TÜRKİYE’NİN ENERJİ TALEBİNİ TAHMİN ETMEK İÇİN TULUMLULAR SÜRÜ ALGORİTMASINA DAYALI BİR UYGULAMA

Tulumlular sürü algoritması (TSA), optimizasyon problemlerini çözmek için önerilmiş olan popülasyon tabanlı bir algoritmadır. Enerji talebinin tahmini, her ülke için oldukça önemli bir konudur. Çünkü bir ülkenin ekonomisi, enerji talebinden doğrudan etkilenmektedir. Bu nedenle, yapılan bu çalışmada, Türkiye’nin gelecekteki enerji talebini tahmin etmek için TSA tabanlı doğrusal bir yaklaşım önerilmektedir. Doğrusal modelin elde edilmesi aşamasında, bir ülkenin gayri safi yurtiçi hasıla, nüfus, ithalat ve ihracat verileri modelin giriş parametreleri olarak alınmıştır. Daha sonra bu parametrelerin optimum ağırlık katsayılarını bulmak amacıyla TSA algoritması kullanılmıştır. Önerilen modelin eğitim ve test aşaması için Türkiye'nin 1979-2011 arasındaki yıllara ait olan veri seti kullanılmıştır. Doğrusal model oluşturulduktan sonra, Türkiye’nin 2012’den 2030’a kadar olacak şekilde 20 yıllık bir süre için enerji talebi, üç farklı muhtemel senaryo için tahmin edilmiştir. Daha sonra ise önerilen model ile elde edilen deneysel sonuçlar, Türkiye’nin enerji talebini için literatürde önerilmiş olan diğer algoritmaların elde ettiği deneysel sonuçlar ile karşılaştırılmıştır. Deneysel sonuçlar ve karşılaştırmalar gösterdi ki, bu çalışma kapsamında önerilen model Türkiye’nin geleceğe dönük enerji talebini tahmin etmek için rekabetçi ve güvenilir sonuçlar elde etmiştir.

Anahtar Kelimeler:

Doğrusal model, enerji talebi, tahmin, tulumlular sürüsü algoritması

AN APPLICATION BASED ON THE TUNICATE SWARM ALGORITHM FOR PREDICTION THE ENERGY DEMAND OF TURKEY

The tunicate swarm algorithm (TSA) is a population-based swarm algorithm proposed for solving global optimization problems. The estimation of energy demand is a serious topic for policy makers. Because the economy of a country is directly affected by energy demand. On account of this, in this study we propose a TSA based linear approach for estimation the Turkey energy demand for future. Gross domestic product, population, import and export are taken as parameters for linear model. And then, TSA algorithm has used for find the optimum weight coefficients of these parameters. For training and testing phase of proposed model the data set of Turkey in 1979 to 2011 are used. After the model is created, the energy demand of Turkey for a 20-year period from 2012 to 2030 are estimated for different three scenarios. The obtained experimental result of proposed model has been compared with the state-of-art algorithms proposed for solving energy demand of Turkey in the literature. The experimental results and comparisons show that the proposed model is highly competitive and robust optimizer for estimation the energy demand of Turkey.

Keywords:

Energy demand, estimation, linear model, tunicate swarm algorithm,

PDF

___

[1] Bilgen S, Kaygusuz K, Sari A. Renewable energy for a clean and sustainable future. Energy sources, 26, 12 (2004), 1119-1129.
[2] Priddle R. World energy outlook 2002. International Energy Agency, IEA/OECD, Paris (2002).
[3] Ediger VŞ, Tatlıdil H. Forecasting the primary energy demand in Turkey and analysis of cyclic patterns. Energy Conversion and Management, 43, 4 (2002), 473-487.
[4] Häfele W. A Systems Approach to Energy: Handling large amounts of energy in a way that is safe, clean, cheap, and efficient is a more serious long-range problem than producing an adequate fuel supply. American Scientist, 62, 4 (1974), 438-447.
[5] Azadeh A, Saberi M, Ghaderi S, Gitiforouz A, Ebrahimipour V. Improved estimation of electricity demand function by integration of fuzzy system and data mining approach. Energy Conversion and Management, 49, 8 (2008), 2165-2177.
[6] Koc I, Kivrak H, Babaoglu I. The estimation of the energy demand in Turkey using grey wolf optimizer algorithm. Annals of the Faculty of Engineering Hunedoara, 17, 1 (2019), 113-117.
[7] Canyurt OE, Öztürk HK. Three different applications of genetic algorithm (GA) search techniques on oil demand estimation. Energy conversion and management, 47, 18-19 (2006), 3138-3148.
[8] Sonmez M, Akgüngör AP, Bektaş S. Estimating transportation energy demand in Turkey using the artificial bee colony algorithm. Energy, 122 (2017), 301-310.
[9] Pérez-Lombard L, Ortiz J, Pout C. A review on buildings energy consumption information. Energy and buildings, 40, 3 (2008), 394-398.
[10] Biçer A. Enerji Talep Tahminine Yönelik Program Geliştirme ve Bir Bölge için Uygulaması. Yüksek Lisans, 2018.
[11] Sadri A, Ardehali M, Amirnekooei K. General procedure for long-term energy-environmental planning for transportation sector of developing countries with limited data based on LEAP (long-range energy alternative planning) and EnergyPLAN. Energy, 77 (2014), 831-843.
[12] Erdogdu E. Electricity demand analysis using cointegration and ARIMA modelling: A case study of Turkey. Energy policy, 35, 2 (2007), 1129-1146.
[13] Koç İ, Nureddin R, Kahramanlı H. Türkiye'de enerji talebini tahmin etmek için doğrusal form kullanarak GSA (Yerçekimi Arama Algoritması) ve IWO (Yabani Ot Optimizasyon Algoritması) tekniklerinin uygulanması (2018).
[14] Dilaver Z, Hunt LC. Industrial electricity demand for Turkey: a structural time series analysis. Energy Economics, 33, 3 (2011), 426-436.
[15] Ediger VŞ, Akar S. ARIMA forecasting of primary energy demand by fuel in Turkey. Energy policy, 35, 3 (2007), 1701-1708
[16] Kankal M, Akpınar A, Kömürcü Mİ, Özşahin TŞ. Modeling and forecasting of Turkey’s energy consumption using socio-economic and demographic variables. Applied Energy, 88, 5 (2011), 1927-1939.
[17] Yumurtaci Z, Asmaz E. Electric energy demand of Turkey for the year 2050. Energy Sources, 26, 12 (2004), 1157-1164.
[18] ES H, KALENDER ÖKSÜZ F, Hamzacebi C. Forecasting the net energy demand of Turkey by artificial neural networks (2014).
[19] Beskirli M, Hakli H, Kodaz H. The energy demand estimation for Turkey using differential evolution algorithm. Sādhanā, 42, 10 (2017), 1705-1715.
[20] Ceylan H, Ozturk HK. Estimating energy demand of Turkey based on economic indicators using genetic algorithm approach. Energy Conversion and Management, 45, 15-16 (2004), 2525-2537.
[21] Gulcu S, Kodaz H. The estimation of the electricity energy demand using particle swarm optimization algorithm: A case study of Turkey. Procedia computer science, 111 (2017), 64-70.
[22] Kıran MS, Gündüz M. A recombination-based hybridization of particle swarm optimization and artificial bee colony algorithm for continuous optimization problems. Applied Soft Computing, 13, 4 (2013), 2188-2203.
[23] Kıran MS, Özceylan E, Gündüz M, Paksoy T. A novel hybrid approach based on particle swarm optimization and ant colony algorithm to forecast energy demand of Turkey. Energy conversion and management, 53, 1 (2012), 75-83.
[24] Kıran MS, Özceylan E, Gündüz M, Paksoy T. Swarm intelligence approaches to estimate electricity energy demand in Turkey. Knowledge-Based Systems, 36 (2012), 93-103.
[25] Özkış A. A new model based on vortex search algorithm for estimating energy demand of Turkey. Pamukkale University Journal of Engineering Sciences, 26, 5 (959-965.
[26] Toksarı MD. Ant colony optimization approach to estimate energy demand of Turkey. Energy Policy, 35, 8 (2007), 3984-3990.
[27] Toksarı MD. Estimating the net electricity energy generation and demand using the ant colony optimization approach: case of Turkey. Energy Policy, 37, 3 (2009), 1181-1187.
[28] Uguz H, Hakli H, Baykan ÖK. A new algorithm based on artificial bee colony algorithm for energy demand forecasting in Turkey. IEEE, City, 2015.
[29] Ünler A. Improvement of energy demand forecasts using swarm intelligence: The case of Turkey with projections to 2025. Energy policy, 36, 6 (2008), 1937-1944.
[30] Kaur S, Awasthi LK, Sangal A, Dhiman G. Tunicate swarm algorithm: a new bio-inspired based metaheuristic paradigm for global optimization. Engineering Applications of Artificial Intelligence, 90 (2020), 103541.
[31] Bulut YM, Yıldız Z. Comparing energy demand estimation using various statistical methods: the case of Turkey. Gazi University Journal of Science, 29, 2 (2016), 237-244.
[32] National Statistics http://www.tuik.gov.tr. City, 2016.
[33] Berrill J. The Tuniccafa. The Royal Society: London (1950).
[34] Fetouh T, Elsayed AM. Optimal control and operation of fully automated distribution networks using improved tunicate swarm intelligent algorithm. IEEE Access, 8 (2020), 129689-129708.
[35] Chander S, Vijaya P. Tunicate Swarm-Based Black Hole Entropic Fuzzy Clustering for Data Clustering using COVID Data. IEEE, City, 2020.