Adem DALCALI, Harun ÖZBAY

Effects of COVID-19 on electric energy consumption in Turkey and ANN-based short-term forecasting

Due to the coronavirus, millions of people worldwide carry out their work, education, shopping, culture, and entertainment activities from their homes now using the advantages of today’s technology. Apart from this, patient care and follow-up are carried out with the help of electronic equipment especially in the institutions where health services are provided. It is important to provide a reliable electricity supply for humanity so that people can perform all these services. In this study, the outlook of energy in Turkey was examined. The current energy consumption and investments were examined. Then, the precautions by the government in the pandemic period according to the occurrence and spread of COVID-19 in the country are given in chronological order. The actual electricity consumption data were obtained daily across the country, after all these precautions. It was observed that electricity consumption decreased significantly, especially on restricted days. It is inarguable that energy consumption estimation should be made in the short term so that the energy sector is not adversely affected by this situation. In this study, more accurate short-term consumption forecasting methods were developed during the COVID-19 pandemic period: nonlinear autoregressive (NARX) and long short-term memory (LSTM) artificial neural networks (ANNs). Between January and April 2019 electrical consumption data were used to train and validate the forecast prediction. The NARX and LSTM are potential candidates for effective forecasting of electricity consumption. However, the obtained LSTM results suggest that the proposed method performs better than the NARX ANN.

PDF

___

1] Ünler A. Improvement of energy demand forecasts using swarm intelligence: The case of Turkey with projections to 2025. Energy Policy 2008; 36 (6): 1937-1944. doi: 10.1016/j.enpol.2008.02.018
[2] Boran FE. Forecasting natural gas consumption in Turkey using grey prediction. Energy Sources, Part B: Economics, Planning, and Policy 2015; 10 (2): 208-213. doi: 10.1080/15567249.2014.893040
[3] Küçükönder TY. Utilization of lignite reserves within the scope of decreasing the foreign energy dependency and increasing its economic contribution. Ministry of Development of Turkey, Ankara, Turkey, 2014 (in Turkish). [4] Hepbasli A, Ozalp N. Present status of cogeneration. Energy Sources 2002; 24 (2): 169-177. doi: 10.1080/00908310252774480
[5] Haliloğlu EY, Tutu BE. Short-term electricity power demand forecasting for Turkey. Journal of Yaşar University 2018; 13 (51): 243-255 (in Turkish with an abstract in English).
[6] Schellong W. Energy demand analysis and forecast. In: Kini G (editor). Energy Management Systems. Rijeka, Croatia: InTech, 2011, pp. 101-120,
[7] Vilar JM, Cao R, Aneiros G. Forecasting next-day electricity demand and price using nonparametric func- tional methods. International Journal of Electrical Power & Energy Systems 2012; 39 (1): 48-55. doi: 10.1016/j.ijepes.2012.01.004
[8] Taylor JW. Triple seasonal methods for short-term electricity demand forecasting. European Journal of Operational Research 2010; 204 (1): 139-152. doi: 0.1016/j.ejor.2009.10.003
[9] Fan S. Hyndman RJ. Short-term load forecasting based on a semi-parametric additive model. IEEE Transactions on Power Systems 2012; 27 (1): 134-141. doi: 10.1109/TPWRS.2011.2162082
[10] Hyndman RJ, Fan S. Density forecasting for long-term peak electricity demand. IEEE Transactions on Power Systems 2010; 25 8 (2): 1142-1153. doi: 10.1109/TPWRS.2009.2036017
[11] McSharry PE, Bouwman S, Bloemhof G. Probabilistic forecasts of the magnitude and timing of peak electricity demand. IEEE Transactions on Power Systems 2005; 20 (2): 1166-1172. doi: 10.1109/TPWRS.2009.2036017
[12] Wang AJ, Ramsay B. A neural network based estimator for electricity spot-pricing with particular reference to weekend and public holidays. Neurocomputing 1998; 23 (1-3): 47-57. doi: 10.1016/S0925-2312(98)00079-4
[13] Srinivasan D, Chang CS, Liew AC. Demand forecasting using fuzzy neural computation, with special emphasis on weekend and public holiday forecasting. IEEE Transactions on Power Systems 1995; 10 (4): 1897-1903. doi: 10.1109/59.476055
[14] Chang Z, Zhang Y, Chen W. Effective adam-optimized LSTM neural network for electricity price forecasting. In: IEEE 9th International Conference on Software Engineering and Service Science; Beijing, China; 2018. pp. 245-248.
[15] Kim TY, Cho SB. Predicting residential energy consumption using CNN-LSTM neural networks. Energy 2019; 182: 72-81. doi: 10.1016/j.energy.2019.05.230
[16] Kong W, Dong ZY, Jia Y, Hill DJ, Xu Y et al. Short-term residential load forecasting based on LSTM recurrent neural network. IEEE Transactions on Smart Grid 2019; 10(1): 841-851. doi: 10.1109/TSG.2017.2753802
[17] Zheng J, Xu C, Zhang Z, Li X. Electric load forecasting in smart grids using Long-Short-Term-Memory based Recurrent Neural Network. In: 51st Annual Conference on Information Sciences and Systems, Baltimore, MD, USA; 2017. pp. 1-6.
[18] Amber KP, Ahmad R, Aslam MW, Kousar A, Usman M, Khan MS. Intelligent techniques for forecasting electricity consumption of buildings. Energy 2018; 157: 886-893. doi: 10.1016/j.energy.2018.05.155
[19] Cabral JA, Legey LFL, Cabral MVF. Electricity consumption forecasting in Brazil: A spatial econometrics ap- proach.Energy 2017; 126: 124-131. doi: 10.1016/j.energy.2017.03.005
[20] Brubacher SR, Wilson GT. Interpolating time series with application to the estimation of holiday effects on electricity demand. Journal of the Royal Statistical Society. Series C (Applied Statistics) 1976; 25 (2):107-116. doi: 10.2307/2346678
[21] Ertürk O, Ertürk AE. The effect of renewable energy sources on power generation and current account deficit in Turkey. In: 4th SCF International Conference on “Economic and Social Impacts of Globalization” and Future of Turkey-EU Relations; Nevşehir, Turkey; 2018. pp. 103-113 (in Turkish).
[22] Delihasanlar E, Yaylacı EK, Dalcalı A. Solar energy potential in the world and Turkey, current status, incentives, installation cost analysis-Karabuk province sample. Electronic Letters on Science & Engineering 2019; 15: 12-20 (in Turkish with an abstract in English).
[23] Aggarwal S, Goswami D, Hooda M, Chakravarty A, Kar A, Vasudha. Recommendation systems for interactive multimedia entertainment. In: Hemanth J, Bhatia M, Geman O (editors). Data Visualization and Knowledge Engineering. Lecture Notes on Data Engineering and Communications Technologies, vol 32. Cham: Springer, pp. 23-48.
[24] Christiansen N, Kaltschmitt M, Dzukowski F, Isensee F. Electricity consumption of medical plug loads in hospital laboratories: Identification, evaluation, prediction and verification. Energy and Buildings 2015; 107: 392-406. doi: 10.1016/j.enbuild.2015.08.022.
[25] Lund PD, Lindgren J, Mikkola J, Salpakari J. Review of energy system flexibility measures to enable high levels of variable renewable electricity. Renewable and Sustainable Energy Reviews 2015; 45: 785-807. doi: 10.1016/j.rser.2015.01.057.
[26] Raza MQ, Khosravi A. A review on artificial intelligence-based load demand forecasting techniques for smart grid and buildings. Renewable and Sustainable Energy Reviews 2015; 50: 1352-1372. doi: 10.1016/j.rser.2015.04.065
[27] Ghayekhloo M, Menhaj MB, Ghofrani M. A hybrid short-term load forecasting with a new data preprocessing framework. Electric Power Systems Research 2015; 119: 138-148. doi: 10.1016/j.epsr.2014.09.002
[28] Gamboa JCB. Deep learning for time-series analysis. arXiv 2017; 1-13. arXiv preprint arXiv:1701.01887.
[29] Sak H, Senior A, Beaufays F. Long short-term memory recurrent neural network architectures for large scale acoustic modeling. In: Fifteenth Annual Conference of the International Speech Communication Association. Singapore; 2014. pp. 338-342
[30] Bouktif S, Fiaz A, Oun, A, Serhani AS. Optimal deep learning LSTM model for electric load forecasting using feature selection and genetic algorithm: Comparison with machine learning approaches. Energies 2018; 11 (7): 1-20. doi: 10.3390/en11071636
[31] Yang A, Li W, Yang X. Short-term electricity load forecasting based on feature selection and Least Squares Support Vector Machines. Knowledge-Based Systems 2019; 163: 159-173. doi: 0.1016/j.knosys.2018.08.027
[32] Venturini M. Simulation of compressor transient behavior through recurrent neural network models. Journal of Turbomachinery 2005; 128 (3): 444-454. doi:10.1115/GT2005-68030
[33] MATLAB (2018). R2018a Neural Network Toolbox.
[34] Bennett C, Stewart RA, Lu J. Autoregressive with exogenous variables and neural network short-term load forecast models for residential low voltage distribution networks. Energies 2014; 7: 2938-2960. doi: 10.3390/en7052938
[35] Andalib A, Atry F. Multi-step ahead forecasts for electricity prices using NARX: a new approach, a crit- ical analysis of one-step ahead forecasts. Energy Conversion and Management 2009; 50 (3): 739-747. doi: 10.1016/j.enconman.2008.09.040
[36] Koschwitz D, Frisch J, Van Treeck C. Data-driven heating and cooling load predictions for non-residential buildings based on support vector machine regression and NARX Recurrent Neural Network: A comparative study on district scale. Energy 2018; 165: 134-142. doi: 10.1016/j.energy.2018.09.068