NODAL LOAD MODELS IN THE PROBLEMS OF EVALUATING AND FORECASTING THE RISK OF EMERGENCY SITUATIONS IN ELECTRICAL ENERGY SYSTEMS
The conditions of operation of modern electric power systems (EES) with power plants of various types are analyzed. The need to increase the accuracy of forecasting the service life of electrical equipment and nodal load of power systems has been established. For the tasks of analyzing the risk of emergency situations in the UES in case of failures of electrical equipment, a software module for processing retrospective and operational information on the values of the node load has been created. An approach to the transformation of statistical probability distributions into fuzzy intervals is proposed, which makes it possible to use the obtained dependencies with different forms of representation of the initial information in probabilistic-statistical modeling of UES modes. A mathematical model of nodal load forecasting based on MGUA-like neural networks is built.
2. Review on Risk Assessment of Power System / Shiwen Y., Hui H., Chengzhi W., Hao G., Hao F. Procedia Computer Science. 2017. Vol. 109. P. 1200–1205.
3. Ciapessoni E., Cirio D., Gagleoti E. A probabilistic approach for operational risk assessment of power systems. CIGRE. 2008. P. 4–114.
4. Bardyk E., Bolotnyi N. Development of a model for determining a priority sequence of power transformers out of service. Eastern-European Journal of Enterprise Technologies. 2018. Vol. 3. Issue 8 (93). P. 6–15.
5. Artemchuk V. O., Bilan T. R., Blinov I. V., Martynyuk O. V., Miroshnyk V. O. etc. Theoretical and applied foundations of economic, ecological and technological functioning of energy facilities. Under the editorship A. O. Zaporizhia, T. R. Bilan. K. 2017. 312 p.
6. Chernenko P. O., Miroshnyk V. O. Short-term forecasting of the electrical load of the power supply company using an artificial neural network of deep learning. Proceedings of the Institute of Electrodynamics of the National Academy of Sciences of Ukraine. 2018. No. 50. P. 5–11.
7. The question of building fuzzy models for assessing the technical condition of objects of electrical systems: monogr. / M. V. Kosterev, E. I. Bardyk. K.: NTUU "KPI". 2011. 148 p.
8. H. H. Alhelou, M. Hamedani-Golshan, T. Njenda, and P. Siano, “A Survey on Power System Blackout and Cas-cading Events: Research Motivations and Challenges,” Energies. 2019. Vol. 12. No. 4. P. 1–28.
9. Reliability centered maintenance optimization for power distribution systems / Yssaad B., Khiat M., Chaker A. // International Journal of Electrical Power & Energy Systems. 2014. Vol. 55. P. 108–115.
10. Handschin E., Jurgens I., Neumann C. Long term optimization for risk-oriented asset management // 16th Power Systems Computation Conference. Glas-gow. 2008.
11. Bardyk Ye. I. Modelling and assessment of chances of failure of power systems electrical equipment taking into account the after repair resource restoration level // Visnyk of National Mining University. 2014. Issue 3. P. 82–90.
12. Diligensky N. V., Dymova L. G., Sevastyanov P. V. Fuzzy modeling and multicriteria optimization of production systems under uncertainty: technology, economics, ecology. M.: Mashinostroenie-1. 2004. 336 p.
13. Shtovba S. D. Designing fuzzy systems using MATLAB. – M.: Hot line. - Telecom, 2007. - 288 p.
14. S. A. V. Goerdin, J. J. Smit and R. P. Y. Mehairjan, “Monte Carlo simulation applied to support risk-based decision making in electricity distribution networks,” 2015 IEEE Eindhoven PowerTech, Eindhoven, Netherlands. 2015. P. 1–5. https://doi.org/10.1109/PTC.2015.7232494.
15. Bidyuk P. I. Analysis of time series / Bidyuk P. I., Romanenko V. D., Tymoshchuk O. L. - K.: Polytechnic, 2010. - 317 p.
16. A.D. Papalexopoulos, T.C. Hesterberg, ‘A Regression Based Approach to Short Term Load Forecasting’, IEEE Transactions on Power Systems. 1990. 5(1). P.40–45.
17. Bann D. W., Farmer E. D. Comparative models for predicting electrical load: Per. from English. M.: Energoatomizzdat. 1987. 200 p.
18. Osovsky S. Neural networks for information processing. M.: Finance and statistics. 2002. 344 p.
19. A. A. Desouky, M. M. Elkateb, ‘Hybrid adaptive tech-niques for electric-load forecast using ANN and ARI-MA’, IEE Proceedings of Generation, Transmission and Distribution. 2000. 147 (4). P. 213–217.
20. Bodyansky E.V. Artificial neural networks: architec-tures, learning, applications / E. V. Bodyansky, O. G. Rudenko. Kharkiv: TELETECH. 2004. 372 p.
21. Shumilova G. P., Gotman N. E., Startseva T. B. Short-term forecasting of electrical loads using artificial neural networks. Electricity. 1999. No. 10. P. 6–12.
22. Kushnarev F. A., Morkhov A. Yu., Nadtoka I. I. Forecast-ing of power consumption based on fuzzy sets // Izv. universities. Electromechanics. 1994. No. 6. P. 74
23. Brown M. Neural networks for modelling and control / Ed. by C. J.Harris“AdvancesIntelligent Control” / M. Brown, C. J. Harris. London: Taylor and Francis, 1994. P. 85–112.
24. A.G. Ivakhnenko Inductive methods of self-organization of models of complex systems/A.H. Ivakhnenko. Kyiv: Nauk. Dumka. 1982. 296 p.
25. Ivakhnenko A. G. Long-term forecasting and control of complex systems. Kyiv: Technique. 1975. 345 p.
26. Elattar E. E., Goulermas J. Y., Wu Q. H. Generalized Locally Weighted GMDH for Short Term Load Forecasting // Systems, Man, and Cybernetics, Part C: Applications and Reviews. 2012. 42. No. 3. P. 345–356. Pappas S., Ekonomou L. Comparison of Artificial Intelligence Metho
27. E. V. Mantula. A predictive neural network with a variable structure for monitoring environmental pollution indicators, Bionics of Intelligence. 2013. No. 1 (80). P. 112–116.
Abstract views: 26 PDF Downloads: 20