Regression Model Extractions of a T-Equivalent Circuit Modelling for Medium-Length Transmission Line Based-on the Parametric Simulation Approach

Selami Balcı; Mustafa Akkaya

Makale detayları

Regression Model Extractions of a T-Equivalent Circuit Modelling for Medium-Length Transmission Line Based-on the Parametric Simulation Approach

Yazarlar:

Selami Balcı | Mustafa Akkaya

Yayıncı:

Gazi University

Ana Başlıklar:

Elektrik Enerjisi Taşıma | Şebeke ve Sistemleri

Dergi:

Politeknik Dergisi Vol.27 Issue 4, pp.1649-1658

Belge Tipi:

Makale

Yayın Tarihi:

9/2024

Belge Dili:

İngilizce

Document ID (Org No.):

2001327705

pISSN:

2147-9429

Anahtar kelimeler:

Özet:

 In medium-length power transmission line models, the difference between the end-of-line and head-of-line voltage can be calculated with classical mathematical expressions. However, since the line parameters are not linear, these calculations can be approximated according to certain assumptions. The parametric data analysis approach proposed in this study obtained a data set for different variations by changing the line length and line parameters transmission line specific parameters such as resistance, inductance, and capacitance with certain steps. Then, using this data set, a classification is made with machine learning. In addition, data analysis is carried out with the end-of-line voltage value graphs obtained with different line parameters and the proposed approach is verified by constructing a test simulation circuit of a three-phase 200 km length with 154 kV line voltage value. Thus, a parametric simulation study has been presented, especially in electrical engineering education. In addition, Support Vector Regression SVR and Decision Tree Regression DTR models in the field of machine learning were used to measure the consistency of the data set created for 5 pF, 8 pF and 10 pF capacity values. With the figures and numerical data presented comparatively, it is clearly seen that the Long Short-Term Memory LSTM algorithm produces more successful scores in all three categories. In this context, the prediction accuracy was between 97 and 98 with DTR, while the accuracy was between 81 and 85 with SVR. Thus, prediction results in the range of 98 - 99 were obtained in the LSTM model.

 In medium-length power transmission line models, the difference between the end-of-line and head-of-line voltage can be calculated with classical mathematical expressions. However, since the line parameters are not linear, these calculations can be approximated according to certain assumptions. The parametric data analysis approach proposed in this study obtained a data set for different variations by changing the line length and line parameters transmission line specific parameters such as resistance, inductance, and capacitance with certain steps. Then, using this data set, a classification is made with machine learning. In addition, data analysis is carried out with the end-of-line voltage value graphs obtained with different line parameters and the proposed approach is verified by constructing a test simulation circuit of a three-phase 200 km length with 154 kV line voltage value. Thus, a parametric simulation study has been presented, especially in electrical engineering education. In addition, Support Vector Regression SVR and Decision Tree Regression DTR models in the field of machine learning were used to measure the consistency of the data set created for 5 pF, 8 pF and 10 pF capacity values. With the figures and numerical data presented comparatively, it is clearly seen that the Long Short-Term Memory LSTM algorithm produces more successful scores in all three categories. In this context, the prediction accuracy was between 97 and 98 with DTR, while the accuracy was between 81 and 85 with SVR. Thus, prediction results in the range of 98 - 99 were obtained in the LSTM model.

 In medium-length power transmission line models, the difference between the end-of-line and head-of-line voltage can be calculated with classical mathematical expressions. However, since the line parameters are not linear, these calculations can be approximated according to certain assumptions. The parametric data analysis approach proposed in this study obtained a data set for different variations by changing the line length and line parameters transmission line specific parameters such as resistance, inductance, and capacitance with certain steps. Then, using this data set, a classification is made with machine learning. In addition, data analysis is carried out with the end-of-line voltage value graphs obtained with different line parameters and the proposed approach is verified by constructing a test simulation circuit of a three-phase 200 km length with 154 kV line voltage value. Thus, a parametric simulation study has been presented, especially in electrical engineering education. In addition, Support Vector Regression SVR and Decision Tree Regression DTR models in the field of machine learning were used to measure the consistency of the data set created for 5 pF, 8 pF and 10 pF capacity values. With the figures and numerical data presented comparatively, it is clearly seen that the Long Short-Term Memory LSTM algorithm produces more successful scores in all three categories. In this context, the prediction accuracy was between 97 and 98 with DTR, while the accuracy was between 81 and 85 with SVR. Thus, prediction results in the range of 98 - 99 were obtained in the LSTM model.

 Orta uzunlukta enerji nakil hattı modellerinde hat sonu ve hat başı gerilimi arasındaki fark klasik matematiksel ifadelerle hesaplanabilmektedir. Ancak hat parametreleri doğrusal olmadığından bu hesaplamalara belirli varsayımlara göre yaklaşılabilir. Bu çalışmada önerilen parametrik veri analizi yaklaşımı, hat uzunluğunu ve hat parametrelerini direnç, endüktans, kapasitans gibi iletim hattına özgü parametreler belirli adımlarla değiştirerek farklı varyasyonlar için bir veri seti elde etmiştir. Daha sonra bu veri seti kullanılarak makine öğrenmesi ile bir sınıflandırma yapılmıştır. Ayrıca farklı hat parametreleri ile elde edilen hat sonu gerilim değeri grafikleri ile veri analizi yapılmış ve önerilen yaklaşım, 200 km uzunluğunda, 154 kV hat gerilim değerine sahip üç fazlı bir test simülasyon devresi kurularak doğrulanmıştır. Böylece özellikle elektrik mühendisliği eğitiminde parametrik bir simülasyon çalışması ortaya konmuştur. Ayrıca makine öğrenimi alanında Destek Vektör Regresyonu SVR ve Karar Ağacı Regresyonu DTR modelleri kullanılarak 5 pF, 8 pF ve 10 pF kapasite değerleri için oluşturulan veri setinin tutarlılığı ölçüldü. Karşılaştırmalı olarak sunulan rakamlar ve sayısal verilerle Uzun Kısa Süreli Bellek LSTM algoritmasının her üç kategoride de daha başarılı puanlar ürettiği açıkça görülüyor. Bu bağlamda DTR ile tahmin doğruluğu 97 ile 98 arasında, SVR ile ise doğruluk 81 ile 85 arasında gerçekleşti. Böylece LSTM modelinde 98 - 99 aralığında tahmin sonuçları elde edilmiştir.

Makale detayları

Regression Model Extractions of a T-Equivalent Circuit Modelling for Medium-Length Transmission Line Based-on the Parametric Simulation Approach

Yazarlar:

Selami Balcı | Mustafa Akkaya

Yayıncı:

Gazi University

Ana Başlıklar:

Elektrik Enerjisi Taşıma | Şebeke ve Sistemleri

Dergi:

Politeknik Dergisi Vol.27 Issue 4, pp.1649-1658

Belge Tipi:

Makale

Yayın Tarihi:

9/2024

Belge Dili:

İngilizce

Document ID (Org No.):

2001327705

pISSN:

2147-9429

Transmission line parameters

T-equivalent circuit modelling

DTR

SVR

LSTMİletim hattı parametreleri

T-eşdeğer devre modellemesi

DTR

SVR

LSTM.

Sayı

Makale detayları

Yazarlar: Selami Balcı | Mustafa Akkaya

Yayıncı: Gazi University

Ana Başlıklar: Elektrik Enerjisi Taşıma | Şebeke ve Sistemleri

Dergi: Politeknik Dergisi Vol.27 Issue 4, pp.1649-1658

Belge Tipi: Makale

Yayın Tarihi: 9/2024

Belge Dili: İngilizce

Document ID (Org No.): 2001327705

pISSN: 2147-9429

Sayı

Yazarlar:

Selami Balcı | Mustafa Akkaya

Yayıncı:

Gazi University

Ana Başlıklar:

Elektrik Enerjisi Taşıma | Şebeke ve Sistemleri

Dergi:

Politeknik Dergisi Vol.27 Issue 4, pp.1649-1658

Belge Tipi:

Makale

Yayın Tarihi:

9/2024

Belge Dili:

İngilizce

Document ID (Org No.):

2001327705

pISSN:

2147-9429