Application of Contemporary Artificial Intelligence Algorithms in Real Energy Consumption Estimation in Residences

Fatih Atalar; Ertuğrul Adıgüzel; Aysel Ersoy

Article Details

Application of Contemporary Artificial Intelligence Algorithms in Real Energy Consumption Estimation in Residences

Authors:

Fatih Atalar | Ertuğrul Adıgüzel | Aysel Ersoy

Publisher:

Necmettin Erbakan University

Main Topics:

Elektrik Tesisleri

Journal:

Necmettin Erbakan Üniversitesi Fen ve Mühendislik Bilimleri Dergisi Vol.7 Issue 1, pp.31-47

Document Type:

Article

Publication Date:

4/2025

Document Language:

English

Document ID (Org No.):

2001338796

pISSN:

2667-7989

Keywords:

Abstract:

 The acceleration of industrialisation has resulted in a corresponding increase in the demand for energy supplies, driven by the growing use of new generation electronic equipment in residential settings. The advent of renewable energy, or green energy, has prompted a shift away from traditional methods of energy production, such as the use of natural gas and fossil fuels. However, this transition has given rise to a number of challenges. It is of great importance to monitor data in order to integrate the obtained electricity into the system and to monitor it. The acquisition of energy data on a large scale is made possible by the implementation of dynamic relay communication within micro and macro scale smart grids, which have been specifically designed for this purpose. Deep learning algorithms and machine learning methods are employed for the processing and analysis of data obtained in the context of the Internet of Things IoT. The implementation of these methods enables smart grids to operate with reduced loss and enhanced efficiency. The estimation of energy consumption at the smallest scale facilitates the implementation of optimised energy management strategies. By ensuring the flow of electricity in the optimal amount power, the potential for waste can be mitigated. The rapid and sophisticated responses of machine and deep learning algorithms facilitate more structured and sustainable energy management for both users and producers. In this study, four years worth of electrical energy data from residential sources was analysed using techniques such as Convolutional Neural Network, Long Short-Term Memory, Random Forest and K-Nearest Neighbours Regression. The resulting analyses enabled the estimation of energy consumption. To assess the efficacy of learning algorithms in the study across varying training and test data ratios, the dataset was partitioned using three distinct division methods: hold-out 90 training - 10 testing, hold-out 80 training - 20 testing, and a 67 training - 33 testing split. Additionally, a 10-fold cross-validation approach was employed for further evaluation. Comparative analysis revealed that the LSTM model emerged as the top-performing model, boasting the lowest MSE value of 0.0054 for daily forecasts.

 The acceleration of industrialisation has resulted in a corresponding increase in the demand for energy supplies, driven by the growing use of new generation electronic equipment in residential settings. The advent of renewable energy, or green energy, has prompted a shift away from traditional methods of energy production, such as the use of natural gas and fossil fuels. However, this transition has given rise to a number of challenges. It is of great importance to monitor data in order to integrate the obtained electricity into the system and to monitor it. The acquisition of energy data on a large scale is made possible by the implementation of dynamic relay communication within micro and macro scale smart grids, which have been specifically designed for this purpose. Deep learning algorithms and machine learning methods are employed for the processing and analysis of data obtained in the context of the Internet of Things IoT. The implementation of these methods enables smart grids to operate with reduced loss and enhanced efficiency. The estimation of energy consumption at the smallest scale facilitates the implementation of optimised energy management strategies. By ensuring the flow of electricity in the optimal amount power, the potential for waste can be mitigated. The rapid and sophisticated responses of machine and deep learning algorithms facilitate more structured and sustainable energy management for both users and producers. In this study, four years worth of electrical energy data from residential sources was analysed using techniques such as Convolutional Neural Network, Long Short-Term Memory, Random Forest and K-Nearest Neighbours Regression. The resulting analyses enabled the estimation of energy consumption. To assess the efficacy of learning algorithms in the study across varying training and test data ratios, the dataset was partitioned using three distinct division methods: hold-out 90 training - 10 testing, hold-out 80 training - 20 testing, and a 67 training - 33 testing split. Additionally, a 10-fold cross-validation approach was employed for further evaluation. Comparative analysis revealed that the LSTM model emerged as the top-performing model, boasting the lowest MSE value of 0.0054 for daily forecasts.

 The acceleration of industrialisation has resulted in a corresponding increase in the demand for energy supplies, driven by the growing use of new generation electronic equipment in residential settings. The advent of renewable energy, or green energy, has prompted a shift away from traditional methods of energy production, such as the use of natural gas and fossil fuels. However, this transition has given rise to a number of challenges. It is of great importance to monitor data in order to integrate the obtained electricity into the system and to monitor it. The acquisition of energy data on a large scale is made possible by the implementation of dynamic relay communication within micro and macro scale smart grids, which have been specifically designed for this purpose. Deep learning algorithms and machine learning methods are employed for the processing and analysis of data obtained in the context of the Internet of Things IoT. The implementation of these methods enables smart grids to operate with reduced loss and enhanced efficiency. The estimation of energy consumption at the smallest scale facilitates the implementation of optimised energy management strategies. By ensuring the flow of electricity in the optimal amount power, the potential for waste can be mitigated. The rapid and sophisticated responses of machine and deep learning algorithms facilitate more structured and sustainable energy management for both users and producers. In this study, four years worth of electrical energy data from residential sources was analysed using techniques such as Convolutional Neural Network, Long Short-Term Memory, Random Forest and K-Nearest Neighbours Regression. The resulting analyses enabled the estimation of energy consumption. To assess the efficacy of learning algorithms in the study across varying training and test data ratios, the dataset was partitioned using three distinct division methods: hold-out 90 training - 10 testing, hold-out 80 training - 20 testing, and a 67 training - 33 testing split. Additionally, a 10-fold cross-validation approach was employed for further evaluation. Comparative analysis revealed that the LSTM model emerged as the top-performing model, boasting the lowest MSE value of 0.0054 for daily forecasts.

 Sanayileşmenin hızlanmasıyla birlikte artan enerji arz talebi artık konutlarda da kullanılan yeni nesil elektronik ekipmanlar nedeniyle her geçen gün artmaktadır. Enerjinin klasik yöntemlerle doğalgaz, sosil yakıtlar vb. üretilmesine alternatif olarak geliştirilen be yeşil enerji adı verilen yenilenebilir enerjinin kullanımının yaygınlaşmasıyla beraber bazı sorunlar ortaya çıkmaktadır. Elde edilen elektriğin sisteme entegre bir şekilde verilip takip edilebilmesi için veri izlemesi büyük önem arz etmektedir. Bu amaçla kurulan mikro ve makro ölçekteki akıllı şebekelerin dinamik röle haberleşmesi sayesinde büyük ölçeklerde enerji verileri elde edilmektedir. Nesnelerin interneti IoT çağında elde edilen bu verilerin işlenmesi ve analiz edilmesi için derin öğrenmek algoritmaları ve makine öğrenmesi yöntemleri kullanılmaktadır. Bu yöntemlerin sağlamış olduğu doğru analizler sayesinde akıllı şebekeler daha az kayıpla yüksek verimle çalışmaktadır. En küçük ölçekli bir kullanıcının enerji tüketim hesabı kestirimi optimize bir enerji yönetimi sağlamaktadır. Elektriğin doğru miktarda güçte akışı sağlandıktan sonra ortaya çıkabilecek israfın da önüne geçilebilmektedir. Makine ve derin öğrenme algoritmalarının hızlı ve gelişmiş tepkileri sayesinde hem kullanıcılar hem de üreticiler daha planlı ve sürdürülebilir bir enerji yönetimine sahip olmaktadırlar. Bu çalışmada konutlara ait 4 yıllık elektrik enerji verileri Convolutional Neural Network, Long Short-Term Memory, Random Forest ve K-Nearest Neighbors Regression gibi yöntemlerle analiz edilmiştir. Bu analizler neticesinde tüketilecek enerjinin tahmini yapılmıştır. Çalışmadaki öğrenme algoritmalarının etkinliğini değişen eğitim ve test veri oranlarına göre değerlendirmek için veri seti üç farklı bölme yöntemi kullanılarak bölümlendi: 90 eğitim - 10 test, 80 eğitim - 20 test ve 67 eğitim - 33 test bölümü. Ek olarak, daha ileri değerlendirme için 10 katlı çapraz doğrulama yaklaşımı kullanıldı. Karşılaştırmalı analiz, LSTM modelinin günlük tahminler için en düşük MSE değeri olan 0,0054 ile en iyi performans gösteren model olarak ortaya çıktığını ortaya çıkardı.

Article Details

Application of Contemporary Artificial Intelligence Algorithms in Real Energy Consumption Estimation in Residences

Authors:

Fatih Atalar | Ertuğrul Adıgüzel | Aysel Ersoy

Publisher:

Necmettin Erbakan University

Main Topics:

Elektrik Tesisleri

Journal:

Necmettin Erbakan Üniversitesi Fen ve Mühendislik Bilimleri Dergisi Vol.7 Issue 1, pp.31-47

Document Type:

Article

Publication Date:

4/2025

Document Language:

English

Document ID (Org No.):

2001338796

pISSN:

2667-7989

Smart systems

Deep learning

Machine learningAkıllı sistemler

Derin öğrenme

Makine öğrenmesi

Issues

Article Details

Application of Contemporary Artificial Intelligence Algorithms in Real Energy Consumption Estimation in Residences

Authors: Fatih Atalar | Ertuğrul Adıgüzel | Aysel Ersoy

Publisher: Necmettin Erbakan University

Main Topics: Elektrik Tesisleri

Journal: Necmettin Erbakan Üniversitesi Fen ve Mühendislik Bilimleri Dergisi Vol.7 Issue 1, pp.31-47

Document Type: Article

Publication Date: 4/2025

Document Language: English

Document ID (Org No.): 2001338796

pISSN: 2667-7989

Smart systems

Deep learning

Machine learningAkıllı sistemler

Derin öğrenme

Makine öğrenmesi

Issues

Authors:

Fatih Atalar | Ertuğrul Adıgüzel | Aysel Ersoy

Publisher:

Necmettin Erbakan University

Main Topics:

Elektrik Tesisleri

Journal:

Necmettin Erbakan Üniversitesi Fen ve Mühendislik Bilimleri Dergisi Vol.7 Issue 1, pp.31-47

Document Type:

Article

Publication Date:

4/2025

Document Language:

English

Document ID (Org No.):

2001338796

pISSN:

2667-7989