giriş veri seti olarak sadece yılın günleri kullanılmıştır. İkinci durum için Ay, Ayın Günü, Mesai Günü ve Yılın Günleri kullanılmıştır. Üçüncü durum için ikinci duruma ek Bayram Günleri, Tatil, Hafta sonu, Normal Gün, Dolar verileri kullanılmıştır. Dördüncü durumda ise üçüncü duruma ek olarak Meteoroloji verileri kullanılmıştır. Sonuç olarak RMSE değerleri dört için sırası ile şu şekildedir; RMSE1:1501,897 , RMSE2:1005,312 , RMSE3:1343,179 , RMSE4:9342,352. Bu çalışma ile arz talep dengesi ve enerji yönetiminde etkili çözümler sunulması amaçlanmıştır. Bu çalışma, farklı veri kombinasyonlarının LSTM tabanlı tüketim tahminine etkisini derinlemesine analiz ederek, daha fazla veri kullanımının her zaman daha iyi tahmin doğruluğu sağlamayacağını göstermesi bakımından özgün bir katkı sunmaktadır. Yapılan tahminlemelerle enerji tedarikçilerinin ve sanayi bölgelerinin doğru enerji yönetimi yapabilmesi için önemli bir katkı sağlanması amaçlanmaktadır.

Makale detayları

Short-Term Electricity Load Forecasting Using Artificial Intelligence (Artificial Neural Networks) Method and Meteorological Data for Sivas-Central 1st Organized Industrial Zone

Yazarlar:

Seyit Ahmet Keklikci | Yunis Torun

Yayıncı:

Sivas Cumhuriyet University

Ana Başlıklar:

Elektrik Mühendisliği (Diğer)

Dergi:

Sivas Cumhuriyet Üniversitesi Mühendislik Fakültesi Dergisi Vol.3 Issue 1, pp.20-31

Belge Tipi:

Makale

Yayın Tarihi:

6/2025

Belge Dili:

İngilizce

Document ID (Org No.):

2001353115

pISSN:

3023-7203

Artificial Neural Networks

LSTM

Electricity Consumption

Load Estimation

Artificial IntelligenceLSTM

Yük tahmini

Elektrik Tüketimi

Yapay Sinir Ağları

Yapay Zeka

Sayı

Makale detayları

Yazarlar: Seyit Ahmet Keklikci | Yunis Torun

Yayıncı: Sivas Cumhuriyet University

Ana Başlıklar: Elektrik Mühendisliği (Diğer)

Dergi: Sivas Cumhuriyet Üniversitesi Mühendislik Fakültesi Dergisi Vol.3 Issue 1, pp.20-31

Belge Tipi: Makale

Yayın Tarihi: 6/2025

Belge Dili: İngilizce

Document ID (Org No.): 2001353115

pISSN: 3023-7203

Sayı

Yazarlar:

Seyit Ahmet Keklikci | Yunis Torun

Yayıncı:

Sivas Cumhuriyet University

Ana Başlıklar:

Elektrik Mühendisliği (Diğer)

Dergi:

Sivas Cumhuriyet Üniversitesi Mühendislik Fakültesi Dergisi Vol.3 Issue 1, pp.20-31

Belge Tipi:

Makale

Yayın Tarihi:

6/2025

Belge Dili:

İngilizce

Document ID (Org No.):

2001353115

pISSN:

3023-7203