Didem Guleryuz
Didem Guleryuz
Department of Industrial Engineering, Bayburt University, Bayburt, Turkey
Energy is one of the most critical inputs in social and economic development, is an essential factor in increasing living standards and creating sustainable development. Since energy is an indispensable input in all sectors, energy dependence contributed to the necessity of countries' energy policy. It has critical importance to predict energy demand to determine energy policies. According to Turkey's annual energy consumption, the industry sector has consumed the most energy in the last five years. The prediction and analysis of energy demand with economic data in the industrial sector is an essential indicator of the economic development relationship between energy demand and industry. In this study, Multiple Linear Regression (MLR), Adaptive Neuro-Fuzzy Inference System (ANFIS), and optimized ANFIS with Particle Swarm Optimization (PSO) methods are employed to forecast energy demand for Turkish industrial sectors. The indicators which affect energy consumption were determined to estimate the energy demand. The 30-year dataset between 1990 and 2019 was split as training and test set. MLR, ANFIS and PSO- ANFIS were compared according to performance evaluation, and the most proper model was identified. The coefficient of determination (R2) for PSO-ANFIS, MLR, and ANFIS models are 0.9951, 0.9889, and 0.9932 in the training stage, and 0.9423, 0.9181, and 0.8776 in the testing stage, respectively. The study results indicated that the PSO-ANFIS model showed superior prediction capability with the least estimation error than MLR and ANFIS models. Consequently, parameters tuned PSO-ANFIS is able to predict the industrial energy demand in Turkey with high accuracy.
Industrial Energy Demand, Forecasting, ANFIS, PSO-ANFIS, MLR
Didem Guleryuz (2021). Determination of industrial energy demand in Turkey using MLR, ANFIS and PSO-ANFIS. Journal of Artificial Intelligence and Systems, 3, 16–34. https://doi.org/10.33969/AIS.2021.31002.
[1] IEA. IEA World Energy Report 2005. https://www.iea.org.
[2] IEA. IEA World Energy Balances 2020. https://www.iea.org/subscribe-to-data-services/world-energy-balances-and-statistics.
[3] Bayramoğlu T, Pabuçcu H, Çelebi Boz F, Türkiye İçin Anfıs Modeli İle Birincil Enerji Talep Tahmini. Ege Akad Bakis (Ege Acad Rev 2017;17:431–46. https://doi.org/10.21121/eab.2017328408.
[4] Barak S, Sadegh SS. Forecasting energy consumption using ensemble ARIMA-ANFIS hybrid algorithm. Int J Electr Power Energy Syst 2016;82:92–104. https://doi.org/10.1016/j.ijepes.2016.03.012.
[5] Jawad M, Nadeem MSA, Shim SO, Khan IR, Shaheen A, Habib N, et al. Machine Learning Based Cost Effective Electricity Load Forecasting Model Using Correlated Meteorological Parameters. IEEE Access 2020;8:146847–64. https://doi.org/10.1109/ACCESS.2020.3014086.
[6] Karaaslan A, Gezen M. Forecasting of Turkey's sectoral energy demand by using fuzzy grey regression model. Int J Energy Econ Policy 2017;7:67–77.
[7] Adedeji P, Madushele N, Akinlabi S. Adaptive Neuro-fuzzy Inference System (ANFIS) for a multi-campus institution energy consumption forecast in South Africa. Proc Int Conf Ind Eng Oper Manag 2018;2018:950–8.
[8] Yayar R, Hekim M, Yılmaz V, Bakırcı F. A comparison of ANFIS and ARIMA techniques in the forecasting of electric energy consumption of Tokat province in Turkey. J Econ Soc Stud 2011;1:87–112. https://doi.org/10.14706/jecoss11124.
[9] Akay D, Atak M. Grey prediction with rolling mechanism for electricity demand forecasting of Turkey. Energy 2007;32:1670–5. https://doi.org/10.1016/j.energy.2006.11.014.
[10] Demirci E. Anfis İle Doğalgaz Talep Tahmini; Türkiye Örneği. Int J Soc Sci Acad 2020.
[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. Appl Soft Comput J 2016;49:663–75. https://doi.org/10.1016/j.asoc.2016.07.053.
[12] Ahmad AS, Hassan MY, Abdullah MP, Rahman HA, Hussin F, Abdullah H, et al. A review on applications of ANN and SVM for building electrical energy consumption forecasting. Renew Sustain Energy Rev 2014;33:102–9. https://doi.org/10.1016/j.rser.2014.01.069.
[13] Vinagre E, Pinto T, Ramos S, Vale Z, Corchado JM. Electrical Energy Consumption Forecast Using Support Vector Machines. Proc - Int Work Database Expert Syst Appl DEXA 2017:171–5. https://doi.org/10.1109/DEXA.2016.046.
[14] Kasule A, Ayan K. Using PSO and Genetic algorithms to optimize ANFIS model for forecasting Uganda's net electricity consumption. Sak Univ J Sci 2020:324–37. https://doi.org/10.16984/saufenbilder.629553.
[15] Aghay SH, Fallahpour A, Selvaraj J, Rahim NA. Long-term electrical energy consumption formulating and forecasting via optimized gene expression programming. Energy 2017;126:144–64. https://doi.org/10.1016/j.energy.2017.03.009.
[16] Huang Y, Yang L, Gao C, Jiang Y, Dong Y. A novel prediction approach for short-term renewable energy consumption in china based on improved gaussian process regression. Energies 2019;12:1–17. https://doi.org/10.3390/en12214181.
[17] Beyca OF, Ervural BC, Tatoglu E, Ozuyar PG, Zaim S. Using machine learning tools for forecasting natural gas consumption in the province of Istanbul. Energy Econ 2019;80:937–49. https://doi.org/10.1016/j.eneco.2019.03.006.
[18] Liu X, Moreno B, García AS. A grey neural network and input-output combined forecasting model. Primary energy consumption forecasts in Spanish economic sectors. Energy 2016;115:1042–54. https://doi.org/10.1016/j.energy.2016.09.017.
[19] Alcaraz C, Villalvazo S. The effect of natural gas shortages on the Mexican economy. Energy Econ 2017;66:147–53. https://doi.org/10.1016/j.eneco.2017.06.006.
[20] Shaikh F, Ji Q. Forecasting natural gas demand in China: Logistic modelling analysis. Int J Electr Power Energy Syst 2016;77:25–32. https://doi.org/10.1016/j.ijepes.2015.11.013.
[21] Naji S, Shamshirband S, Basser H, Alengaram UJ, Jumaat MZ, Amirmojahedi M. Soft computing methodologies for estimation of energy consumption in buildings with different envelope parameters. Energy Effic 2016;9:435–53. https://doi.org/10.1007/s12053-015-9373-z.
[22] Azadeh A, Asadzadeh SM, Ghanbari A. An adaptive network-based fuzzy inference system for short-term natural gas demand estimation: Uncertain and complex environments. Energy Policy 2010;38:1529–36. https://doi.org/10.1016/j.enpol.2009.11.036.
[23] Hamzaçebi C. Forecasting of Turkey's net electricity energy consumption on sectoral bases. Energy Policy 2007;35:2009–16. https://doi.org/10.1016/j.enpol.2006.03.014.
[24] Moayedi H, Raftari M, Sharifi A, Jusoh WAW, Rashid ASA. Optimization of ANFIS with GA and PSO estimating α ratio in driven piles. Eng Comput 2020;36:227–38. https://doi.org/10.1007/s00366-018-00694-w.
[25] Basser H, Karami H, Shamshirband S, Akib S, Amirmojahedi M, Ahmad R, et al. Hybrid ANFIS-PSO approach for predicting optimum parameters of a protective spur dike. Appl Soft Comput J 2015;30:642–9. https://doi.org/10.1016/j.asoc.2015.02.011.
[26] Shamshirband S, Hadipoor M, Baghban A, Mosavi A, Bukor J, Várkonyi-Kóczy AR. Developing an ANFIS-PSO model to predict mercury emissions in combustion flue gases. Mathematics 2019;7:1–16. https://doi.org/10.3390/math7100965.
[27] Pousinho HMI, Mendes VMF, Catalão JPS. A hybrid pso-anfis approach for short-term wind power prediction in Portugal. Energy Convers Manag 2011;52:397–402. https://doi.org/10.1016/j.enconman.2010.07.015.
[28] Kouziokas GN. A new W-SVM kernel combining PSO-neural network transformed vector and Bayesian optimized SVM in GDP forecasting. Eng Appl Artif Intell 2020;92:103650. https://doi.org/10.1016/j.engappai.2020.103650.
[29] Hamit-Haggar M. Greenhouse gas emissions, energy consumption and economic growth: A panel cointegration analysis from Canadian industrial sector perspective. Energy Econ 2012;34:358–64. https://doi.org/10.1016/j.eneco.2011.06.005.
[30] Dées S, Karadeloglou P, Kaufmann RK, Sánchez M. Modelling the world oil market: Assessment of a quarterly econometric model. Energy Policy 2007;35:178–91. https://doi.org/10.1016/j.enpol.2005.10.017.
[31] TME. Energy Efficiency Portal 2020. https://enverportal.enerji.gov.tr/.
[32] Bank W. World Bank Open Data 2020. https://data.worldbank.org/.
[33] Wang Y, Li J, Gu J, Zhou Z, Wang Z. Artificial neural networks for infectious diarrhea prediction using meteorological factors in Shanghai (China). Appl Soft Comput J 2015;35:280–90. https://doi.org/10.1016/j.asoc.2015.05.047.
[34] Zahedi G, Azizi S, Bahadori A, Elkamel A, Wan Alwi SR. Electricity demand estimation using an adaptive neuro-fuzzy network: A case study from the Ontario province - Canada. Energy 2013;49:323–8. https://doi.org/10.1016/j.energy.2012.10.019.
[35] Duan H, Lei GR, Shao K. Forecasting crude oil consumption in China using a grey prediction model with an optimal fractional-order accumulating operator. Complexity 2018;2018. https://doi.org/10.1155/2018/3869619.
[36] Civelekoglu G, Yigit NO, Diamadopoulos E, Kitis M. Prediction of bromate formation using multi-linear regression and artificial neural networks. Ozone Sci Eng 2007;29:353–62. https://doi.org/10.1080/01919510701549327.
[37] Becerra M, Jerez A, Aballay B, Garcés HO, Fuentes A. Forecasting emergency admissions due to respiratory diseases in high variability scenarios using time series: A case study in Chile. Sci Total Environ 2020;706. https://doi.org/10.1016/j.scitotenv.2019.134978.