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

Yıl 2025, Cilt: 7 Sayı: 1, 31 - 47

Fatih Atalar , Ertuğrul Adıgüzel , Aysel Ersoy

Öz

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.

Anahtar Kelimeler

Smart systems, Deep learning, Machine learning

Etik Beyan

This article is derived from the master’s thesis entitled “Comparison of deep learning and machine learning methods for estimating energy consumption in houses” that was completed under the supervision of Prof. Dr. Aysel ERSOY (Master’s Thesis, Istanbul University-Cerrahpaşa, Istanbul, Türkiye, 2020). The data and insights presented herein are based on the findings of the aforementioned thesis, with permission from the author. This work aims to build upon and expand the research conducted in the original thesis, contributing to the ongoing discourse in the field.

Teşekkür

The authors extend their heartfelt gratitude to Erol YAVUZ for his invaluable technical support, which significantly contributed to the efficient and expeditious execution of simultaneous analyses in the software employed during the application of artificial intelligence methods. His expertise and assistance were instrumental in the successful completion of this research endeavor.

Konutlarda Reel Enerji Tüketimi Kestiriminde Güncel Yapay Zeka Algoritmalarının Uygulanması

Öz

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

Anahtar Kelimeler

Akıllı sistemler, Derin öğrenme, Makine öğrenmesi

Kaynakça

• S. Fathi, R. Srinivasan, A. Fenner, S. Fathi, Machine learning applications in urban building energy performance forecasting: A systematic review, Renewable and Sustainable Energy Reviews. 133 (2020), 110287. doi:10.1016/J.RSER.2020.110287
• S. Yang, M.P. Wan, W. Chen, B.F. Ng, S. Dubey, Model predictive control with adaptive machine-learning-based model for building energy efficiency and comfort optimization, Applied Energy. 271 (2020), 115147. doi:10.1016/J.APENERGY.2020.115147
• N.T. Mbungu, R.M. Naidoo, R.C. Bansal, M.W. Siti, D.H. Tungadio, An overview of renewable energy resources and grid integration for commercial building applications, Journal of Energy Storage. 29 (2020), 101385. doi:10.1016/J.EST.2020.101385
• A. Rejeb, K. Rejeb, S. Simske, H. Treiblmaier, S. Zailani, The big picture on the internet of things and the smart city: a review of what we know and what we need to know, Internet of Things (Netherlands). 19 (2022), 100565. doi:10.1016/J.IOT.2022.100565
• A.H. Al-Badi, R. Ahshan, N. Hosseinzadeh, R. Ghorbani, E. Hossain, Survey of smart grid concepts and technological demonstrations worldwide emphasizing on the Oman perspective, Applied System Innovation. 3 (2020) 1–27. doi:10.3390/ASI3010005
• M. Hacıbeyoglu, M. Çelik, Ö. Erdaş Çiçek, Energy Efficiency Estimation in Buildings with K Nearest Neighbor Algorithm, Necmettin Erbakan University Journal of Science and Engineering. 5(2) (2023), 65–74. doi:10.47112/neufmbd.2023.10
• Y. Liu, H. Chen, L. Zhang, X. Wu, X. jia Wang, Energy consumption prediction and diagnosis of public buildings based on support vector machine learning: A case study in China, Journal of Cleaner Production. 272 (2020), 122542. doi:10.1016/J.JCLEPRO.2020.122542
• E. Mocanu, P.H. Nguyen, M. Gibescu, W.L. Kling, Deep learning for estimating building energy consumption, Sustainable Energy, Grids and Networks. 6 (2016), 91–99. doi:10.1016/J.SEGAN.2016.02.005
• T.Y. Kim, S.B. Cho, Predicting residential energy consumption using CNN-LSTM neural networks, Energy. 182 (2019), 72–81. doi:10.1016/J.ENERGY.2019.05.230
• H. Georges and B. Alice. Individual household electric power consumption, UCI Machine Learning Repository. 2012. https://doi.org/10.24432/C58K54
• X.M. Zhang, K. Grolinger, M.A.M. Capretz, L. Seewald, Forecasting Residential Energy Consumption: Single Household Perspective, içinde: Proceedings - 17th IEEE International Conference on Machine Learning and Applications, ICMLA 2018, 2018: ss. 110–117. doi:10.1109/ICMLA.2018.00024
• Y. Kocadayi, O. Erkaymaz, R. Uzun, Estimation of Tr81 area yearly electric energy consumption by artificial neural networks, Bilge International Journal of Science and Technology Research. 1 (2017), 59–64.
• D. Yılmaz, A.M. Tanyer, I.D. Toker, A data-driven energy performance gap prediction model using machine learning, Renewable and Sustainable Energy Reviews. 181 (2023), 113318. doi:10.1016/J.RSER.2023.113318
• F.E. Sapnken, M.M. Hamed, B. Soldo, J. Gaston Tamba, Modeling energy-efficient building loads using machine-learning algorithms for the design phase, Energy and Buildings. 283 (2023), 112807. doi:10.1016/J.ENBUILD.2023.112807
• P. Balakumar, T. Vinopraba, K. Chandrasekaran, Deep learning based real time Demand Side Management controller for smart building integrated with renewable energy and Energy Storage System, Journal of Energy Storage. 58 (2023), 106412. doi:10.1016/J.EST.2022.106412
• B. Peker, F. A. Çuha, ve H. A. Peker, Analytical solution of Newton’s law of cooling equation via kashuri fundo transform, Necmettin Erbakan University Journal of Science and Engineering. 6(1) (2024), 10–20. doi:10.47112/neufmbd.2024.29
• B. Akgayev, S. Akbayrak, M. Yılmaz, M. S. Büker, ve V. Unsur, Assessing the feasibility of photovoltaic systems in Türkiye: Technical and economic analysis of on-grid, off-grid, and utility-scale PV installations, Necmettin Erbakan University Journal of Science and Engineering. 6(1) (2024), 69–92. doi: 10.47112/neufmbd.2024.33
• N. Kulaksız, M. Hançer, Flight tests for aircraft in simulink-flightgear environments and comparison of aerodynamic effects on stability/frame axes, Asrel Aerospace Research Letters. 1 (2022), 69–83. doi:10.56753/ASREL.2022.2.1
• J.C. Kim, S.M. Cho, H.S. Shin, Advanced power distribution system configuration for smart grid, IEEE Transactions on Smart Grid. 4 (2013), 353–358. doi:10.1109/TSG.2012.2233771
• O. Majeed Butt, M. Zulqarnain, T. Majeed Butt, Recent advancement in smart grid technology: Future prospects in the electrical power network, Ain Shams Engineering Journal. 12 (2021), 687–695. doi:10.1016/J.ASEJ.2020.05.004
• C. Crozier, T. Morstyn, M. McCulloch, The opportunity for smart charging to mitigate the impact of electric vehicles on transmission and distribution systems, Applied Energy. 268 (2020), 114973. doi:10.1016/J.APENERGY.2020.114973
• M. Karakoyun, A. Özkış, Development of binary moth-flame optimization algorithms using transfer functions and their performance comparison, Necmettin Erbakan University Journal of Science and Engineering. 3(2) (2021), 1-10.
• T. Ahmad, R. Madonski, D. Zhang, C. Huang, A. Mujeeb, Data-driven probabilistic machine learning in sustainable smart energy/smart energy systems: Key developments, challenges, and future research opportunities in the context of smart grid paradigm, Renewable and Sustainable Energy Reviews. 160 (2022), 112128. doi:10.1016/J.RSER.2022.112128
• R.I.D. Harris, Testing for unit roots using the augmented Dickey-Fuller test: Some issues relating to the size, power and the lag structure of the test, Economics Letters. 38 (1992), 381–386. doi:10.1016/0165-1765(92)90022-Q
• Y.H. Bhosale, K.S. Patnaik, Bio-medical imaging (X-ray, CT, ultrasound, ECG), genome sequences applications of deep neural network and machine learning in diagnosis, detection, classification, and segmentation of COVID-19: a Meta-analysis & systematic review, Multimedia Tools and Applications. 82 (2023), 39157–39210. doi:10.1007/S11042-023-15029-1
• M.M. Islam, F. Karray, R. Alhajj, J. Zeng, A Review on deep learning techniques for the diagnosis of novel coronavirus (COVID-19), IEEE Access. 9 (2021), 30551–30572. doi:10.1109/ACCESS.2021.3058537
• P. Manikandan, U. Durga, C. Ponnuraja, An integrative machine learning framework for classifying SEER breast cancer, Scientific Reports. 13 (2023), 1–12. doi:10.1038/s41598-023-32029-1
• R. Anand, S.V. Lakshmi, D. Pandey, B.K. Pandey, An enhanced ResNet-50 deep learning model for arrhythmia detection using electrocardiogram biomedical indicators, Evolving Systems. 15 (2024), 83–97. doi:10.1007/S12530-023-09559-0/TABLES/7
• A. Uddin, M. Islam, A. Talukder, A.A. Hossain, A. Akhter, S. Aryal, M. Muntaha, Machine learning based diabetes Detection Model for false negative reduction, Biomedical Materials & Devices. 2 (2023), 427–443. doi:10.1007/s44174-023-00104-w
• R. Olu-Ajayi, H. Alaka, I. Sulaimon, F. Sunmola, S. Ajayi, Building energy consumption prediction for residential buildings using deep learning and other machine learning techniques, Journal of Building Engineering. 45 (2022), 103406. doi:10.1016/J.JOBE.2021.103406
• H. Ma, L. Xu, Z. Javaheri, N. Moghadamnejad, M. Abedi, Reducing the consumption of household systems using hybrid deep learning techniques, Sustainable Computing: Informatics and Systems. 38 (2023), 100874. doi:10.1016/J.SUSCOM.2023.100874
• M. Schonlau, R.Y. Zou, The random forest algorithm for statistical learning, Stata Journal. 20 (2020), 3–29. doi:10.1177/1536867X20909688
• O. Kramer, K-Nearest Neighbors. In: Dimensionality Reduction with Unsupervised Nearest Neighbors. Intelligent Systems Reference Library, vol 51. (2013). Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-38652-7_2
• K. Fukushima, Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position, Biological Cybernetics. 36 (1980), 193–202. doi:10.1007/BF00344251/METRICS
• X. Wang, Y. Zhao, F. Pourpanah, Recent advances in deep learning, International Journal of Machine Learning and Cybernetics. 11 (2020), 747–750. doi:10.1007/S13042-020-01096-5/METRICS
• A. Sherstinsky, Fundamentals of recurrent neural network (RNN) and long short-term memory (LSTM) network, Physica D: Nonlinear Phenomena. 404 (2020), 132306. doi:10.1016/J.PHYSD.2019.132306
• R.C. Staudemeyer, E.R. Morris, Understanding LSTM -- a tutorial into long short-term memory recurrent neural networks, Neural and Evolutionary Computing. (2019). https://arxiv.org/abs/1909.09586v1
• E. Yavuz, Comparison Of Deep Learning And Machine Learning Methods For Estimating Energy Consumption In Houses, M.Sc. Thesis, Istanbul University-Cerrahpaşa Institute of Graduate Studies Department of Electrical and Electronic Engineering, Istanbul, 2020.
• J.Q. Wang, Y. Du, J. Wang, LSTM based long-term energy consumption prediction with periodicity, Energy. 197 (2020), 117197. doi:10.1016/J.ENERGY.2020.117197
• S. Alaloul, B.A. Tayeh, M.A. Musarat, D. Durand, J. Aguilar, M.D. R-Moreno, An analysis of the energy consumption forecasting problem in smart buildings using LSTM, Sustainability. 14 (2022), 13358. doi:10.3390/SU142013358
• R. Olu-Ajayi, H. Alaka, I. Sulaimon, F. Sunmola, S. Ajayi, Building energy consumption prediction for residential buildings using deep learning and other machine learning techniques, Journal of Building Engineering. 45 (2022), 103406. doi:10.1016/J.JOBE.2021.103406