-

Abstract

The importance of power quality in Electrical systems increases with each passing day and has become an important criterion in energy system. The main factors affecting the quality of power are harmonics, flicker, transients, voltage sags (Sags), sudden voltage surges (Sweels). The harmonics causes resonance, sudden trips, loss and so on and this problems adversely affect the quality of power. In this study residential and industrial zones were examined. Different ways are used for the analysis and the estimation of the harmonics. In order to get an estimate of the value of

Keywords

• Power Distribution System, Artificial Neural Network, Harmonic ,Power Quality

GERÇEK ZAMANLI ENERJİ DAĞITIM SİSTEMLERİNİN YAPAY SİNİR AĞLARI KULLANILARAK MODELLENMESİ VE HARMONİK TAHMİNİ - REAL TIME POWER DISTRUBUTION SYSTEM MODELLING AND HARMONIC ESTIMATION USING NEURAL NETWORK

Abstract

GERÇEK ZAMANLI ENERJİ DAĞITIM SİSTEMLERİNİN YAPAY SİNİR AĞLARI KULLANILARAK MODELLENMESİ VE HARMONİK TAHMİNİ

Elektrik sistemlerinde önemli bir kriter olan güç kalitesi her geçen gün önemini artırmaktadır. Güçkalitesini etkileyen başlıca etkenler; harmonikler, kırpışma (flicker), geçici rejimler(transient), ani gerilimdüşmeleri(Sags), ani gerilim yükselmeleri(Sweels) olarak sayılabilir. Harmonikler, rezonans, ani açma, ani
gerilim değişimleri v.b. olaylar güç kalitesini olumsuz olarak etkilemektedir. Harmoniklerin analizi ve tahminedilmelerinde literatürde çeşitli yöntemler kullanılmaktadır. Yapılan çalışmada, Manisa ilindeki yerleşim yeri ve
sanayi bölgesinden ölçülen Toplam Akım Harmonik Distorsiyonu (THD1) değerleri kullanılarak, ilerde sistemdeoluşabilecek, THDA1 değerlerini tahmin edecek bir Yapay Sinir Ağı (YSA) modeli geliştirilmiştir. Verilerin bir
kısmı YSA modelini oluşturmada, kalan kısmı da modeli test için kullanılmıştır. YSA ile tahmin edilendeğerlerin gerçek THD1 değerlerine çok yakın olduğu görülmüştür. Bu model ilave yüklerle birlik oluşabilecek THD1
değerlerinin önceden tahmin edilmesine ve tasarlanacak filtre parametrelerinin belirlenmesinde faydalıolabilir.

REAL TIME POWER DISTRUBUTION SYSTEM MODELLING AND HARMONIC ESTIMATION USING NEURAL NETWORK

The importance of power quality in Electrical systems increases with each passing day and has become an important criterion in energy system. The main factors affecting the quality of power are harmonics, flicker, transients, voltage sags (Sags), sudden voltage surges (Sweels). The harmonics causes resonance, sudden trips, loss and so on and this problems adversely affect the quality of power. In this study THD1 values of residential and industrial zones were examined. Different ways are used for the analysis and the estimation of the harmonics. In order to get an estimate of the value of THD1 values Artificial Neural Networks were used. THD1 values were estimated with using this ANN model. With this method, accurate estimated values obtained. This estimated THD1 values can be used to selecting the required filter system. In this way, by reducing harmonic values, a significant improvement in power quality can be achieved. With the proposed ANN model, equipment that improve the power quality can be preselected while planning energy distribution systems. This model can be used for the planning the energy systems which has the high Power Quality. This ANN model can be used to estimate values in different systems .

Keywords

• -

References

1. V.E. Wagner et aI. , "Effects of harmonics on equipment," IEEE Trans. Power Del., vol. 8, no. 2, pp. 672-680, 1993.
2. R. Yacamini, "Power system harmonics: Part Problems caused by distorted supplies," Power Engineering Journal, vol. 9, no. 5, pp. 233-238, 19 J. Arrilliaga and N. R. Watson, Power System Harmonics.: John Wiley & Sons, 2003.
3. IEEE GUide for Harmonic Control and Reactive Compensation of Static Power Converters, ANSIIIEEE Std. 519-1981, 1981.
4. Requirements for Harmonic Control in Electrical Power Systems, IEEE Std. 519-1992, 1992. and Limits for Harmonic Current Emissions
5. (Equipment Input Current Less than i6 A Per Phase), IEC Std. 61000-3-2, 2005.
6. Limitation of Emission of Harmonic Currents in Low-Voltage Power Supply Systems for Equipment with Rated Current Greater than i 6 A, IEC Std. 61000-3-4, 1998.
7. U.Arumugam ,N.M. Nor,M.F. Abdullah "A Brief on Advances of Harmonic State Estimation Techniques in Power Systems.’’ International Journal of information and Electronics Engineering Vol.1,No.3,Nowember 2011
8. Sachin K. Jain and S. N. Singh, "Harmonics Estimation in Emerging Power System: Key Issues and Challenges," Electr. Power Syst. Res., vo1.81, pp. 1754-1766,2011.

9. HuaOuyang.Jialin Wang " Power System Transient Signal Analysis based on Prony Algorithm and neural network," IEEE PES ISGT ASIA 2012 1569605083
10. Wang Li,Wang Xiao-hua ,’’ Application Of Neural Network In Power System Inter_Harmonic Dedection ‘’ 978-0-7695-4360-4/10 2010 IEEE
11. Ibrahim El-Amin, Ihab Arafah ‘’ Artificial Neural Network for Power System _Harmonic Estimation’’ 0-7803-5105-3/98 1998 IEEE Sachin
12. ‘’Adaptive Wavelet Neural Network Based Harmonic Estimation Single –Phase Systems’’ 978- 1-4673-6008-1 2012 IEEE ,D.Saxena,S.N. Singh
13. Yalçınöz T. , Erdem S. , Eminoğlu U. , "Yapay sinir ağları ile Niğde Bölgesinin elektrik yük tahmini" Chen Ying,Lin Qingsheng "New Research on Harmonic Dedection Based Neural for Power System’’ 978-0-7695-3589-4/09 2009 IEEE
14. H. C. Lin, "Intelligent neural network-based Dynamic power system harmonic detection," 0- 7803-8610-8/04 2004 IEEE
15. Liu Qian-jin,Qin Si-shi, "A DFP- Neural Network Algorithm for Analysis of Power System Harmonics ’’ 978-1-4244-4813-5/10 2010 IEEE
16. Mario Oleskovicz,Marcelo A.A. Lima,Etienne Biassoto,Denis V. Coury ‘’ Estimation of Harmonic Currents Injected by Nonlinear Loads for a Distorted Power Supply Scenario Using Artificial Neural Networks’’ 978-1-1673-1943-0/12 2012 IEEE
17. Hsiung Cheng Lin, "Intelligent neural network-based fast power system harmonic detection," IEEE Trans. ind. Electron., vol. 54, no. 1, pp. 43-52, 2007. harmonikler’’, Brsen, 2.1-13,2003 C.‘’Elektrik tesislerinde
18. Hamzaçebi C.,’’Yapay Sinir Ağları’, Ekin, 4- 104, 2011
19. Makridakis S., Wheelwright,S.C.,Mc Gee,V., ’’Forecasting:Methods and applications’’ John Wiley & Sons, NY,3-476 1983.
20. Gonzales S.’’Neural Netorks for Forecasting:A Complemantry Approach to Linear Regression Methods ,Working Paper 2000-07, Canada, 26-33, 2000. Geliş Tarihi: 11.09.2014 Kabul Tarihi:23.12.2014