Derin öğrenme tabanlı konut yükü tanımlama modeli ve performans analizi

Yıl 2025, Cilt: 40 Sayı: 3 , 1637 - 1646 , 21.08.2025

Ardan Hüseyin Eşlik , Emre Akarslan , Rasim Doğan

https://doi.org/10.17341/gazimmfd.1473453

https://izlik.org/JA89EW29GF

Öz

Modern çağın hızla değişen enerji ihtiyaçlarına cevap vermek, evlerin enerji yönetimini daha da kritik hale getirmektedir. Akıllı ev teknolojilerinin yükselişiyle birlikte, konut yüklerinin etkili bir şekilde tanımlanması ve yönetilmesi giderek daha büyük bir önem kazanmaktadır. Bu çalışmada, konut yükü tanımlaması için CNN derin öğrenme tabanlı yeni bir yaklaşım önerilmiştir. Önerilen modelin etkinliği ve uygulanabilirliği, geleneksel makine öğrenimi yöntemleri olan Rastgele Orman, Karar Ağaçları ve K-En Yakın Komşu ile karşılaştırılarak değerlendirilmiştir. Afyon Kocatepe Üniversitesi laboratuvarlarında gerçekleştirilen deneysel verilerle desteklenen çalışma sonuçları, CNN derin öğrenme modelinin doğruluk, kesinlik, duyarlılık ve F-ölçütü gibi kritik metriklerde en üstün performansı sergilediğini ortaya koymuştur.

Anahtar Kelimeler

Konut Yükü Tanımlaması , Derin Öğrenme , Evrişimli Sinir Ağları , Zaman Serisi Sınıflandırması , Makine Öğrenmesi

Kaynakça

• 1. Ghosh S., Chatterjee A., Chatterjee D., An improved load feature extraction technique for smart homes using fuzzy-based NILM, IEEE Transactions on Instrumentation and Measurement, 70, 1-9, 2021.
• 2. Eşlik A.H., Sen O., Serttaş F., CNN-LSTM model for solar radiation prediction: performance analysis, Journal of the Faculty of Engineering and Architecture of Gazi University, 39 (4), 2155-2162, 2024.
• 3. Chojecki A., Rodak M., Ambroziak A., Borkowski P., Energy management system for residential buildings based on fuzzy logic: Design and implementation in smart-meter, IET Smart Grid, 3, 254-66, 2020.
• 4. Hart G.W., Nonintrusive appliance load monitoring, Proceedings of the IEEE, 80, 1870-91, 1992.
• 5. Eşlik A.H., Akarslan E., Doğan R., A novel approach for residential load identification based on dynamic time warping, Sustainable Energy, Grids and Networks, 101316, 2024.
• 6. Akarslan E., Doğan R., A novel approach based on a feature selection procedure for residential load identification, Sustainable Energy, Grids and Networks, 27, 100488, 2021.
• 7. Akarslan E., Doğan R., A novel approach for residential load appliance identification, Sustainable Cities and Society, 63, 102484, 2020.
• 8. Gürbüz F.B., Bayindir R., Seyfettin V., Elektrikli ev aletlerinde müdahalesiz yük izleme, sınıflandırma ve kontrolünün gerçekleştirilmesi, Gazi University Journal of Science Part C: Design and Technology, 11, 1209-22, 2023.
• 9. Heo S., Kim H., Toward load identification based on the Hilbert transform and sequence to sequence long short-term memory, IEEE Transactions on Smart Grid, 12, 3252-64, 2021.
• 10. Ghosh S., Chatterjee D., Non-intrusive identification of harmonic polluting loads in a smart residential system, Sustainable Energy, Grids and Networks, 26, 100446, 2021.
• 11. Kumar M., Gopinath R., Harikrishna P., Srinivas K., Non-intrusive load monitoring system for similar loads identification using feature mapping and deep learning techniques, Measurement Science and Technology, 32, 125902, 2021.
• 12. Han Y., Xu Y., Huo Y., Zhao Q., Non-intrusive load monitoring by voltage-current trajectory enabled asymmetric deep supervised hashing, IET Generation, Transmission & Distribution, 15, 3066-80, 2021.
• 13. Hu M., Tao S., Fan H., Li X., Sun Y., Sun J., Non-intrusive load monitoring for residential appliances with ultra-sparse sample and real-time computation, Sensors, 21, 5366, 2021.
• 14. Li Y., Wang H., Yang Z., Yang J., Chen Z., Stacking ensemble learning-based load identification considering feature fusion by cyber-physical approach, IEEE Sensors Journal, 23, 5997-6007, 2023.
• 15. Ghosh S., Panda D.K., Das S., Chatterjee D., Cross-correlation based classification of electrical appliances for non-intrusive load monitoring, 2021 International Conference on Sustainable Energy and Future Electric Transportation (SEFET): IEEE, 1-6, 2021.
• 16. Hosseini S.S., Delcroix B., Henao N., Agbossou K., Kelouwani S., Towards feasible solutions for load monitoring in Quebec residences, Sensors, 23, 7288, 2023.
• 17. Yin H., Zhou K., Yang S., Non-intrusive load monitoring by load trajectory and multi feature based on DCNN, IEEE Transactions on Industrial Informatics, 2023.
• 18. Moradzadeh A., Mohammadi-Ivatloo B., Abapour M., Anvari-Moghaddam A., Gholami Farkoush S., Rhee S.B., A practical solution based on convolutional neural network for non-intrusive load monitoring, Journal of Ambient Intelligence and Humanized Computing, 12, 9775-89, 2021.
• 19. Ding D., Li J., Zhang K., Wang H., Wang K., Cao T., Non-intrusive load monitoring method with inception structured CNN, Applied Intelligence, 1-18, 2022.
• 20. De Paiva Penha D., Castro A.R.G., Convolutional neural network applied to the identification of residential equipment in non-intrusive load monitoring systems, 3rd International Conference on Artificial Intelligence and Applications, 11-21, 2017.
• 21. Hubel D.H., Wiesel T.N., Receptive fields of single neurones in the cat's striate cortex, The Journal of Physiology, 148, 574, 1959.
• 22. Wen L., Li X., Gao L., Zhang Y., A new convolutional neural network-based data-driven fault diagnosis method, IEEE Transactions on Industrial Electronics, 65, 5990-8, 2017.
• 23. Rahimilarki R., Gao Z., Jin N., Zhang A., Convolutional neural network fault classification based on time-series analysis for benchmark wind turbine machine, Renewable Energy, 185, 916-31, 2022.
• 24. Karaali I., Eminağaoğlu M., A convolutional neural network model for marble quality classification, Journal of the Faculty of Engineering and Architecture of Gazi University, 36 (1), 347-358, 2021.
• 25. Bouktif S., Fiaz A., Ouni A., Serhani M.A., Optimal deep learning LSTM model for electric load forecasting using feature selection and genetic algorithm: Comparison with machine learning approaches, Energies, 11, 1636, 2018.
• 26. De Baets L., Ruyssinck J., Develder C., Dhaene T., Deschrijver D., Appliance classification using VI trajectories and convolutional neural networks, Energy and Buildings, 158, 32-6, 2018.
• 27. Liu H., Wu H., Yu C., A hybrid model for appliance classification based on time series features, Energy and Buildings, 196, 112-23, 2019.
• 28. Da Silva Nolasco L., Lazzaretti A.E., Mulinari B.M., DeepDFML-NILM: A new CNN-based architecture for detection, feature extraction and multi-label classification in NILM signals, IEEE Sensors Journal, 22, 501-9, 2021.
• 29. Azzam A., Sanami S., Aghdam A.G., Low-frequency load identification using CNN-BiLSTM attention mechanism, 2024 32nd Mediterranean Conference on Control and Automation (MED): IEEE, 712-7, 2024.