تخمین حد دینامیکی پایداری ولتاژ در سیستم‌های قدرت با استفاده از یادگیری ماشین

نوع مقاله : مقاله پژوهشی (کاربردی)

نویسندگان

1 عضو هیات علمی، گروه مهندسی برق، دانشگاه فنی و حرفه‌ای، تهران، ایران.

2 عضو هیات علمی، گروه مهندسی برق، موسسه آموزش عالی میثاق، رفسنجان، ایران.

چکیده

امروزه ناپایداری‌های مکرر ولتاژ در سیستم‌های قدرت مدرن، یک نگرانی برای بهره‌برداران سیستم‌های قدرت محسوب می‌شود. پایداری ولتاژ سیستم‌های قدرت را می‌توان با استفاده از تحلیل‌های استاتیکی و دینامیکی مطالعه کرد و براساس آن به مرزهای پایداری ولتاژ شامل مرزهای استاتیکی مانند بیشینه بارپذیری سیستم قدرت و مرزهای دینامیکی مانند نقاط دوشاخگی دست یافت. با این حال، امروزه با افزایش مصرف انرژی الکتریکی در سیستم‌های قدرت، بحث پیش‌بینی به‌هنگام پایداری ولتاژ، اهمیت چشمگیری پیدا کرده است. در این مقاله، با استفاده از شبکه عصبی چندلایه پرسپترون و ترکیب تحلیل‌های شبیه‌سازی حوزه زمان، تحلیل دوشاخگی و تحلیل مدال، حد دینامیکی پایداری ولتاژ براساس مرز انشعاب هاپف پیش‌بینی شده است. در این راستا به‌منظور افزایش دقت و سرعت آموزش و نیز آزمون شبکه عصبی در پیش‌بینی حد دینامیکی پایداری ولتاژ از یک روش انتخاب مؤلفه تحت عنوان تئوری اطلاعات متقابل استفاده شده است. الگوریتم ارائه‌شده بر سیستم آزمون 14 با سه استاندارد بررسی گردید و تأثیر انواع مدل‌های استاتیکی بارهای سیستم قدرت شامل بارهای توان ثابت، جریان ثابت و امپدانس ثابت بر قابلیت الگوریتم پیشنهادی بررسی شد. 

کلیدواژه‌ها

موضوعات


عنوان مقاله [English]

Estimating the Dynamic Margin of Voltage Stability in Power Systems Using Machine Learning

نویسندگان [English]

  • Mohammadali Alipour 1
  • Mohammadreza Jafari 2
1 Department of electrical engineering, Technical and Vocational University, Tehran, Iran.
2 Member Faculty, Department of Electrical Engineering, Misagh Higher Education Institute, Rafsanjan, Iran.
چکیده [English]

Frequent voltage instabilities in modern power systems are now a concern for power system operators. Voltage stability of power systems can be studied using static and dynamic analyses, based on which voltage stability margins including static boundaries such as maximum loadability and dynamic boundaries such as bifurcation points can be achieved.  However, today, with the increasing consumption of electrical energy in power systems, the discussion of voltage stability prediction has become significant. In this paper, using the multilayer neural network of perceptron and a combination of time-domain simulation analyzes, bifurcation analysis, and modal analysis, the dynamic margin of voltage stability based on the Hopf bifurcation boundary was predicted. In this regard, in order to increase the accuracy and speed of training and testing the neural network in predicting the dynamic margin of voltage stability, a feature selection method called mutual information theory was used. The proposed algorithm was investigated on a standard 14-bus test system; and the effect of various static models of power system loads including constant power loads, constant current, and constant impedance were examined.

کلیدواژه‌ها [English]

  • Dynamic margin of voltage stability
  • Prediction of voltage stability
  • Perceptron neural network
  • Feature selection method
  • Mutual Information
[1] Isaac, S., Adebola, S., Ayokunle, A., Katende, J., & Claudius, A. (2021). Voltage collapse prediction using artificial neural network. International Journal of Electrical and Computer Engineering, 11(1), 124-132. https://doi.org/10.11591/ijece.v11i1.pp124-132
[2] Alipour, M. (2017). Optimal allocation of SVC and TCSC in power system by means of fuzzy estimator with the approach of increasing the static stability of the voltage. Karafan Quarterly Scientific Journal, 14(2), 95-121. https://karafan.tvu.ac.ir/articl e_100507.html?lang=en
[3] Ibe, O. G., & Onyema, A. I. (2013). Concepts of reactive power control and voltage stability methods in power system network. International Organization Of Scientific Research Journal of Computer Engineering, 11(2), 15-25. https://doi.org/10.9790/0661-1121525
[4] Larik, R. M., Mustafa, M. W., & Panjwani, M. K. (2019). A statistical jacobian application for power system optimization of voltage stability. Indonesian Journal of Electrical Engineering and Computer Science, 13(1), 331-338. https://doi.org/10.11591/ijee cs.v13.i1.pp331-338
[5] Mobarak, Y. A. (2015). Voltage collapse prediction for Egyptian interconnected electrical grid EIEG. International Journal on Electrical Engineering and Informatics, 7(1), 79-88. https://doi.org/10.15676/ijeei.2015.7.1.6
[6] Saha, G., Chakraborty, K., & Das, P. (2018). Voltage Stability Prediction on Power Networks using Artificial Neural Networks. Indonesian Journal of Electrical Engineering and Computer Science, 10(1), 1-9. https://doi.org/10.11591/ijeecs.v10.i1.pp1-9
[7] Sridhar, J., & Prakash, R. (2019). Multi-objective whale optimization based minimization of loss, maximization of voltage stability considering cost of DG for optimal sizing and placement of DG. International Journal of Electrical and Computer Engineering 9(2), 835-839. https://doi.org/10.11591/ijece.v9i2.pp.835-839
[8] Zamani, M. K. M., Musirin, I., Mustaffa, S. A. S., & Suliman, S. I. (2019). Optimal SVC allocation via symbiotic organisms search for voltage security improvement. Telecommunication Computing Electronics and Control, 17(3), 1267-1274. https:/ /doi.org/10.12928/telkomnika.v17i3.9905
[9] Acevedo, L. F., Bothia-Vargas, G., & Candelo, J. E. (2018). Dynamic voltage stability comparison of thermal and wind power generation with different static and dynamic load models. International Journal of Electrical and Computer Engineering, 8(3), 1401-14011. https://doi.org/10.11591/ijece.v8i3.pp1401-1411
[10] Danish, M. S. S., Yona, A., & Senjyu, T. (2015). A review of voltage stability assessment techniques with an improved voltage stability indicator. International Journal of Emerging Electric Power Systems, 16(2), 107-115. https://doi.org/10.1515/ijeeps-2014-0167
[11] Lee, D. H. A. (2016). Voltage Stability Assessment Using Equivalent Nodal Analysis. IEEE Transactions on Power Systems, 31(1), 454-463. https://doi.org/10.1109/TP WRS.2015.2402436
[12] Pérez-Londoño, S., Rodríguez, L. F., & Olivar, G. (2014). A Simplified Voltage Stability Index (SVSI). International Journal of Electrical Power & Energy Systems, 63, 806-813. https://doi.org/10.1016/j.ijepes.2014.06.044
[13] Canizares, C. A. (2002). Voltage stability assessment: concepts, practices and tools. IEEE/PES power system stability subcommittee special publication,(SP101PSS). h ttps://scholar.google.ca/citations?view_op=view_citation&hl=en&user=NqIpnMkAAAAJ&citation_for_view=NqIpnMkAAAAJ:9yKSN-GCB0IC
[14] Nor, A. M., Sulaiman, M., Kadir, A. F. A., & Omar, R. (2016). Voltage instability analysis for electrical power system using voltage stabilty margin and modal analysis. Indonesian Journal of Electrical Engineering and Computer Science, 3(3), 655-662. https://doi.org /10.11591/ijeecs.v3.i3.pp655-662
[15] Amjady, N., & Velayati, M. H. (2009). Evaluation of the maximum loadability point of power systems considering the effect of static load models. Energy Conversion and Management, 50(12), 3202-3210. https://doi.org/10.1016/j.enconman.2009.08 .026
[16] Chen, H., Wang, Y., & Zhou, R. (2001). Transient and voltage stability enhancement via co-ordinated excitation and UPFC control. IEE Proceedings - Generation, Transmission and Distribution, 148(3), 201-208. https://doi.org/10.1049/ip-gtd:20 010189
[17]  Zhihong, F. (1992). The static voltage stability analysis methods for many generators power system–singularity decoupled method. Proceedings of CSEE, 12(3), 10-18.
[18] Jiang, T., Wan, K., & Feng, Z. (2019). Boundary-derivative direct method for computing saddle node bifurcation points in voltage stability analysis. International Journal of Electrical Power & Energy Systems, 112(3), 199-208. https://doi.org/10.1016/j.ijepes.2 019.04.039
[19] Neves, L. S., Alberto, L. F. C., & Chiang, H-D. (2020). A fast method for detecting limit-induced bifurcation in electric power systems. Electric Power Systems Research, 180, 106101. https://doi.org/10.1016/j.epsr.2019.106101
[20] Rao, S. D., Tylavsky, D. J., & Feng, Y. (2017). Estimating the saddle-node bifurcation point of static power systems using the holomorphic embedding method. International Journal of Electrical Power & Energy Systems, 84, 1-12. https://doi.org/10.1016/j.ijepes.2016.04. 045
[21] Roque, M. M., & Pessanha, J. E. O. (2020). Methodology for Voltage Stability Analysis Using Hopf Bifurcation and Continuation Power Flow Simulator. Electric Power Components and Systems, 48(12-13), 1211-1220. https://doi.org/10.1080/15325008. 2020.1854382
[22] Amroune, M., Bouktir, T., & Musirin, I. (2018). Power System Voltage Stability Assessment Using a Hybrid Approach Combining Dragonfly Optimization Algorithm and Support Vector Regression. Arabian Journal for Science and Engineering, 43(6), 3023-3036. https://doi.org/10.1007/s13369-017-3046-5
[23] Naganathan, G. S., & Babulal, C. K. (2019). Optimization of support vector machine parameters for voltage stability margin assessment in the deregulated power system. Soft Computing, 23(20), 10495-10507. https://doi.org/10.1007/s00500-018-3615-x
[24] Villa-Acevedo, W. M., López-Lezama, J. M., & Colomé, D. G. (2020). Voltage Stability Margin Index Estimation Using a Hybrid Kernel Extreme Learning Machine Approach. Energies, 13(4), 1-19. https://doi.org/10.3390/en13040857
[25] Sabri, M. (2017). Stabilization and control of the power system using meta-heuristic algorithms. Karafan Quarterly Scientific Journal, 14(2), 33-55. https://karafan.tvu. ac.ir/article_100504.html?lang=en
[26] Nizam, M., Mohamed, A., & Hussain, A. (2010). Dynamic voltage collapse prediction in power systems using support vector regression. Expert Systems with Applications, 37(5), 3730-3736. https://doi.org/10.1016/j.eswa.2009.11.052
[27] Zhou, D. Q., Annakkage, U. D., & Rajapakse, A. D. (2010). Online Monitoring of Voltage Stability Margin Using an Artificial Neural Network. IEEE Transactions on Power Systems, 25(3), 1566-1574. https://doi.org/10.1109/TPWRS.2009.2038059
[28] Kamalasadan, S., Thukaram, D., & Srivastava, A. K. (2009). A new intelligent algorithm for online voltage stability assessment and monitoring. International Journal of Electrical Power & Energy Systems, 31(2-3), 100-110. https://doi.org/10.1016/j.ijepes.2008. 10.011
[29] Sanchez, Z., González - Cueto Cruz, J., Sánchez, G., Hernandez Herrera, H., & Silva, J. (2020). Voltage collapse point evaluation considering the load dependence in a power system stability problem. International Journal of Electrical and Computer Engineering, 10(1), 61-71. https://doi.org/10.11591/ijece.v10i1.pp61-71
[30] Hanchuan, P., Fuhui, L., & Ding, C. (2005). Feature selection based on mutual information criteria of max-dependency, max-relevance, and min-redundancy. IEEE Transactions on Pattern Analysis and Machine Intelligence, 27(8), 1226-1238. https://doi.org/10.11 09/TPAMI.2005.159