EN
TR
LONG-TERM ENERGY CONSUMPTION FORECAST OF TURKEY WITH SWARM INTELLIGENCE-BASED ALGORITHMS
Abstract
Energy is one of the most important tools of civilization countries. Growing population, level of prosperity and developing technology all over the world are among the factors that seriously increase energy consumption. Realization of energy production and consumption within framework of sustainable development has been one of the most important goals of our time. It is very important to make predict how much energy will be needed in Turkey coming years because of the energy used is exhaustible, these sources are foreign-dependent and due to environmental conditions. For obtain such an important prediction in study, swarm intelligence-based meta-heuristic algorithms Whale Optimization Algorithm (WOA) and Artificial Bee Colony Algorithm (ABC) was preferred. Data of variables are gross domestic product (GDP), population, import and export, between 1990-2009 were used for education and data between 2009-2019 were used for test. According to results of best model obtained, it was tried to determine amount of energy that Turkey may need by 2040 in four possible scenarios. According to the results, it can be observed that ABC model was given as better results from the WOA model by R^2 values as 86% meanwhile MAPE (Mean Absolute Percentage Error) values as 8,74% for the test data.
Keywords
References
- Akay, B. (2009). Nümerik optimizasyon problemlerinde yapay arı kolonisi algoritmasının performans analizi. Doktora Tezi. Erciyes Üniversitesi Fen Bilimleri Enstitüsü Bilgisayar Mühendisliği Ana Bilim Dalı, Kayseri 325s.
- Azadeh, A., Ghaderi, S.F., Tarverdian, S., Saberi, M. (2007). Integration of artificial neural networks and genetic algorithm to predict electrical energy consumption. Applied Mathematics and Computation, 186 (2) ,1731–1741. https://doi.org/10.1016/j.amc.2006.08.093
- Barth, F. G. (1982). Insects and Flowers: The biology of a partnership. Princeton, N.J.: Princeton University Press. Bayramoğlu, T., Pabucçu, H., Boz, F. (2017). Türkiye için anfis modeli ile birincil enerji talep tahmini. Ege Akademik Bakış, 17 (3), 431-446. https://doi.org/10.21121/eab.2017328408
- Behrang, M.A., Assareh, E., Assari, M.R., Ghanbarzadeh, A. (2010). Application of PSO (particle swarm optimization) and GA (genetic algorithm) techniques on demand estimation of oil in Iran. Energy, 35(12), 5223-5229. https://doi.org/10.1016/j.energy.2010.07.043
- Binici, M. (2019). Matematiksel modelleme kullanılarak Türkiye’nin enerji tüketim tahmini. Yüksek Lisans Tezi. Sivas Cumhuriyet Üniversitesi Fen Bilimleri Üniversitesi Makine Mühendisliği Ana Bilim Dalı, Sivas 59s.
- Doğan, C. (2019). Balina optimizasyon algoritması ve gri kurt optimizasyonu algoritmaları kullanılarak yeni hibrit optimizasyon algoritmalarının geliştirilmesi. Yüksek Lisans Tezi. Erciyes Üniversitesi Fen Bilimleri Üniversitesi Bilgisayar Mühendisliği Ana Bilim Dalı, Kayseri 69s.
- Durğun, S. (2018). Türkiye’nin enerji talebinin yapay zekâ teknikleriyle uzun dönem tahmini. Yüksek Lisans Tezi. Necmettin Erbakan Üniversitesi Fen Bilimleri Enstitüsü Enerji Sistemleri Mühendisliği Ana Bilim Dalı, Konya 62s.
- Ekinci, F. (2019). YSA ve ANFIS tekniklerine dayalı enerji tüketim tahmin yöntemlerinin karşılaştırılması. Düzce Üniversitesi Bilim ve Teknoloji Dergisi, 7(3), 1029 – 1044. https://doi.org/10.29130/dubited.485822
Details
Primary Language
Turkish
Subjects
Computer Software
Journal Section
Research Article
Publication Date
June 3, 2023
Submission Date
November 7, 2022
Acceptance Date
March 9, 2023
Published in Issue
Year 1970 Volume: 26 Number: 2
APA
Babaoğlu, M., & Haznedar, B. (2023). SÜRÜ ZEKÂSI TABANLI ALGORİTMALAR İLE TÜRKİYE’NİN UZUN VADELİ ENERJİ TÜKETİM TAHMİNİ. Kahramanmaraş Sütçü İmam Üniversitesi Mühendislik Bilimleri Dergisi, 26(2), 424-441. https://doi.org/10.17780/ksujes.1200583
Cited By
METEOROLOJİK VERİLER KULLANILARAK RÜZGÂR ENERJİSİ ÜRETİMİNİN FARKLI MAKİNE ÖĞRENMESİ YÖNTEMLERİ İLE TAHMİN EDİLMESİ
Kahramanmaraş Sütçü İmam Üniversitesi Mühendislik Bilimleri Dergisi
https://doi.org/10.17780/ksujes.1667861