Renewable electric energy estimation by hyperparameter optimization using hybrid deep learning method

Yıl 2023, , 770 - 777, 15.07.2023

Kübra Kaysal , Ahmet Haşim Yurttakal , Fatih Onur Hocaoğlu

https://doi.org/10.28948/ngumuh.1263782

Öz

The unregulated and unconscious use of energy sources causes environmental damage. On the other hand the increasing population density, development of industry and technology increase the demand for electrical energy day by day. For this purpose, investments in the energy sector are directed towards renewable energy sources such as wind energy in order to ensure both environment-friendly and supply-demand balance. The amount of energy obtained from wind energy varies depending on regional differences such as wind direction and speed. In this study, a method is proposed to achieve better results in predicting electricity generation from wind energy by capturing the non-linear and non-stationary nature of wind energy using a hybrid approach of deep learning methods, specifically CNN and BLSTM architectures. In the forecasting model, 26280 real-time data measured at hourly frequency are used. In addition, the hyperparameter values used in the model were optimized using the Grid Search algorithm in order to increase the prediction success. The success of the proposed hybrid model is compared with the BLSTM model. As a result, the R2 value, which indicates the success rate of the proposed CNN-BLSTM model, was calculated as 0.984.

Anahtar Kelimeler

Renewable electric energy, Deep learning, Hyperparameter optimization

Hibrit derin öğrenme yöntemi kullanılarak hiperparametre optimizasyonu ile yenilenebilir elektrik enerjisi tahmini

Öz

Enerji kaynaklarının düzensiz ve bilinçsiz kullanımı çevresel tahribatlara sebep olurken, artan nüfus yoğunluğu, sanayi ve teknolojinin gelişmesi de her geçen gün elektrik enerjisi talebini artırmaktadır. Bu amaçla enerji sektörü, yatırımlarını hem çevre dostu hem de arz-talep dengesini sağlamak adına rüzgâr enerjisi gibi yenilenebilir enerji kaynaklarına yöneltmektedir. Rüzgâr enerjisinden elde edilen enerji miktarı rüzgârın yönü ve hızı gibi bölgesel farklılıklara bağlı olarak değişkenlik göstermektedir. Bu çalışmada, rüzgâr enerjisinden elektrik üretimi tahmininde daha iyi sonuçlar elde etmek amacıyla rüzgâr enerjisinin doğrusal ve durağan olmayan yapısını yakalamak için derin öğrenme metotlarından CNN ve BLSTM mimarilerinin hibrit bir şekilde kullanıldığı bir yöntem önerilmektedir. Tahmin modelinde, saatlik frekansta ölçülmüş 26280 adet gerçek zamanlı veri kullanılmıştır. Ayrıca tahmin başarısını artırmak adına modelde kullanılan hiperparametre değerleri Grid Search arama algoritması kullanılarak optimize edilmiştir. Önerilen hibrit modelin başarısı BLSTM modeli ile kıyaslanmıştır. Sonuç olarak önerilen CNN-BLSTM modelinin başarım oranını gösteren R2 değeri 0.984 olarak hesaplanmıştır.

Anahtar Kelimeler

Yenilenebilir elektrik enerjisi, Derin öğrenme, Hiperparametre optimizasyonu

Kaynakça

• M. Ali, M. Adnan, M.Tariq, Optimum control strategies for short term load forecasting in smart grids. International Journal of Electrical Power & Energy Systems ,113, 792-806, 2019. https://doi.org/10.10 16/j.ijepes.2019.06.010.
• C. Wang, T. Bäck, H. H. Hoos, M. Baratchi, S. Limmer, and M. Olhofer, Automated machine learning for short-term electric load forecasting. In 2019 IEEE Symposium Series on Computational Intelligence SSCI, pp. 314-321, Xiamen, China, December 2019.
• S. Bouktif, A. Fiaz, A. Ouni, M. A. Serhani, Optimal deep learning lstm model for electric load forecasting using feature selection and genetic algorithm: Comparison with machine learning approaches. Energies, 11(7), 1636, 2018. https://doi.org/10.339 0/en11071636.
• J. Wu, X. Y. Chen, H. Zhang, L. D. Xiong, H. Lei, S. H. Deng, Hyperparameter optimization for machine learning models based on Bayesian optimization. Journal of Electronic Science and Technology, 17(1), 26-40, 2019. https://doi.org/10.11989/JEST.1674-862 X.80904120.
• Y. Wang, S. Sun, X. Chen, X. Zeng, Y. Kong, J. Chen, T. Wang, Short-term load forecasting of industrial customers based on SVMD and XGBoost. International Journal of Electrical Power & Energy Systems, 129, 106830, 2021. https://doi.org/10.1016/j.ijepes.2021.10 6830.
• K. Liu, J. Cheng, J. Yi, Copper price forecasted by hybrid neural network with Bayesian Optimization and wavelet transform. Resources Policy, 75, 102520,2022. https://doi.org/10.1016/j.resourpol.2021.102520.
• D. M. Belete and M. D. Huchaiah, Grid search in hyperparameter optimization of machine learning models for prediction of HIV/AIDS test results. International Journal of Computers and Applications, 44(9), 875-886, 2022. https://doi.org/10 .1080/1206212X.2021.1974663.
• H. Alibrahim and S. A. Ludwig, Hyperparameter optimization: Comparing genetic algorithm against grid search and bayesian optimization. In 2021 IEEE Congress on Evolutionary Computation, pp. 1551-1559, Kraków, Poland, June 2021.
• B. Z. Aufa, S. Suyanto and A. Arifianto, Hyperparameter setting of LSTM-based language model using grey wolf optimizer. In 2020 International Conference on Data Science and Its Applications, pp. 1-5, Bandung, Indonesia, August, 2020.
• A. Zainab, A. Ghrayeb, M. Houchati, S. S. Refaat and H. Abu-Rub, Performance evaluation of tree-based models for big data load forecasting using randomized hyperparameter tuning. In 2020 IEEE International Conference on Big Data, pp. 5332-5339, Atlanta, GA, USA, December, 2020.
• S. Gao, Y. Huang, S. Zhang, J. Han, G. Wang, M. Zhang, Q. Lin, Short-term runoff prediction with GRU and LSTM networks without requiring time step optimization during sample generation. Journal of Hydrology, 589, 125188, 2020. https://doi.org/10.101 6/j.jhydrol.2020.125188.
• S. M. J. Jalali, S. Ahmadian, A. Khosravi, M. Shafie-khah, S. Nahavandi, J. P. Catalão, A novel evolutionary-based deep convolutional neural network model for intelligent load forecasting. IEEE Transactions on Industrial Informatics, 17(12), 8243-8253, 2021. https://doi.org/10.1109/TII.2021.3065718.
• G. Trierweiler Ribeiro, J. Guilherme Sauer, N. Fraccanabbia, V. Cocco Mariani, L. dos Santos Coelho, Bayesian optimized echo state network applied to short-term load forecasting. Energies, 13(9), 2390, 2020. https://doi.org/10.3390/en13092390.
• F. Kosanoğlu, Z. N. Kiriş ve Ö. F. Beyca, Tekrarlayan Sinir Ağları Temelli Rüzgâr Hızı Tahmin Modelleri: Yalova Bölgesinde Bir Uygulama. Journal of Intelligent Systems: Theory and Applications, 5(2), 178-188, 2022. https://doi.org/10.38016/jista.1120383.
• A. Gülcü ve Z. Kuş, A Survey of Hyper-parameter Optimization Methods in Convolutional Neural Networks. Gazi Üniversitesi Fen Bilimleri Dergisi, 7(2), 503-522, 2019. https://doi.org/10.29109/gujsc.51 4483.
• P. Görgel ve E. Kavlak, Uzun kısa süreli hafıza ve evrişimsel sinir ağları ile rüzgar enerjisi üretim tahmini. Dicle Üniversitesi Mühendislik Fakültesi Mühendislik Dergisi, 11(1), 69-80, 2020. https://doi.org/10.24012/ dumf.596533.
• Y. Yu, X. Si, C. Hu, J. Zhang, A review of recurrent neural networks: LSTM cells and network architectures. Neural Computation, 31(7), 1235-1270, 2019. https://doi.org/10.1162/neco_a_01199.
• V. Pattana-Anake and F. J. J. Joseph, Hyper Parameter Optimization of Stack LSTM Based Regression for PM 2.5 Data in Bangkok. In 2022 7th International Conference on Business and Industrial Research, pp. 13-17, Bangkok, Thailand, May 2022.
• L. Latifoğlu, Derin sinir ağları modeli ile standardize yağış indeksi tahmini. Niğde Ömer Halisdemir Üniversitesi Mühendislik Bilimleri Dergisi, 1-1, 11(4), 1006-1024, 2022. https://doi.org/10.28948/ngumuh.11 45279.
• H. Çetiner, Recurrent Neural Network Based Model Development for Energy Consumption Forecasting. Bitlis Eren Üniversitesi Fen Bilimleri Dergisi, 11(3), 759-769, 2022. https://doi.org/10.17798 /bitlisfen.1077 393.
• Y. Imrana, Y. Xiang, L. Ali, Z. Abdul-Rauf, A bidirectional LSTM deep learning approach for intrusion detection. Expert Systems with Applications, 185, 115524, 2021. https://doi.org/10.1016/j.eswa.202 1.115524.
• G. Zhang, F. Tan, Y. Wu, Ship motion attitude prediction based on an adaptive dynamic particle swarm optimization algorithm and bidirectional LSTM neural network. IEEE Access, 8, 90087-90098, 2020. https://doi.org/10.1088/1755-1315/440/3/032115.
• M. N. Akhter, S. Mekhilef, H. Mokhlis, Z. M. Almohaimeed, M. A. Muhammad, A. S. M. Khairuddin, M. M. Hussain, An hour-ahead PV power forecasting method based on an RNN-LSTM model for three different PV plants. Energies, 15(6), 2243, 2022. https://doi.org/10.3390/en15062243.
• S. M. Malakouti, A. R. Ghiasi, A. A. Ghavifekr, P. Emami, Predicting wind power generation using machine learning and CNN-LSTM approaches. Wind Engineering, 46(6), 1853-1869, 2022. https://doi.org /10.1177/0309524X221113013
• F. Saeed, A. Paul, H. Seo, A Hybrid Channel-Communication-Enabled CNN-LSTM Model for Electricity Load Forecasting. Energies, 15(6), 2263, 2022. https://doi.org/10.3390/en15062263.
• A. Rai, A. Shrivastava, K. C. Jana, K. C, A CNN‐BiLSTM based deep learning model for mid‐term solar radiation prediction. International Transactions on Electrical Energy Systems, 31(9), e12664, 2021. https ://doi.org/10.1002/2050-7038.12664.
• Y. A. Ali, E. M. Awwad, M. Al-Razgan, A. Maarouf, Hyperparameter Search for Machine Learning Algorithms for Optimizing the Computational Complexity. Processes, 11(2), 349, 2023. https://doi. org/10.3390/pr11020349.
• Z. Qu, J. Xu, Z. Wang, R. Chi, H. Liu, Prediction of electricity generation from a combined cycle power plant based on a stacking ensemble and its hyperparameter optimization with a grid-search method. Energy, 227, 120309, 2021.https://doi.org/10. 1016/j.energy.2021.120309.
• E. Akarslan and F. O. Hocaoglu, A novel method based on similarity for hourly solar irradiance forecasting. Renewable Energy, 112, 337-346, 2017. https://doi .org/10.1016/j.renene.2017.05.058.
• R. Jiao, T. Zhang, Y. Jiang, H. He, Short-term non-residential load forecasting based on multiple sequences LSTM recurrent neural network. IEEE Access, 6, 59438-59448, 2018. https://doi.org/10.1109/ ACCESS.2018.2873712.
• E. Tanyıldız and F. Demirtaş, Hyper Parameter Optimization. In 2019 1st International Informatics and Software Engineering Conference, pp. 1-5, Ankara, Turkey, November, 2019.