Güç Sistemlerinde Harmoniklerin Yapay Zeka Destekli Kısa Dönemli Kestirimi

Abstract

Elektrik enerjisine olan ihtiyacın artması beraberinde daha verimli sistemlerin kullanımı gereksinimini ortaya çıkarmıştır. Teknolojinin ilerlemesiyle birlikte birçok alanda yarı iletken malzemelerin kullanılması, güç sistemlerinde doğrusal olmayan karakterli yüklerin artmasına neden olmuştur. Sözkonusu yüklerin güç sistemi üzerindeki bozucu etkileri filtreleme yolu ile giderilmekle birlikte, önceden bilinerek önlem alınması sistem işletme güvenliği açısından büyük fayda sağlayacaktır. Bu çalışmanın temel motivasyonu bu kapsam üzerine tesis edilmiştir. Çalışmada öncelikle bir veri seti oluşturulması amacıyla MATLAB/Simulink platformunda bir güç sistemi tasarlanmış, bu sistemde ortaya çıkan harmonik bozulmalar Hızlı Fourier Dönüşümü aracılığıyla tespit edilmiştir. Analiz vasıtasıyla oluşturulan veri seti, yapay sinir ağları modeli ile işlenmiştir. Elde edilen sonuçlar ve grafikler üzerinden sistemin başarımı incelenmiştir.

Keywords

• Harmonikler
• Güç Sistem Analizi
• Kısa Dönemli Kestirim
• Yapay Zekâ

Artificial Intelligence Based Short-Term Estimation of Harmonics in Power Systems

Abstract

The increasing demand for electrical energy has led to the need for more efficient systems. With the advancement of technology, the use of semiconductor materials in many areas has led to an increase in nonlinear loads in power systems. Although the disturbing effects of these loads on the power system can be eliminated by filtering, taking precautions by knowing in advance will be of great benefit in terms of system operational safety. The main motivation of this study is based on this scope. In the study, firstly, a power system is designed in MATLAB/Simulink platform in order to create a data set and the harmonic distortions occurring in this system are detected by means of Fast Fourier Transform. The data set generated by the analysis was processed with an artificial neural network model. The performance of the system is analyzed through the obtained results and graphs.

Keywords

• Harmonics
• Power System Analysis
• Short Term Estimation
• Artificial Intelligence

References

1. [1] J. Valenzuela and J. Pontt, “Real-time interharmonics detection and measurement based on FFT algorithm,” 2009 Applied Electronics International Conference, AE 2009, no. 1, pp. 259–264, 2009.
2. [2] N. Severoglu and O. Salor, “Statistical Models of EAF Harmonics Developed for Harmonic Estimation Directly from Waveform Samples Using Deep Learning Framework,” IEEE Trans Ind Appl, vol. 57, no. 6, pp. 6730–6740, 2021, doi: 10.1109/TIA.2021.3114127.
3. [3] N. Severoglu and O. Salor, “Amplitude and phase estimations of power system harmonics using deep learning framework,” IET Generation, Transmission and Distribution, vol. 14, no. 19, pp. 4089–4096, 2020, doi: 10.1049/iet-gtd.2019.1491.
4. [4] N. Mohan, K. P. Soman, and R. Vinayakumar, “Deep power: Deep learning architectures for power quality disturbances classification,” Proceedings of 2017 IEEE International Conference on Technological Advancements in Power and Energy: Exploring Energy Solutions for an Intelligent Power Grid, TAP Energy 2017, pp. 1–6, 2018, doi: 10.1109/TAPENERGY.2017.8397249.
5. [5] J. Ma, J. Zhang, L. Xiao, K. Chen, and J. Wu, “Classification of Power Quality Disturbances via Deep Learning,” IETE Technical Review (Institution of Electronics and Telecommunication Engineers, India), vol. 34, no. 4, pp. 408–415, 2017, doi: 10.1080/02564602.2016.1196620.
6. [6] S. Wang and H. Chen, “A novel deep learning method for the classification of power quality disturbances using deep convolutional neural network,” Appl Energy, vol. 235, no. September 2018, pp. 1126–1140, 2019, doi: 10.1016/j.apenergy.2018.09.160.
7. [7] E. M. Kuyunani, A. N. Hasan, and T. Shongwe, “Improving voltage harmonics forecasting at a wind farm using deep learning techniques,” in IEEE International Symposium on Industrial Electronics, Institute of Electrical and Electronics Engineers Inc., Jun. 2021. doi: 10.1109/ISIE45552.2021.9576357.
8. [8] J. Mazumdar, R. G. Harley, F. C. Lambert, and G. K. Venayagamoorthy, “Neural network based method for predicting nonlinear load harmonics,” IEEE Trans Power Electron, vol. 22, no. 3, pp. 1036–1045, May 2007, doi: 10.1109/TPEL.2007.897109.

9. [9] P. M. Ivry, O. A. Oke, D. W. P. Thomas, and M. Sumner, “Predicting Harmonic Distortion of Multiple Converters in a Power System,” Journal of Electrical and Computer Engineering, vol. 2017, 2017, doi: 10.1155/2017/7621413.
10. [10] Y. Dong et al., “Nonlinear Load Harmonic Prediction Method Based on Power Distribution Internet of Things,” Sci Program, vol. 2021, 2021, doi: 10.1155/2021/9978900.
11. [11] İ. Özer, S. B. Efe, and H. Özbay, “CNN / Bi-LSTM-based deep learning algorithm for classification of power quality disturbances by using spectrogram images,” International Transactions on Electrical Energy Systems, vol. 31, no. 12, pp. 1–16, 2021, doi: 10.1002/2050-7038.13204.
12. [12] E. M. Kuyumani, A. N. Hasan, and T. Shongwe, “A Hybrid Model Based on CNN-LSTM to Detect and Forecast Harmonics: A Case Study of an Eskom Substation in South Africa,” Electric Power Components and Systems, 2023, doi: 10.1080/15325008.2023.2181883.
13. [13] R. Cahuantzi, X. Chen, and S. Güttel, “A comparison of LSTM and GRU networks for learning symbolic sequences,” arXiv:2107.02248v3, Jul. 2021, [Online]. Available: http://arxiv.org/abs/2107.02248.
14. [14] P. T. Yamak, L. Yujian, and P. K. Gadosey, “A comparison between ARIMA, LSTM, and GRU for time series forecasting,” in ACM International Conference Proceeding Series, Association for Computing Machinery, Dec. 2019, pp. 49–55. doi: 10.1145/3377713.3377722.
15. [15] A. Y. Hatata and M. Eladawy, “Prediction of the true harmonic current contribution of nonlinear loads using NARX neural network,” Alexandria Engineering Journal, vol. 57, no. 3, pp. 1509–1518, Sep. 2018, doi: 10.1016/j.aej.2017.03.050.
16. [16] Y. Liu, H. Yang, and C. Ma, “A New Method For Estimation Of Harmonics And Inter-Harmonics,” in 2012 China International Conference on Electricity Distribution (CICED 2012), Shangai: IEEE, 2012, pp. 1–5.
17. [17] V. A. Katic and A. M. Stanisavljevic, “Smart Detection of Voltage Dips Using Voltage Harmonics Footprint,” IEEE Trans Ind Appl, vol. 54, no. 5, pp. 5331–5342, 2018, doi: 10.1109/TIA.2018.2819621.
18. [18] F. Tariq, R. Shareef, and T. Mahmood, “Investigating the Effect of Non-Linear Loads on Sizing of Voltage Source in Microgrid with Distributed Energy Resources,” in 2022 5th International Conference on Energy Conservation and Efficiency, ICECE 2022 - Proceedings, Institute of Electrical and Electronics Engineers Inc., 2022. doi: 10.1109/ICECE54634.2022.9758974.
19. [19] S. Chatterjee , S. Nigam , JB Singh , LN Upadhyaya “Software fault prediction using Nonlinear Autoregressive with eXogenous Inputs (NARX) network “App Intell , vol. 37 no. 1, pp. 121-129, 2012.
20. [20] XIE, H., TANG, H., & LIAO, Y. (2009). “Time Series Prediction Based On NARX Neural Networks: An Advanced Approach”. Proceedings of the Eighth International Conference on Machine Learning and Cybernetics, Baoding, 12-15 Haziran: 1275- 1279.
21. [21] S. Khaleghi , D. Karimi , SH Beheshti , MS Hosen , H. Behi , M. Berecibar , J. Van Mierlo “Online health diagnosis of lithium-ion batteries based on nonlinear autoregressive neural network” Applied Energy , vol. 282, 2021.