Araştırma Makalesi
BibTex RIS Kaynak Göster

ELEKTRİK ÜRETİMİNİN PLANLANMASI İÇİN DERİN ÖĞRENME TABANLI TALEP TAHMİN SİSTEMİ

Yıl 2024, , 511 - 522, 03.06.2024
https://doi.org/10.17780/ksujes.1399160

Öz

Ekonomik ve endüstriyel gelişimin devam ettiği günümüz dünyasında elektrik enerjisinin önemi sürekli artmaktadır. Sistemdeki kayıp enerji maliyetlerini azaltmak, üretim harcamalarını uygun şekilde planlamak, piyasa oyuncularının ekonomik olarak zarar görmemesini sağlamak ve sistem tüketicilerine kaliteli ve kesintisiz enerji ulaştırmak için enerji talebinin mümkün olduğunca hassas bir şekilde tahmin edilmesi gerekmektedir. Sistemin elektrik enerjisi arz ve talebinin dengelenmesi bir tahmin planı ile mümkündür. Araştırmamız, Türkiye Elektrik Tüketim Verileri ve meteorolojik veriler kullanılarak, zaman ve resmi tatil özellikleri de eklenerek 2018-2021 dönemi için saatlik elektrik tüketim yük tahminleri üretmeyi amaçlamaktadır. Modellerin tahmin performansı, çoklu makine öğrenimi modelleri ve derin sinir ağı tabanlı zaman serisi modelleri verilerle eğitilerek değerlendirilmektedir. Yük talep tahmin problemimizinin tahmin sonuçları değerlendirildiğinde derin öğrenme yöntemlerinin makine öğrenmesi modellerine kıyasla tahmin başarısında daha yüksek sonuçlar verdiği görülmüştür. Kullandığımız derin öğrenme yöntemlerinden LSTM modelinin tahmin başarısının RNN ve GRU modellerinden daha yüksek olduğu gözlemlenmiştir. Analiz, enerji arzı ve talebi arasındaki uyumsuzlukların giderilmesini öngörmektedir.

Kaynakça

  • Aguilar Madrid, E. & Antonio, N.(2021). Short-term electricity load forecasting with machine learning. Information, 12(2), 50. https://doi.org/10.3390/info12020050.
  • Amjady, N. (2001). Short-term hourly load forecasting using time-series modeling with peak load estimation capability. IEEE Transactions on power systems, 16(3), 498-505. https://doi.org/10.1109/59.932287.
  • Aydogan, M. (2019). Performing Text Analysis Using Deep Learning Algorithms in Big Data. Doctoral Thesis. Inonu University Institute of Science and Technology, Malatya.
  • Banik, R., Das, P., Ray, S. & Biswas, A. (2021). Prediction of electrical energy consumption based on machine learning technique. Electrical Engineering, 103(2) , 909-920. https://doi.org/10.1007/s00202-020-01126-z.
  • Biskin, O.T. & Çifci, A. (2021). Forecasting of Turkey’s Electrical Energy Consumption using LSTM and GRU Networks. Bilecik Şeyh Edebali University Journal of Science and Technology, 8(2), 656-667. https://doi.org/10.35193/bseufbd.935824.
  • Chan, S., Oktavianti, I. & Puspita, V. (2019). A deep learning cnn and ai-tuned svm for electricity consumption forecasting: Multivariate time series data. In 2019 IEEE 10th Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON) 0488-0494. IEEE. https://doi.org/10.1109/IEMCON.2019.8936260.
  • Cunkas, M. & Altun, A.A. (2010). Long term electricity demand forecasting in Turkey using artificial neural networks. Energy Sources, Part B: Economics, Planning, and Policy, 5(3) , 279-289. https://doi.org/10.1080/15567240802533542.
  • Chung, J., Gulcehre, C., Cho, K. & Bengio, Y. (2014). Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv preprint arXiv:1412.3555.
  • Durgun, S. (2018). Long-term forecasting of Turkey's energy demand with artificial intelligence techniques, Master's Thesis. Necmettin Erbakan University Institute of Science and Technology, Konya.
  • Elmas, C. (2018). Artificial intelligence applications. Seçkin Publishing.
  • EXIST, Real Time Consumption Data. (2022). https://seffaflik.epias.com.tr/electricity/electricity-consumption/ex-post-consumption/real-time-consumption
  • Gokce, M.M. & Duman, E. (2022). Performance Comparison of Simple Regression, Random Forest and XGBoost Algorithms for Forecasting Electricity Demand. In 2022 3rd International Informatics and Software Engineering Conference (IISEC) 1-6. IEEE. https://doi.org/10.1109/IISEC56263.2022.9998213
  • Hong, T. (2010). Short term electric load forecasting. North Carolina State University. Kim, Y., Son, H.G., & Kim, S. (2019). Short term electricity load forecasting for institutional buildings. Energy Reports, 5, 1270–1280. https://doi.org/10.1016/j.egyr.2019.08.086.
  • Kumar, S., Hussain, L., Banarjee, S. & Reza, M. (2018). Energy load forecasting using deep learning approach-LSTM and GRU in spark cluster. In 2018 fifth international conference on emerging applications of information technology (EAIT) 1-4. IEEE. https://doi.org/10.1109/EAIT.2018.8470406.
  • Li, J. (2017). Assessing the accuracy of predictive models for numerical data: Not r nor r2, why not? Then what?. PloS one, 12(8), e0183250. https://doi.org/10.1371/journal.pone.0183250.
  • Lin, Z., Cheng, L. & Huang, G. (2020). Electricity consumption prediction based on LSTM with attention mechanism. IEEJ Transactions on Electrical and Electronic Engineering, 15(4), 556-562. https://doi.org/10.1002/tee.23088
  • NASA, Power Data Access Viewer. (2022). https://power.larc.nasa.gov/data-access-viewer/.
  • Nisanci, M. (2005). Electricity demand and the relationship between electricity consumption and economic growth in Turkey. Journal of Social Economic Research, 5(9), 107-121.
  • Pervan, N., Keles, Y. (2019). Making semantic inference from Turkish texts using deep learning approaches. Doctoral Thesis. Ankara University Institute of Science and Technology, Ankara.
  • Singh, A.K., Khatoon, S., Muazzam, M. & Chaturvedi, D.K. (2012) Load forecasting techniques and methodologies: A review. In 2012 2nd International Conference on Power, Control and Embedded Systems, 1-10. IEEE. https://doi.org/10.1109/ICPCES.2012.6508132.
  • Tan, M., Santos, C.D., Xiang, B. & Zhou, B. (2015). Lstm-based deep learning models for non-factoid answer selection. arXiv preprint arXiv:1511.04108.
  • Yan,K., Wang, X., Du, Y., Jin, N., Huang, H. & Zhou, H. (2018). Multi-step short-term power consumption forecasting with a hybrid deep learning strategy. Energies, 11(11), 3089. https://doi.org/10.3390/en11113089.
  • Yildiz, B., Bilbao, J.I. & Sproul, A.B. (2017). A review and analysis of regression and machine learning models on commercial building electricity load forecasting. Renewable and Sustainable Energy Reviews, 73, 1104-1122. https://doi.org/10.1016/j.rser.2017.02.023.
  • Zheng, J., Xu, C., Zhang, Z. & Li, X. (2017). Electric load forecasting in smart grids using long-short-term-memory based recurrent neural network. In 2017 51st Annual conference on information sciences and systems (CISS) 1-6. IEEE.

A DEEP LEARNING-BASED DEMAND FORECASTING SYSTEM FOR PLANNING ELECTRICITY GENERATION

Yıl 2024, , 511 - 522, 03.06.2024
https://doi.org/10.17780/ksujes.1399160

Öz

In today's world, where economic and industrial development continues, the importance of electrical energy is constantly increasing. Energy demand should be forecast as precisely as possible to reduce lost energy costs in the system, to plan generation expenditures appropriately, to ensure that market players are not economically harmed, and to deliver quality and uninterrupted energy to system consumers. Balancing the electric energy supply and demand of the system is possible with a forecasting plan. Our research aims to generate hourly electricity consumption load forecasts for the period 2018-2021 using Turkish Electricity Consumption Data and meteorological data, with the addition of time and public holiday features. The forecasting performance of the models is evaluated by training multiple machine learning models and deep neural network-based time series models with the data. When the prediction results of our load demand forecasting problem were evaluated, it was seen that deep learning methods gave higher results in prediction success compared to machine learning models. It has been observed that the prediction success of the LSTM model, one of the deep learning methods we use, is higher than the RNN and GRU models. The analysis envisages the elimination of mismatches between energy supply and demand.

Kaynakça

  • Aguilar Madrid, E. & Antonio, N.(2021). Short-term electricity load forecasting with machine learning. Information, 12(2), 50. https://doi.org/10.3390/info12020050.
  • Amjady, N. (2001). Short-term hourly load forecasting using time-series modeling with peak load estimation capability. IEEE Transactions on power systems, 16(3), 498-505. https://doi.org/10.1109/59.932287.
  • Aydogan, M. (2019). Performing Text Analysis Using Deep Learning Algorithms in Big Data. Doctoral Thesis. Inonu University Institute of Science and Technology, Malatya.
  • Banik, R., Das, P., Ray, S. & Biswas, A. (2021). Prediction of electrical energy consumption based on machine learning technique. Electrical Engineering, 103(2) , 909-920. https://doi.org/10.1007/s00202-020-01126-z.
  • Biskin, O.T. & Çifci, A. (2021). Forecasting of Turkey’s Electrical Energy Consumption using LSTM and GRU Networks. Bilecik Şeyh Edebali University Journal of Science and Technology, 8(2), 656-667. https://doi.org/10.35193/bseufbd.935824.
  • Chan, S., Oktavianti, I. & Puspita, V. (2019). A deep learning cnn and ai-tuned svm for electricity consumption forecasting: Multivariate time series data. In 2019 IEEE 10th Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON) 0488-0494. IEEE. https://doi.org/10.1109/IEMCON.2019.8936260.
  • Cunkas, M. & Altun, A.A. (2010). Long term electricity demand forecasting in Turkey using artificial neural networks. Energy Sources, Part B: Economics, Planning, and Policy, 5(3) , 279-289. https://doi.org/10.1080/15567240802533542.
  • Chung, J., Gulcehre, C., Cho, K. & Bengio, Y. (2014). Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv preprint arXiv:1412.3555.
  • Durgun, S. (2018). Long-term forecasting of Turkey's energy demand with artificial intelligence techniques, Master's Thesis. Necmettin Erbakan University Institute of Science and Technology, Konya.
  • Elmas, C. (2018). Artificial intelligence applications. Seçkin Publishing.
  • EXIST, Real Time Consumption Data. (2022). https://seffaflik.epias.com.tr/electricity/electricity-consumption/ex-post-consumption/real-time-consumption
  • Gokce, M.M. & Duman, E. (2022). Performance Comparison of Simple Regression, Random Forest and XGBoost Algorithms for Forecasting Electricity Demand. In 2022 3rd International Informatics and Software Engineering Conference (IISEC) 1-6. IEEE. https://doi.org/10.1109/IISEC56263.2022.9998213
  • Hong, T. (2010). Short term electric load forecasting. North Carolina State University. Kim, Y., Son, H.G., & Kim, S. (2019). Short term electricity load forecasting for institutional buildings. Energy Reports, 5, 1270–1280. https://doi.org/10.1016/j.egyr.2019.08.086.
  • Kumar, S., Hussain, L., Banarjee, S. & Reza, M. (2018). Energy load forecasting using deep learning approach-LSTM and GRU in spark cluster. In 2018 fifth international conference on emerging applications of information technology (EAIT) 1-4. IEEE. https://doi.org/10.1109/EAIT.2018.8470406.
  • Li, J. (2017). Assessing the accuracy of predictive models for numerical data: Not r nor r2, why not? Then what?. PloS one, 12(8), e0183250. https://doi.org/10.1371/journal.pone.0183250.
  • Lin, Z., Cheng, L. & Huang, G. (2020). Electricity consumption prediction based on LSTM with attention mechanism. IEEJ Transactions on Electrical and Electronic Engineering, 15(4), 556-562. https://doi.org/10.1002/tee.23088
  • NASA, Power Data Access Viewer. (2022). https://power.larc.nasa.gov/data-access-viewer/.
  • Nisanci, M. (2005). Electricity demand and the relationship between electricity consumption and economic growth in Turkey. Journal of Social Economic Research, 5(9), 107-121.
  • Pervan, N., Keles, Y. (2019). Making semantic inference from Turkish texts using deep learning approaches. Doctoral Thesis. Ankara University Institute of Science and Technology, Ankara.
  • Singh, A.K., Khatoon, S., Muazzam, M. & Chaturvedi, D.K. (2012) Load forecasting techniques and methodologies: A review. In 2012 2nd International Conference on Power, Control and Embedded Systems, 1-10. IEEE. https://doi.org/10.1109/ICPCES.2012.6508132.
  • Tan, M., Santos, C.D., Xiang, B. & Zhou, B. (2015). Lstm-based deep learning models for non-factoid answer selection. arXiv preprint arXiv:1511.04108.
  • Yan,K., Wang, X., Du, Y., Jin, N., Huang, H. & Zhou, H. (2018). Multi-step short-term power consumption forecasting with a hybrid deep learning strategy. Energies, 11(11), 3089. https://doi.org/10.3390/en11113089.
  • Yildiz, B., Bilbao, J.I. & Sproul, A.B. (2017). A review and analysis of regression and machine learning models on commercial building electricity load forecasting. Renewable and Sustainable Energy Reviews, 73, 1104-1122. https://doi.org/10.1016/j.rser.2017.02.023.
  • Zheng, J., Xu, C., Zhang, Z. & Li, X. (2017). Electric load forecasting in smart grids using long-short-term-memory based recurrent neural network. In 2017 51st Annual conference on information sciences and systems (CISS) 1-6. IEEE.
Toplam 24 adet kaynakça vardır.

Ayrıntılar

Birincil Dil İngilizce
Konular Derin Öğrenme
Bölüm Elektrik Elektronik Mühendisliği
Yazarlar

Muhammet Mustafa Gökçe 0000-0003-1214-1698

Erkan Duman 0000-0003-2439-7244

Yayımlanma Tarihi 3 Haziran 2024
Gönderilme Tarihi 1 Aralık 2023
Kabul Tarihi 26 Mart 2024
Yayımlandığı Sayı Yıl 2024

Kaynak Göster

APA Gökçe, M. M., & Duman, E. (2024). A DEEP LEARNING-BASED DEMAND FORECASTING SYSTEM FOR PLANNING ELECTRICITY GENERATION. Kahramanmaraş Sütçü İmam Üniversitesi Mühendislik Bilimleri Dergisi, 27(2), 511-522. https://doi.org/10.17780/ksujes.1399160