Application of long short-term memory (LSTM) neural network based on deep
learning for electricity energy consumption forecasting

ARSLAN, Niyazi; YASAR, Abdulkadir; BILGILI, Mehmet; SEKERTEKIN, Aliihsan

doi:10.3906/elk-2011-14

Application of long short-term memory (LSTM) neural network based on deep learning for electricity energy consumption forecasting

Mehmet BILGILI, (Çukurova Üniversitesi, Ceyhan Mühendislik Fakültesi, Makine Mühendisliği Bölümü, Adana, Türkiye)

Niyazi ARSLAN, (Çukurova Üniversitesi, Ceyhan Mühendislik Fakültesi, Geomatik Mühendisliği Bölümü, Adana, Türkiye)

Aliihsan SEKERTEKIN, (Çukurova Üniversitesi, Ceyhan Mühendislik Fakültesi, Geomatik Mühendisliği Bölümü, Adana, Türkiye)

Abdulkadir YASAR (Çukurova Üniversitesi, Ceyhan Mühendislik Fakültesi, Makine Mühendisliği Bölümü, Adana, Türkiye)

Turkish Journal of Electrical Engineering and Computer Sciences

8 0

Yıl: 2022 Cilt: 30 Sayı: 1 Sayfa Aralığı: 140 - 157 Metin Dili: İngilizce DOI: 10.3906/elk-2011-14 İndeks Tarihi: 30-06-2022

Application of long short-term memory (LSTM) neural network based on deep learning for electricity energy consumption forecasting

Öz:

Electricity is the most substantial energy form that significantly affects the development of modern life, work efficiency, quality of life, production, and competitiveness of the society in the ever-growing global world. In this respect, forecasting accurate electricity energy consumption (EEC) is fairly essential for any country’s energy consumption planning and management regarding its growth. In this study, four time-series methods; long short-term memory (LSTM) neural network, adaptive neuro-fuzzy inference system (ANFIS) with subtractive clustering (SC), ANFIS with fuzzy cmeans (FCM), and ANFIS with grid partition (GP) were implemented for the short-term one-day ahead EEC prediction. Root mean square error (RMSE), correlation coefficient (R), mean absolute error (MAE) and mean absolute percentage error (MAPE) were considered as statistical accuracy criteria. Those forecasted results by the LSTM, ANFIS-FCM, ANFIS-SC and ANFIS-GP models were evaluated by comparing with the actual data using statistical accuracy metrics. According to the testing process, the best MAPE values were obtained to be 4.47%, 3.21%, 2.34%, and 1.91% for the ANFIS-GP, ANFIS-SC, ANFIS-FCM, and LSTM, respectively. Furthermore, the best RMSE values were found as 25.94 GWh, 41.17 GWh, 29.50 GWh, and 80.14 GWh for the LSTM, ANFIS-SC, ANFIS-FCM, and ANFIS-GP models, respectively. As a consequence, the LSTM model generally outperformed all ANFIS models. The results revealed that forecasting of short-term daily EEC time series using the LSTM approach can provide high accuracy results.

Anahtar Kelime:

Belge Türü: Makale Makale Türü: Araştırma Makalesi Erişim Türü: Erişime Açık

[1] Waewsak J, Landry M, Gagnon Y. Offshore wind power potential of the Gulf of Thailand. Renewable Energy 2015; 81: 609–626. doi: 10.1016/j.renene.2015.03.069
[2] Kaplan YA. Overview of wind energy in the world and assessment of current wind energy policies in Turkey. Renewable & Sustainable Energy Reviews 2015; 43: 562–568. doi: 10.1016/j.rser.2014.11.027
[3] Bilgili M, Sahin B, Yasar A, Simsek E. Electric energy demands of Turkey in residential and industrial sectors. Renewable & Sustainable Energy Reviews 2012; 16 (1): 404–414. doi: 10.1016/j.rser.2011.08.005
[4] Kavaklioglu K. Modeling and prediction of Turkey’s electricity consumption using Support Vector Regression. Applied Energy 2011; 88 (1): 368–375. doi: 10.1016/j.apenergy.2010.07.021
[5] Ardakani FJ, Ardehali MM. Long-term electrical energy consumption forecasting for developing and developed economies based on different optimized models and historical data types. Energy 2014; 65: 452–461. doi: 10.1016/j.energy.2013.12.031
[6] Bilgili M, Ozbek A, Sahin B, Kahraman A. An overview of renewable electric power capacity and progress in new technologies in the world. Renewable & Sustainable Energy Reviews 2015; 49: 323–334. doi: 10.1016/j.rser.2015.04.148
[7] Bianco V, Manca O, Nardini S, Minea AA. Analysis and forecasting of nonresidential electricity consumption in Romania. Applied Energy 2010; 87 (11): 3584–3590. doi: 10.1016/j.apenergy.2010.05.018
[8] Mohan N, Soman KP, Sachin Kumar S. A data-driven strategy for short-term electric load forecasting using dynamic mode decomposition model. Applied Energy 2018; 232: 229–244. doi: 10.1016/j.apenergy.2018.09.190
[9] Tutun S, Chou C-A, Canıyılmaz E. A new forecasting framework for volatile behavior in net electricity consumption: A case study in Turkey. Energy 2015; 93: 2406–2422. doi: 10.1016/j.energy.2015.10.064
[10] Kaytez F, Taplamacioglu MC, Cam E, Hardalac F. Forecasting electricity consumption: A comparison of regression analysis, neural networks and least squares support vector machines. International Journal of Electrical Power & Energy Systems 2015; 67: 431–438. doi: 10.1016/j.ijepes.2014.12.036
[11] Yang Y, Chen Y, Wang Y, Li C, Li L. Modelling a combined method based on ANFIS and neural network improved by DE algorithm: A case study for short-term electricity demand forecasting. Applied Soft Computing 2016; 49: 663–675. doi: 10.1016/j.asoc.2016.07.053
[12] Soares LJ, Souza LR. Forecasting electricity demand using generalized long memory. International Journal of Forecasting 2006; 22 (1): 17–28. doi: 10.1016/j.ijforecast.2005.09.004
[13] Zhang J, Wei Y-M, Li D, Tan Z, Zhou J. Short term electricity load forecasting using a hybrid model. Energy 2018; 158: 774–781. doi: 10.1016/j.energy.2018.06.012
[14] Rahman A, Srikumar V, Smith AD. Predicting electricity consumption for commercial and residential buildings using deep recurrent neural networks. Applied Energy 2018; 212: 372–385. doi: 10.1016/j.apenergy.2017.12.051
[15] Günay ME. Forecasting annual gross electricity demand by artificial neural networks using predicted values of socio-economic indicators and climatic conditions: Case of Turkey. Energy Policy 2016; 90: 92–101. doi: 10.1016/j.enpol.2015.12.019
[16] Hamzaçebi C. Forecasting of Turkey’s net electricity energy consumption on sectoral bases. Energy Policy 2007; 35 (3): 2009–2016. doi: 10.1016/j.enpol.2006.03.014
[17] Kankal M, Akpınar A, Kömürcü Mİ, Özşahin TŞ. Modeling and forecasting of Turkey’s energy consumption using socio-economic and demographic variables. Applied Energy 2011; 88 (5): 1927–1939. doi: 10.1016/j.apenergy.2010.12.005
[18] Oğcu G, Demirel OF, Zaim S. Forecasting Electricity Consumption with Neural Networks and Support Vector Regression. Procedia - Social and Behavioral Sciences 2012; 58: 1576–1585. doi: 10.1016/j.sbspro.2012.09.1144
[19] Ünlü R. A Comparative Study of Machine Learning and Deep Learning for Time Series Forecasting: A Case Study of Choosing the Best Prediction Model for Turkey Electricity Production. Süleyman Demirel Üniversitesi Fen Bilimleri Enstitüsü Dergisi 2019; 23 (2): 635–646. doi: 10.19113/sdufenbed.494396
[20] Dilaver Z, Hunt LC. Turkish aggregate electricity demand: An outlook to 2020. Energy 2011; 36 (11): 6686–6696. doi: 10.1016/j.energy.2011.07.043
[21] Uzlu E, Kankal M, Akpınar A, Dede T. Estimates of energy consumption in Turkey using neural networks with the teaching–learning-based optimization algorithm. Energy 2014; 75: 295–303. doi: 10.1016/j.energy.2014.07.078
[22] Bilgili M. Estimation of net electricity consumption of Turkey. Journal of Thermal Science and Technology 2009; 29 (2): 89–98.
[23] Ayvaz B, Kusakci AO. Electricity consumption forecasting for Turkey with nonhomogeneous discrete grey model. Energy Sources, Part B: Economics, Planning, and Policy 2017; 12 (3): 260–267. doi: 10.1080/15567249.2015.1089337
[24] Ertugrul ÖF. Forecasting electricity load by a novel recurrent extreme learning machines approach. International Journal of Electrical Power & Energy Systems 2016; 78: 429–435. doi: 10.1016/j.ijepes.2015.12.006
[25] Wang Y, Gan D, Sun M, Zhang N, Lu Z et al. Probabilistic individual load forecasting using pinball loss guided LSTM. Applied Energy 2019; 235: 10–20. doi: 10.1016/j.apenergy.2018.10.078
[26] He F, Zhou J, Feng Z, Liu G, Yang Y. A hybrid short-term load forecasting model based on variational mode decomposition and long short-term memory networks considering relevant factors with Bayesian optimization algorithm. Applied Energy 2019; 237: 103–116. doi: 10.1016/j.apenergy.2019.01.055
[27] Bedi J, Toshniwal D. Deep learning framework to forecast electricity demand. Applied Energy 2019; 238: 1312–1326. doi: 10.1016/j.apenergy.2019.01.113
[28] Hamzacebi C, Es HA. Forecasting the annual electricity consumption of Turkey using an optimized grey model. Energy 2014; 70: 165–171. doi: 10.1016/j.energy.2014.03.105
[29] Çunkaş M, Altun AA. Long Term Electricity Demand Forecasting in Turkey Using Artificial Neural Networks. Energy Sources, Part B: Economics, Planning, and Policy 2010; 5 (3): 279–289. doi: 10.1080/15567240802533542
[30] Kim T-Y, Cho S-B. Predicting residential energy consumption using CNN-LSTM neural networks. Energy 2019; 182: 72–81. doi: 10.1016/j.energy.2019.05.230
[31] Peng L, Liu S, Liu R, Wang L. Effective long short-term memory with differential evolution algorithm for electricity price prediction. Energy 2018; 162: 1301–1314. doi: 10.1016/j.energy.2018.05.052
[32] Wang L, Hu H, Ai X-Y, Liu H. Effective electricity energy consumption forecasting using echo state network improved by differential evolution algorithm. Energy 2018; 153: 801–815. doi: 10.1016/j.energy.2018.04.078
[33] Zeng Y-R, Zeng Y, Choi B, Wang L. Multifactor-influenced energy consumption forecasting using enhanced backpropagation neural network. Energy 2017; 127: 381–396. doi: 10.1016/j.energy.2017.03.094
[34] Zhang Z, Ye L, Qin H, Liu Y, Wang C et al. Wind speed prediction method using Shared Weight Long Short-Term Memory Network and Gaussian Process Regression. Applied Energy 2019; 247: 270–284. doi: 10.1016/j.apenergy.2019.04.047
[35] Zhang J, Yan J, Infield D, Liu Y, Lien F. Short-term forecasting and uncertainty analysis of wind turbine power based on long short-term memory network and Gaussian mixture model. Applied Energy 2019; 241: 229–244. doi: 10.1016/j.apenergy.2019.03.044
[36] Yüksel Haliloğlu E, Tutu BE. Forecasting daily electricity demand for Turkey. Turkish Journal of Energy Policy 2018; 3 (7): 40–49.
[37] Jang J-SR. ANFIS: adaptive-network-based fuzzy inference system. IEEE Transactions on Systems, Man, and Cybernetics 1993; 23 (3): 665–685. doi: 10.1109/21.256541
[38] Abyaneh HZ, Nia AM, Varkeshi MB, Marofi S, Kisi O. Performance Evaluation of ANN and ANFIS Models for Estimating Garlic Crop Evapotranspiration. Journal of Irrigation and Drainage Engineering 2011; 137 (5): 280–286. doi: 10.1061/(ASCE)IR.1943-4774.0000298
[39] Karakuş O, Kuruoǧlu EE, Altinkaya MA. One-day ahead wind speed/power prediction based on polynomial autoregressive model. IET Renewable Power Generation 2017; 11 (11): 1430–1439. doi: 10.1049/iet-rpg.2016.0972
[40] Tabari H, Kisi O, Ezani A, Hosseinzadeh Talaee P. SVM, ANFIS, regression and climate based models for reference evapotranspiration modeling using limited climatic data in a semi-arid highland environment. Journal of Hydrology 2012; 444: 78–89. doi: 10.1016/j.jhydrol.2012.04.007
[41] Park I, Kim HS, Lee J, Kim JH, Song CH et al. Temperature Prediction Using the Missing Data Refinement Model Based on a Long Short-Term Memory Neural Network. Atmosphere (Basel). 2019; 10 (11): 718. doi: 10.3390/atmos10110718
[42] Cai Q, Yan B, Su B, Liu S, Xiang M et al. Short‐term load forecasting method based on deep neural network with sample weights. International Transactions on Electrical Energy Systems 2020; 30 (5). doi: 10.1002/2050-7038.12340
[43] Hochreiter S, Schmidhuber J. Long Short-Term Memory. Neural Computation 1997; 9 (8): 1735–1780. doi: 10.1162/neco.1997.9.8.1735
[44] Zahroh S, Hidayat Y, Pontoh RS. Modeling and Forecasting Daily Temperature in Bandung. In: Proceedings of the International Conference on Industrial Engineering and Operations Management; Riyadh, Saudi Arabia; 2019. pp. 406-412.
[45] Salman AG, Heryadi Y, Abdurahman E, Suparta W. Single Layer & Multi-layer Long Short-Term Memory (LSTM) Model with Intermediate Variables for Weather Forecasting. Procedia Computer Science 2018; 135: 89–98. doi: 10.1016/j.procs.2018.08.153

APA	BILGILI M, ARSLAN N, SEKERTEKIN A, YASAR A (2022). Application of long short-term memory (LSTM) neural network based on deep learning for electricity energy consumption forecasting. , 140 - 157. 10.3906/elk-2011-14
Chicago	BILGILI Mehmet,ARSLAN Niyazi,SEKERTEKIN Aliihsan,YASAR Abdulkadir Application of long short-term memory (LSTM) neural network based on deep learning for electricity energy consumption forecasting. (2022): 140 - 157. 10.3906/elk-2011-14
MLA	BILGILI Mehmet,ARSLAN Niyazi,SEKERTEKIN Aliihsan,YASAR Abdulkadir Application of long short-term memory (LSTM) neural network based on deep learning for electricity energy consumption forecasting. , 2022, ss.140 - 157. 10.3906/elk-2011-14
AMA	BILGILI M,ARSLAN N,SEKERTEKIN A,YASAR A Application of long short-term memory (LSTM) neural network based on deep learning for electricity energy consumption forecasting. . 2022; 140 - 157. 10.3906/elk-2011-14
Vancouver	BILGILI M,ARSLAN N,SEKERTEKIN A,YASAR A Application of long short-term memory (LSTM) neural network based on deep learning for electricity energy consumption forecasting. . 2022; 140 - 157. 10.3906/elk-2011-14
IEEE	BILGILI M,ARSLAN N,SEKERTEKIN A,YASAR A "Application of long short-term memory (LSTM) neural network based on deep learning for electricity energy consumption forecasting." , ss.140 - 157, 2022. 10.3906/elk-2011-14
ISNAD	BILGILI, Mehmet vd. "Application of long short-term memory (LSTM) neural network based on deep learning for electricity energy consumption forecasting". (2022), 140-157. https://doi.org/10.3906/elk-2011-14

APA	BILGILI M, ARSLAN N, SEKERTEKIN A, YASAR A (2022). Application of long short-term memory (LSTM) neural network based on deep learning for electricity energy consumption forecasting. Turkish Journal of Electrical Engineering and Computer Sciences, 30(1), 140 - 157. 10.3906/elk-2011-14
Chicago	BILGILI Mehmet,ARSLAN Niyazi,SEKERTEKIN Aliihsan,YASAR Abdulkadir Application of long short-term memory (LSTM) neural network based on deep learning for electricity energy consumption forecasting. Turkish Journal of Electrical Engineering and Computer Sciences 30, no.1 (2022): 140 - 157. 10.3906/elk-2011-14
MLA	BILGILI Mehmet,ARSLAN Niyazi,SEKERTEKIN Aliihsan,YASAR Abdulkadir Application of long short-term memory (LSTM) neural network based on deep learning for electricity energy consumption forecasting. Turkish Journal of Electrical Engineering and Computer Sciences, vol.30, no.1, 2022, ss.140 - 157. 10.3906/elk-2011-14
AMA	BILGILI M,ARSLAN N,SEKERTEKIN A,YASAR A Application of long short-term memory (LSTM) neural network based on deep learning for electricity energy consumption forecasting. Turkish Journal of Electrical Engineering and Computer Sciences. 2022; 30(1): 140 - 157. 10.3906/elk-2011-14
Vancouver	BILGILI M,ARSLAN N,SEKERTEKIN A,YASAR A Application of long short-term memory (LSTM) neural network based on deep learning for electricity energy consumption forecasting. Turkish Journal of Electrical Engineering and Computer Sciences. 2022; 30(1): 140 - 157. 10.3906/elk-2011-14
IEEE	BILGILI M,ARSLAN N,SEKERTEKIN A,YASAR A "Application of long short-term memory (LSTM) neural network based on deep learning for electricity energy consumption forecasting." Turkish Journal of Electrical Engineering and Computer Sciences, 30, ss.140 - 157, 2022. 10.3906/elk-2011-14
ISNAD	BILGILI, Mehmet vd. "Application of long short-term memory (LSTM) neural network based on deep learning for electricity energy consumption forecasting". Turkish Journal of Electrical Engineering and Computer Sciences 30/1 (2022), 140-157. https://doi.org/10.3906/elk-2011-14