The application of different optimization techniques and Artificial Neural Networks (ANN) for coal-consumption forecasting: a case study

• Autorzy: Seker Mustafa , Unal Kartal Neslihan , Karadirek Selin , Gulludag Cevdet Bertan

Identyfikatory

DOI

10.24425/gsm.2022.141668

Warianty tytułu

PL

Zastosowanie różnych technik optymalizacji i sztucznych sieci neuronowych (SSN) do prognozowania zużycia węgla: studium przypadku

• Języki publikacji: EN

Abstrakty

EN

The demand for energy on a global scale increases day by day. Unlike renewable energy sources, fossil fuels have limited reserves and meet most of the world’s energy needs despite their adverse environmental effects. This study presents a new forecast strategy, including an optimization-based S-curve approach for coal consumption in Turkey. For this approach, Genetic Algorithm (GA) and Particle Swarm Optimization (PSO), Grey Wolf Optimization (GWO), and Whale Optimization Algorithm (WOA) are among the meta-heuristic optimization techniques used to determine the optimum parameters of the S-curve. In addition, these algorithms and Artificial Neural Network (ANN) have also been used to estimate coal consumption. In evaluating coal consumption with ANN, energy and economic parameters such as installed capacity, gross generation, net electric consumption, import, export, and population energy are used for input parameters. In ANN modeling, the Feed Forward Multilayer Perceptron Network structure was used, and Levenberg-Marquardt Back Propagation has used to perform network training. S-curves have been calculated using optimization, and their performance in predicting coal consumption has been evaluated statistically. The findings reveal that the optimization-based S-curve approach gives higher accuracy than ANN in solving the presented problem. The statistical results calculated by the GWO have higher accuracy than the PSO, WOA, and GA with R² = 0.9881, RE = 0.011, RMSE = 1.079, MAE = 1.3584, and STD = 1.5187. The novelty of this study, the presented methodology does not need more input parameters for analysis. Therefore, it can be easily used with high accuracy to estimate coal consumption within other countries with an increasing trend in coal consumption, such as Turkey.

PL

Zapotrzebowanie na energię w skali globalnej rośnie z dnia na dzień. W przeciwieństwie do odnawialnych źródeł energii, paliwa kopalne mają ograniczone rezerwy i zaspokajają większość światowego zapotrzebowania na energię pomimo ich niekorzystnego wpływu na środowisko. Niniejsze opracowanie przedstawia nową strategię prognozowania, w tym oparte na optymalizacji podejście oparte na krzywej S dla zużycia węgla w Turcji. W tym podejściu algorytmy optymalizacji genetycznej (GA) i optymalizacji roju cząstek (PSO), optymalizacja Gray Wolf (GWO) i algorytm optymalizacji wielorybów (WOA) należą do metaheurystycznych technik optymalizacji stosowanych do określenia optymalnych parametrów krzywej S. Ponadto algorytmy te oraz sztuczna sieć neuronowa (SSN) zostały również wykorzystane do oszacowania zużycia węgla. Przy ocenie zużycia węgla za pomocą SSN jako parametry wejściowe wykorzystuje się parametry energetyczne i ekonomiczne, takie jak moc zainstalowana, produkcja brutto, zużycie energii elektrycznej netto, import, eksport i energia ludności. W modelowaniu SSN wykorzystano strukturę Feed Forward Multilayer Perceptron Network, a do uczenia sieci wykorzystano propagację wsteczną Levenberg-Marquardt. Krzywe S zostały obliczone za pomocą optymalizacji, a ich skuteczność w przewidywaniu zużycia węgla została oceniona statystycznie. Wyniki pokazują, że podejście oparte na optymalizacji opartej na krzywej S zapewnia większą dokładność niż SSN w rozwiązaniu przedstawionego problemu. Wyniki statystyczne obliczone przez GWO mają wyższą dokładność niż PSO, WOA i GA z R² = 0,9881, RE = 0,011, RMSE = 1,079, MAE = 1,3584 i STD = 1,5187. Nowość tego badania, prezentowana metodyka nie wymaga dodatkowych parametrów wejściowych do analizy. Dzięki temu może być z łatwością wykorzystany z dużą dokładnością do oszacowania zużycia węgla w innych krajach o tendencji wzrostowej zużycia węgla, takich jak Turcja.

Słowa kluczowe

EN

coal consumption; metaheuristic optimization; grey wolf optimization; particle swarm optimization; whale optimization

PL

zużycie węgla; optymalizacja metaheurystyczna; optymalizacja szarego wilka; optymalizacja roju cząstek; optymalizacja wielorybów

• Wydawca: Instytut Gospodarki Surowcami Mineralnymi i Energią PAN ; Komitet Zrównoważonej Gospodarki Surowcami Mineralnymi PAN
• Czasopismo: Gospodarka Surowcami Mineralnymi
• Rocznik: 2022
• Tom: T. 38, z. 2
• Strony: 77--112
• Opis fizyczny: Bibliogr. 56 poz., rys., tab., wykr.

Twórcy

autor

Seker Mustafa

• Sivas Cumhuriyet University, Turkey

• https://orcid.org/0000-0002-3793-8786

autor

Unal Kartal Neslihan

• Burdur Mehmet Akif Ersoy University, Turkey

autor

Karadirek Selin

• Akdeniz University, Antalya, Turkey

autor

Gulludag Cevdet Bertan

• Akdeniz University, Antalya, Turkey

Bibliografia

• [1] Alam at. al. 2015 – Alam, M.N., Biswarup, D. and Vinay, P. 2015. A Comparative Study of Metaheuristic Optimization Approaches for Directional Overcurrent Relays Coordination. Electric Power Systems Research 128, pp. 39–52, DOI: 10.1016/j.epsr.2015.06.018.
• [2] Anand at. al. 2019 – Anand, H., Nitin, N. and Dhillon, J.S., 2019. Multi-Objective Combined Heat and Power Unit Commitment Using Particle Swarm Optimization. Energy 172, pp. 794–807, DOI: 10.1016/j.energy.2019.01.155.
• [3] Assareh at. al. 2012 – Assareh, E., Behrang, M.A. and Ghanbarzadeh, A. 2012. The Integration of Artificial Neural Networks and Particle Swarm Optimization to Forecast World Green Energy Consumption. Energy Sources, Part B: Economics, Planning and Policy 7(4), pp. 398–410, DOI: 10.1080/15567241003792341.
• [4] Aydin, G. 2015a. The Application of Trend Analysis for Coal Demand Modeling. Energy Sources, Part B: Economics, Planning and Policy 10(2), pp. 183–91, DOI: 10.1080/15567249.2013.813611.
• [5] Aydin, G. 2015b. The Modeling and Projection of Primary Energy Consumption by the Sources. Energy Sources, Part B: Economics, Planning and Policy 10(1), pp. 67–74, DOI: 10.1080/15567249.2013.771716.
• [6] Azadeh at. al. 2007 – Azadeh, A, Ghaderi, S.F. and Sohrabkhani, S. 2007. Forecasting Electrical Consumption by Integration of Neural Network, Time Series and ANOVA. Applied Mathematics and Computation 186(2), pp. 1753–1761, DOI: 10.1016/j.amc.2006.08.094.
• [7] Basheer I.A. and Hajmeer M. 2000. Artificial Neural Networks: Fundamentals, Computing, Design, and Application. Journal of Microbiological Methods 43, pp. 3–31.
• [8] Bechtler at. al. 2001 – Bechtler, H., Browne, M.W., Bansal, P.K. and Kecman, V. 2001. New Approach to Dynamic Modelling of Vapour-Compression Liquid Chillers: Artificial Neural Networks. Applied Thermal Engineering 21(9), pp. 941–53, DOI: 10.1016/S1359-4311(00)00093-4.
• [9] Benalcazar at. al. 2017 – Benalcazar, P., Krawczyk, M. and Kamiński, J. 2017. Forecasting Global Coal Consumption: An Artificial Neural Network Approach. Gospodarka Surowcami Mineralnymi / Mineral Resources Management 33(4), pp. 29–44, DOI: 10.1515/gospo–2017-0042.
• [10] BP 2020. Statistical Review of World Energy. [Online] https://bp.com/en/global/corporate/energy-economics/statistical-review-of-world-energy.html [Accessed: 2022-05-25].
• [11] Clerc, M. and James, K., 2002. The Particle Swarm-Explosion, Stability, and Convergence in a Multidimensional Complex Space. IEEE Transactions on Evolutionary Computation 6(1), pp. 58–73, DOI: 10.1109/4235.985692.
• [12] Dreyfus, G. 2005. Neural Networks: Methodology and Applications. Neural Networks: Methodology and Applications. 1st ed. Berlin: Springer-Verlag Berlin Heidelberg, DOI: 10.1007/3-540-28847-3.
• [13] Eberhart, R. and James, K. 1995. New Optimizer Using Particle Swarm Theory. Proceedings of the International Symposium on Micro Machine and Human Science, pp. 39–43, DOI: 10.1109/mhs.1995.494215.
• [14] Ediger, V.Ş. and Tatlidil, T. 2002. Forecasting the Primary Energy Demand in Turkey and Analysis of Cyclic Patterns. Energy Conversion and Management 43(4), pp. 473–87, DOI: 10.1016/S0196-8904(01)00033-4.
• [15] Elmas, Ç. 2007. Yapay Zeka Uygulamaları. Birinci Ba. Seçkin Yayıncılık.
• [16] Shi, Y. and Eberhart, R.C. 1995. Empirical Study of Particle Swarm Optimization, “in Proc.” Evolutionary Comput, 1942–48.
• [17] EIGM (Directorate General of Energy Affairs) 2018. General Energy Balance Tables. [Online] https:/eigm.gov.tr/tr-TR/Denge-Tablolari/Denge-Tablolari [Accessed: 2022-05-15].
• [18] EKTB (Republic of Turkey Ministry of Energy and Natural Resources) 2019. Electricity Report. [Online] https://enerji.gov.tr/tr-TR/Sayfalar/Elektrik [Accessed: 2022-05-15].
• [19] Fan, S.K.S. and Chiu, Y.Y. 2007. A Decreasing Inertia Weight Particle Swarm Optimizer. Engineering Optimization 39(2), pp. 203–28, DOI: 10.1080/03052150601047362.
• [20] Feng at. al. 2012 – Feng, S.J., Ma, Y.D., Song, Z.L. and Ying, J. 2012. Forecasting the Energy Consumption of China by the Grey Prediction Model. Energy Sources, Part B: Economics, Planning and Policy 7(4), pp. 376–89, DOI: 10.1080/15567240903330426.
• [21] Feng at. al. 2007 – Feng, Y., Teng, G., Wang, A.X. and Yao, Y.M. 2007. Chaotic Inertia Weight in Particle Swarm Optimization. Second International Conference on Innovative Computing, Information and Control, ICICIC 2007, pp. 18–21, DOI: 10.1109/ICICIC.2007.209.
• [22] Gao at. al. 2008 – Gao, Y.L., An, X.H. and Liu, J.M. 2008. A Particle Swarm Optimization Algorithm with Logarithm Decreasing Inertia Weight and Chaos Mutation. Proceedings - 2008 International Conference on Computational Intelligence and Security, CIS 2008 1, pp. 61–65, DOI: 10.1109/CIS.2008.183.
• [23] Hekimoğlu at. al. 2019 – Hekimoǧlu, B., Serdar, E. and Serhat, K. 2019. Optimal PID Controller Design of DC-DC Buck Converter Using Whale Optimization Algorithm. 2018 International Conference on Artificial Intelligence and Data Processing, IDAP 2018, pp. 1–6, DOI: 10.1109/IDAP.2018.8620833.
• [24] Hof, P.R. and Estel, V.D.G. 2006. Structure of the Cerebral Cortex of the Humpback Whale, Megaptera Novaeangliae (Cetacea, Mysticeti, Balaenopteridae). The Anatomical Record Part A: Discoveries in Molecular, Cellular, and Evolutionary Biology 31 (October 2006), pp. 1–31, DOI: 10.1002/ar.a.20407.
• [25] Jiang at. al. 2018 – Jiang, S., Yang, C., Guo, J. and Ding, Z. 2018. ARIMA Forecasting of China’s Coal Consumption, Price and Investment by 2030. Energy Sources, Part B: Economics, Planning and Policy 13(3), pp. 190–195, DOI: 10.1080/15567249.2017.1423413.
• [26] Kalogirou, S.A. 2000. Artificial Neural Networks in Renewable Energy Systems Applications: A Review. Renewable and Sustainable Energy Reviews 5(4), pp. 373–401, DOI: 10.1016/S1364-0321(01)00006-5.
• [27] Kankal, M. and Uzlu, E. 2017. Neural Network Approach with Teaching–Learning-Based Optimization for Modeling and Forecasting Long-Term Electric Energy Demand in Turkey. Neural Computing and Applications 28 (s1), pp. 737–747, DOI: 10.1007/s00521-016-2409-2.
• [28] Kim, H.M. and Seung, H.Y. 2016. Coal Consumption and Economic Growth in Indonesia. Energy Sources, Part B: Economics, Planning and Policy 11(6), pp. 547–552, DOI: 10.1080/15567249.2012.690503.
• [29] Korkmaz at. al. 2008 – Korkmaz, S., Gulbay, R. K. and Turan, M. 2008. Fossil Fuel Potential of Turkey: A Statistical Evaluation of Reserves, Production, and Consumption. Energy Sources, Part B: Economics, Planning and Policy 3(3), pp. 296–304, DOI: 10.1080/15567240601057537.
• [30] Ma, H.W. and Zhang, D.Q. 2009. A Grey Forecasting Model for Coal Production and Consumption. 2009 IEEE International Conference on Grey Systems and Intelligent Services, GSIS 2009, pp. 512–516, DOI: 10.1109/GSIS.2009.5408261.
• [31] Mashayekhi at.al. 2019 – Mashayekhi, M., Harati, M. and Estekanchi, H.E. 2019. Development of an Alternative PSO‐based Algorithm for Simulation of Endurance Time Excitation Functions. Engineering Reports 1(3), pp. 1–15, DOI: 10.1002/eng2.12048.
• [32] Mirjalili, S. and Lewis, A. 2016. The Whale Optimization Algorithm. Advances in Engineering Software 95, pp. 51–67, DOI: 10.1016/j.advengsoft.2016.01.008.
• [33] Mirjalili S. at.al. 2014 – Mirjalili, S., Mirjalili, S.M. and Lewis, A. 2014. Grey Wolf Optimizer. Advances in Engineering Software 69, pp. 46–61, DOI: 10.1016/j.advengsoft.2013.12.007.
• [34] Mohandes at. al. 1998 – Mohandes, M., Rehman, S. and Halawani, T.O. 1998. Estimation of Global Solar Radiation Using Artificial Neural Networks. Renewable Energy 14(1–4), pp. 179–184, DOI: 10.1016/S0960-1481(98)00065-2.
• [35] Orlowska at. al. 2008 – Orlowska, K., Kamiński, T.M. and Szabat, K. 2008. Mechanical State Variable Estimation of Drive System with Elastic Coupling Using Optimised Feed-Forward Neural Networks. Bulletin of the Polish Academy of Sciences: Technical Sciences 56(3), pp. 239–246.
• [36] Osowski at. al. 2021 – Osowski, S., Sawicki, B. and Cichocki, A. 2021. Computational Intelligence in Engineering Practice. Bulletin of the Polish Academy of Sciences: Technical Sciences 69(3), pp. 1–5, DOI: 10.24425/bpasts.2021.137052.
• [37] Ozturk at. al. 2004 – Ozturk, H.K., Canyurt, O.E., Hepbasli, A. and Utlu, Z. 2004. Residential-Commercial Energy Input Estimation Based on Genetic Algorithm (GA) Approaches: An Application of Turkey. Energy and Buildings 36(2), pp. 175–183, DOI: 10.1016/j.enbuild.2003.11.001.
• [38] Palau at. al. 1999 – Palau, A., Velo, E. and Puigjaner, L. 1999. Use of Neural Networks and Expert Systems to Control a Gas/Solid Sorption Chilling Machine. International Journal of Refrigeration 22(1), pp. 59–66, DOI: 10.1016/S0140-7007(97)00046-7.
• [39] Pradan at. al. 2016 – Pradhan, M., Roy, P.K. and Pal, T. 2016. Grey Wolf Optimization Applied to Economic Load Dispatch Problems. International Journal of Electrical Power and Energy Systems 83, pp. 325–334, DOI: 10.1016/j.ijepes.2016.04.034.
• [40] Pradan at. al. 2018 – Pradhan, M., Roy, P.K. and Pal, T. 2018. Oppositional Based Grey Wolf Optimization Algorithm for Economic Dispatch Problem of Power System. Ain Shams Engineering Journal 9(4), pp. 2015–2025, DOI: 10.1016/j.asej.2016.08.023.
• [41] Rutkowski, L. 2008. Computational Intelligence: Methods and Techniques. Computational Intelligence: Methods and Techniques. 1st ed. Berlin: Springer Berlin Heidelberg, DOI: 10.1007/978-3-540-76288-1.
• [42] Sahoo, A. and Chandra, S. 2017. Multi-Objective Grey Wolf Optimizer for Improved Cervix Lesion Classification. Applied Soft Computing Journal 52, pp.64–80, DOI: 10.1016/j.asoc.2016.12.022.
• [43] Şeker, M. 2021. Long Term Electricity Load Forecasting Based on Regional Load Model Using Optimization Techniques: A Case Study. Energy Sources, Part A: Recovery, Utilization and Environmental Effects 44(2022), pp. 1–23, DOI: 10.1080/15567036.2021.1945170.
• [44] Sözen, A. and Arcaklioǧlu, E. 2007. Prospects for Future Projections of the Basic Energy Sources in Turkey. Energy Sources, Part B: Economics, Planning and Policy 2(2), pp. 183–201, DOI: 10.1080/15567240600813930.
• [45] “Statistical Review of World Energy” 2020.
• [46] “TİK(General Directorate of Turkish Coal), Coal Industry Report.” 2019. [Online] http://tki.gov.tr/depo/TKİ–2018 YILI KÖMÜR SEKTÖR RAPORU_guncel.pdf [Accessed: 2022-04-25].
• [47] Topcu, Y. I. and Ulengin, F. 2004. Energy for the Future: An Integrated Decision Aid for the Case of Turkey. Energy 29(1), pp. 137–154, DOI: 10.1016/S0360-5442(03)00160-9.
• [48] Tursun at. al. 2016 – Tursun, F., Cebeci, M.E., Tör, O.B., Şahin, A., Taşkin, H.G. and Güven, A.N. 2016. Determination of Zonal Power Demand S-Curves with GA Based on Top-to-Bottom and End-Use Approaches. 4th International Istanbul Smart Grid Congress and Fair, ICSG 2016, pp. 1–5, DOI: 10.1109/SGCF.2016.7492423.
• [49] Vlachogiannis, J.G. and Lee, K.Y. 2006. A Comparative Study on Particle Swarm Optimization for Optimal Steady-State Performance of Power Systems. IEEE Transactions on Power Systems 21(4), pp. 1718–1728, DOI: 10.1109/TPWRS.2006.883687.
• [50] Watkins, W.A. and Schevill, W.E. 1979. Aerial Observation of Feeding Behavior in Four Baleen Whales: Eubalaena Glacialis, Balaenoptera Borealis, Megaptera Novaeangliae, and Balaenoptera Physalus. Journal of Mammalogy 60(1), pp. 155–163, DOI: 10.2307/1379766.
• [51] Willis, H.L. 2005. Spatial Electric Load Forecasting [Book Review]. IEEE Computer Applications in Power 10, DOI: 10.1109/mcap.1997.582454.
• [52] Yang at. al. 2015 – Yang, C., Gao, W., Liu, N. and Song, C. 2015. Low-Discrepancy Sequence Initialized Particle Swarm Optimization Algorithm with High-Order Nonlinear Time-Varying Inertia Weight. Applied Soft Computing Journal 29, pp. 386–394, DOI: 10.1016/j.asoc.2015.01.004.
• [53] Yilmaz, A.O. and Uslu, T. 2007. The Role of Coal in Energy Production-Consumption and Sustainable Development of Turkey. Energy Policy 35(2), pp. 1117–1128, DOI: 10.1016/j.enpol.2006.02.008.
• [54] Zaki at. al. 2017 – Zaki, D., Ahmed A. and Rezk, H. 2017. Global MPPT Based on Flower Pollination and Differential Evolution Algorithms to Mitigate Partial Shading in Building Integrated PV System. Solar Energy 157, pp. 171–186, DOI: 10.1016/j.solener.2017.08.024.
• [55] Zhou at. al. 2009 – Zhou, J., Fang, R., Li, Y., Zhang, Y. and Peng, B. 2009. Parameter Optimization of Nonlinear Grey Bernoulli Model Using Particle Swarm Optimization. Applied Mathematics and Computation 207(2), pp. 292–299, DOI: 10.1016/j.amc.2008.10.045.
• [56] Zhu, J. 2015. Classic Economic Dispatch. Optimization of Power System Operation, pp. 91–144, DOI: 10.1002/9781118887004.ch4.