Powered by OpenAIRE graph
Found an issue? Give us feedback
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ YÖK Açık Bilim - CoH...arrow_drop_down
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
versions View all 2 versions
addClaim

Zaman serisi analizi ile yapay sinir ağları kestirimlerinin karşılaştırılması

Authors: Uslu, Seda;

Zaman serisi analizi ile yapay sinir ağları kestirimlerinin karşılaştırılması

Abstract

Elektrik enerjisi çoğunlukla depolanamayan ve üretildiğinde hemen tüketilmesi gereken bir enerji çeşididir. Büyük miktarlardaki elektrik enerjisinin depolanması mevcut koşullar altında mümkün değildir. Bu nedenle elektrik talebinin, elektrik arzı ile paralel bir şekilde gitmesi gerekmektedir. Elektrik enerjisi tüketimi yıllara, aylara, günlere ve saatlere göre değişiklik göstermektedir. Bu değişilenlikten dolayı elektrik talebini kestirmek ve talebi karşılayabilecek seviyede kapasiteyi belirlemek çok önemlidir. Elektrik enerjisinin talep planlamalarının yapılması, tüketici memnuniyetsizliklerine sebep olabilecek sorunların yaşanmasını büyük ölçüde engelleyecektir. Bu nedenle elektrik enerjisi tüketimi kestirimleri ne kadar doğru olursa ileriye yönelik planlamalar o kadar doğru olacaktır.Bu çalışmada, uzun dönemli Türkiye elektrik enerjisi tüketimi kestiriminde zaman serisi yöntemlerinden, ?Box-Jenkins? ve ?Yapay Sinir Ağları? yöntemlerinin kestirim başarılarını karşılaştırarak en yüksek başarıyı sağlayan yöntem belirlenmeye çalışılmıştır.Bu amaçla ilk olarak yıllara göre verilmiş olan Türkiye elektrik enerjisi tüketiminin kestirimi için çeşitli zaman serisi analizleri EVIEWS 5 ve MINITAB 15 programları yardımı ile yapılmış ve uygun görülen Otoregresif Model (AR) seçilerek bu model yardımıyla kestiririm yapılmıştır. İkinci olarak farklı yapay sinir ağları kullanılarak MATLAB R2008a programı yardımı ile denemeler yapılarak, uygun olan yapay sinir ağı modeli ile kestirimler yapılmıştır. Son olarak performans istatistikleri yardımı ile iki yöntem karşılaştırılmış ve uygun olan model seçilmiştir.

Electrical energy cannot be stored and should be consumed after production type of energy. Storage of electrical energy is not possible under certain circumstances. Therefore, the demand for electricity should go in parallel with the supply of electricity. Consumption of electrical energy differs monthly, daily or yearly. Because of this difference, to estimate the level of demand and to meet the supply capacity for this demand is very important. Demand planning of electrical energy would prevent the occurrence of customer dissatisfaction problems. Consequently, if the estimations of electrical energy consumption is more accurate, then futuristic long term plans will be more correct.In this study, the method that provides the highest success in the estimation of long-term electric energy consumption in Turkey is determined by comparing the ?Box-Jenkins? and ?Artificial Neural Networks? time series estimation methods.To this end, first, time series analysis of the estimation of yearly electrical energy consumption of Turkey is done by the help of EVIEWS 5 and MINITAB 15 programs and selection of an appropriate Auto-Regressive (AR) model. Second, using different neural networks and making comparisons by the help of MATLAB R2008a program, estimations are done with a suitable neural network model. Lastly, a suitable model is chosen by the comparison of two models with performance statistics method.

68

Country
Turkey
Keywords

Kestirim, Elektrik Tüketimi, Time series, Artificial neural networks, Electric consumption, İstatistik, Statistics, Yapay Sinir Ağları, Estimation, Zaman Serileri, Box-Jenkins

  • BIP!
    Impact byBIP!
    selected citations
    These citations are derived from selected sources.
    This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    0
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Average
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Average
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Average
Powered by OpenAIRE graph
Found an issue? Give us feedback
selected citations
These citations are derived from selected sources.
This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Citations provided by BIP!
popularity
This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
BIP!Popularity provided by BIP!
influence
This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Influence provided by BIP!
impulse
This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
BIP!Impulse provided by BIP!
0
Average
Average
Average
Green