Improving the Recognition of Emergency Modesby Relay Protection Using Decision Tree Methods
Keywords:
short circuit recognition, machine learning, decision tree, random forest, gradient boosting, relay protection and automatic control devices, simulation, algorithm
Abstract
In the context of introducing modern active elements and devices into electrical networks (flexible power transmission lines, controlled shunt reactors, energy storage devices, distributed generation sources, etc.), conventional methods for recognizing emergency modes to secure correct operation of relay protection and automatic control devices (RPA) sometimes become ineffective. With the development and mass-scale application of the IEC 61850 standard, as well as simulation software systems, access to a large amount of information about the electrical network operation modes becomes available, which opens the possibility to develop fundamentally new algorithms for RPA, including those based on machine learning methods. The article explores a new approach to fault recognition in power lines with branches by simultaneously analyzing several information features and applying group machine learning algorithms: decision tree, random forest, and gradient boosting. To obtain training samples, simulation and the Monte Carlo method are used. The results of testing the studied methods have shown the required flexibility, the ability to use a large number of information parameters, as well as better results of fault recognition in comparison with the distance protection relay pickup device. The implementation of the decision tree algorithm for RPA microprocessor devices will not require hardware upgrades, but only involves refinement of special software.
References
1. Положение ПАО «Россети» «О единой технической политике в электросетевом комплексе» Приложение №4 к решению Совета директоров ПАО «МРСК Центра». Протокол от 25.05.2021 № 19/21.
2. Шарыгин М.В., Куликов А.Л. Статистические методы распознавания режимов в релейной защите и автоматике сетей электроснабжения. – Электрические станции, 2018, № 2 (1039), с. 32–39.
3. Лоскутов А.А., Митрович М., Осокин В.Ю. Повышение распознаваемости режимов функционирования системы электроснабжения на основе методов машинного обучения. – Релейная защита и автоматизация, 2020, № 4 (41), с. 26–34
4. Лоскутов А.А., Пелевин П.С., Митрович М. Разработка логической части интеллектуальной многопараметрической релейной защиты. – Электричество, 2020, № 5. с. 12–18.
5. Куликов А.Л., Лоскутов А.А., Совина А.Н. Использование машинного обучения и искусственных нейронных сетей для распознавания витковых замыканий в силовых трансформаторах. – Электричество, 2022, № 10, с. 34–44.
6. Рибейро П.Ф. и др. Обработка сигналов в интеллектуальных сетях энергосистем. М.: Техносфера, 2020, 496 с.
7. Rebizant W., Szafran J., Wiszniewski A. Digital Signal Processing in Power System Protection and Control. London: Springer, 2011, 316 p.
8. Hasan A.N., Pouabe P.S., Twala B. The Use of Machine Learning Techniques to Classify Power Transmission Line Fault Types and Locations. – International Conference on Optimization of Electrical and Electronic Equipment, 2017, pp. 221–226, DOI:10.1109/OPTIM.2017.7974974.
9. Witten I.H., Frank E. Data Mining: Practical Machine Learning Tools and Techniques. Amsterdam: Elsevier, 2005, 525 p.
10. Michie D., Spiegelhalter D., Taylor C. Machine Learning, Neural and Statistical Classification. Ellis Horwood, 1994, 290 p.
11. Bishop C.M. Pattern Recognition and Machine Learning. Berlin: Springer, 2006, 738 p.
12. Breiman L. et al. Classification and Regression Trees. New York: Routledge, 1984, 368 p.
13. Yongli Z., Limin H., Jinling L. Bayesian Networks-Based Approach for Power Systems Fault Diagnosis. – IEEE Transactions on Power Delivery, 2006, No. 21, pp. 636–369, DOI: 10.1109/TPWRD.2005.858774.
14. Ермаков С.М. Метод Монте-Карло в вычислительной математике. СПб., 2009, 192 c.
15. Шкаф дифференциальной защиты линии типа ШЭ2607 091. Руководство по эксплуатации. ЭКРА.656453.126 РЭ. Чебоксары: ООО НПП «ЭКРА», 2008.
16. Лямец Ю.Я. и др. Эффекты многомерности в релейной защите. – Электричество, 2011, № 9, с. 48–54.
17. Андреев В.А. Релейная защита и автоматика систем электроснабжения. М.: Высшая школа, 2006, 639 с.
18. Fawcett T. An Introduction to ROC Analysis. – Pattern Recognition Letters, 2006, No. 8, pp. 861–874, DOI:10.1016/j.patrec.2005.10.010.
19. Hastie T., Tibshirani R., Friedman J. The Elements of Statistical Learning. Berlin: Springer, 2001, 745 p.
20. Ширман Я.Д., Манжос В.Н. Теория и техника обработки радиолокационной информации на фоне помех. М.: Радио и связь, 1981, 416 с.
21. Kulikov A., Loskutov A., Bezdushniy D. Relay Protection and Automation Algorithms of Electrical Networks Based on Simulation and Machine Learning Methods. – Energies, 2022, vol. 15, No. 18, p. 6525, DOI:10.3390/en15186525.
22. Xia Y.Q., Li K.K., David A.K. Adaptive Relay Setting for Stand-Alone Digital Distance Protection. – IEEE Transactions on Power Delivery, 1994, vol. 9, No.1. pp. 480–491, DOI: 10.1109/61.277720.
23. Qi W., Swift G., McLaren P. Distance Protection Using an Artificial Neural Network. – Sixth International Conference on Developments in Power System Protection (Conf. Publ. No. 434). Nottingham, UK, 1997. pp. 286–290, DOI: 10.1049/cp:19970083.
24. Hutter F., Kotthoff L., Vanschoren J. Automated Machine Learning. Cham, Switzerland: Springer, 2019, 219 p.
25. Mueller A.S., Guido S. Introduction to Machine Learning with Python. Sebastopol, CA: O’Reilly, 2016, 338 p.
---
Исследование выполнено в рамках государственного задания в сфере научной деятельности (тема №FSWE-2022-0005)
#
1. Polozhenie PAO «Rosseti» «O edinoy tekhnicheskoy politike v elektrosetevom komplekse» Prilozhenie №4 k resheniyu Soveta direktorov PAO «MRSK TSentra». Protokol ot 25.05.2021 № 19/21 (The Regulation of PJSC ROSSETI "On the Unified Technical Policy in the Electric Grid Complex" Appendix No. 4 to the decision of the Board of Directors of PJSC IDGC of Centre. Protocol No. 19/21 dated 05/25/2021.).
2. Sharygin M.V., Kulikov A.L. Elektricheskie stantsii – in Russ. (Power Plants), 2018, No. 2 (1039), pp. 32–39.
3. Loskutov A.A., Mitrovich M., Osokin V.Yu. Releynaya zashchita i avtomatizatsiya – in Russ. (Relay Protection and Automation), 2020, No. 4 (41), pp. 26–34.
4. Loskutov A.A., Pelevin P.S., Mitrovich M. Elektrichestvo – in Russ. (Electricity), 2020, No. 5. pp. 12–18.
5. Kulikov A.L., Loskutov A.A., Sovina A.N. Elektrichestvo – in Russ. (Electricity), 2022, No. 10, pp. 34–44.
6. Ribeyro P.F. et al. Obrabotka signalov v intellektual'nyh setyah energosistem (Signal Processing in Intelligent Power Grid Networks). М.: Tekhnosfera, 2020, 496 p.
7. Rebizant W., Szafran J., Wiszniewski A. Digital Signal Processing in Power System Protection and Control. London: Springer, 2011, 316 p.
8. Hasan A.N., Pouabe P.S., Twala B. The Use of Machine Learning Techniques to Classify Power Transmission Line Fault Types and Locations. – International Conference on Optimization of Electrical and Electronic Equipment, 2017, pp. 221–226, DOI:10.1109/OPTIM.2017.7974974.
9. Witten I.H., Frank E. Data Mining: Practical Machine Learning Tools and Techniques. Amsterdam: Elsevier, 2005, 525 p.
10. Michie D., Spiegelhalter D., Taylor C. Machine Learning, Neural and Statistical Classification. Ellis Horwood, 1994, 290 p.
11. Bishop C.M. Pattern Recognition and Machine Learning. Berlin: Springer, 2006, 738 p.
12. Breiman L. et al. Classification and Regression Trees. New York: Routledge, 1984, 368 p.
13. Yongli Z., Limin H., Jinling L. Bayesian Networks-Based Approach for Power Systems Fault Diagnosis. – IEEE Transactions on Power Delivery, 2006, No. 21, pp. 636–369, DOI: 10.1109/TPWRD.2005.858774.
14. Ermakov S.M. Metod Monte-Karlo v vychislitel'noy matematike (Monte Carlo Method in Computational Mathematics). SPb., 2009, 192 p.
15. Shkaf differentsial'noy zashchity linii tipa SHE2607 091. Rukovodstvo po ekspluatatsii. EKRA.656453.126 RE (Differential Protection Cabinet of the Line Type ShE2607 091. Operating Manual. EKRA.656453.126 RE). Cheboksary: OOO NPP «EKRA», 2008.
16. Lyamets Yu.Ya. et al. Elektrichestvo – in Russ. (Electricity), 2011, No. 9, pp. 48–54.
17. Andreev V.А. Releynaya zashchita i avtomatika sistem elektrosnabzheniya (Relay Protection and Automation of Power Supply Systems). М.: Vysshaya shkola, 2006, 639 p.
18. Fawcett T. An Introduction to ROC Analysis. – Pattern Recognition Letters, 2006, No. 8, pp. 861–874, DOI:10.1016/j.patrec.2005.10.010.
19. Hastie T., Tibshirani R., Friedman J. The Elements of Statistical Learning. Berlin: Springer, 2001, 745 p.
20. Shirman Ya.D., Manzhos V.N. Teoriya i tekhnika obrabotki radiolokatsionnoy informatsii na fone pomekh (Theory and Technique of Radar Information Processing Against the Background of Interference). М.: Radio i svyaz', 1981, 416 p.
21. Kulikov A., Loskutov A., Bezdushniy D. Relay Protection and Automation Algorithms of Electrical Networks Based on Simulation and Machine Learning Methods. – Energies, 2022, vol. 15, No. 18, p. 6525, DOI:10.3390/en15186525.
22. Xia Y.Q., Li K.K., David A.K. Adaptive Relay Setting for Stand-Alone Digital Distance Protection. – IEEE Transactions on Power Delivery, 1994, vol. 9, No.1. pp. 480–491, DOI: 10.1109/61.277720.
23. Qi W., Swift G., McLaren P. Distance Protection Using an Artificial Neural Network. – Sixth International Conference on Developments in Power System Protection (Conf. Publ. No. 434). Nottingham, UK, 1997. pp. 286–290, DOI: 10.1049/cp:19970083.
24. Hutter F., Kotthoff L., Vanschoren J. Automated Machine Learning. Cham, Switzerland: Springer, 2019, 219 p.
25. Mueller A.S., Guido S. Introduction to Machine Learning with Python. Sebastopol, CA: O’Reilly, 2016, 338 p.
---
The research was carried out within the framework of the state assignment in the field of scientific activity (topic no. FSWE-2022-0005)
2. Шарыгин М.В., Куликов А.Л. Статистические методы распознавания режимов в релейной защите и автоматике сетей электроснабжения. – Электрические станции, 2018, № 2 (1039), с. 32–39.
3. Лоскутов А.А., Митрович М., Осокин В.Ю. Повышение распознаваемости режимов функционирования системы электроснабжения на основе методов машинного обучения. – Релейная защита и автоматизация, 2020, № 4 (41), с. 26–34
4. Лоскутов А.А., Пелевин П.С., Митрович М. Разработка логической части интеллектуальной многопараметрической релейной защиты. – Электричество, 2020, № 5. с. 12–18.
5. Куликов А.Л., Лоскутов А.А., Совина А.Н. Использование машинного обучения и искусственных нейронных сетей для распознавания витковых замыканий в силовых трансформаторах. – Электричество, 2022, № 10, с. 34–44.
6. Рибейро П.Ф. и др. Обработка сигналов в интеллектуальных сетях энергосистем. М.: Техносфера, 2020, 496 с.
7. Rebizant W., Szafran J., Wiszniewski A. Digital Signal Processing in Power System Protection and Control. London: Springer, 2011, 316 p.
8. Hasan A.N., Pouabe P.S., Twala B. The Use of Machine Learning Techniques to Classify Power Transmission Line Fault Types and Locations. – International Conference on Optimization of Electrical and Electronic Equipment, 2017, pp. 221–226, DOI:10.1109/OPTIM.2017.7974974.
9. Witten I.H., Frank E. Data Mining: Practical Machine Learning Tools and Techniques. Amsterdam: Elsevier, 2005, 525 p.
10. Michie D., Spiegelhalter D., Taylor C. Machine Learning, Neural and Statistical Classification. Ellis Horwood, 1994, 290 p.
11. Bishop C.M. Pattern Recognition and Machine Learning. Berlin: Springer, 2006, 738 p.
12. Breiman L. et al. Classification and Regression Trees. New York: Routledge, 1984, 368 p.
13. Yongli Z., Limin H., Jinling L. Bayesian Networks-Based Approach for Power Systems Fault Diagnosis. – IEEE Transactions on Power Delivery, 2006, No. 21, pp. 636–369, DOI: 10.1109/TPWRD.2005.858774.
14. Ермаков С.М. Метод Монте-Карло в вычислительной математике. СПб., 2009, 192 c.
15. Шкаф дифференциальной защиты линии типа ШЭ2607 091. Руководство по эксплуатации. ЭКРА.656453.126 РЭ. Чебоксары: ООО НПП «ЭКРА», 2008.
16. Лямец Ю.Я. и др. Эффекты многомерности в релейной защите. – Электричество, 2011, № 9, с. 48–54.
17. Андреев В.А. Релейная защита и автоматика систем электроснабжения. М.: Высшая школа, 2006, 639 с.
18. Fawcett T. An Introduction to ROC Analysis. – Pattern Recognition Letters, 2006, No. 8, pp. 861–874, DOI:10.1016/j.patrec.2005.10.010.
19. Hastie T., Tibshirani R., Friedman J. The Elements of Statistical Learning. Berlin: Springer, 2001, 745 p.
20. Ширман Я.Д., Манжос В.Н. Теория и техника обработки радиолокационной информации на фоне помех. М.: Радио и связь, 1981, 416 с.
21. Kulikov A., Loskutov A., Bezdushniy D. Relay Protection and Automation Algorithms of Electrical Networks Based on Simulation and Machine Learning Methods. – Energies, 2022, vol. 15, No. 18, p. 6525, DOI:10.3390/en15186525.
22. Xia Y.Q., Li K.K., David A.K. Adaptive Relay Setting for Stand-Alone Digital Distance Protection. – IEEE Transactions on Power Delivery, 1994, vol. 9, No.1. pp. 480–491, DOI: 10.1109/61.277720.
23. Qi W., Swift G., McLaren P. Distance Protection Using an Artificial Neural Network. – Sixth International Conference on Developments in Power System Protection (Conf. Publ. No. 434). Nottingham, UK, 1997. pp. 286–290, DOI: 10.1049/cp:19970083.
24. Hutter F., Kotthoff L., Vanschoren J. Automated Machine Learning. Cham, Switzerland: Springer, 2019, 219 p.
25. Mueller A.S., Guido S. Introduction to Machine Learning with Python. Sebastopol, CA: O’Reilly, 2016, 338 p.
---
Исследование выполнено в рамках государственного задания в сфере научной деятельности (тема №FSWE-2022-0005)
#
1. Polozhenie PAO «Rosseti» «O edinoy tekhnicheskoy politike v elektrosetevom komplekse» Prilozhenie №4 k resheniyu Soveta direktorov PAO «MRSK TSentra». Protokol ot 25.05.2021 № 19/21 (The Regulation of PJSC ROSSETI "On the Unified Technical Policy in the Electric Grid Complex" Appendix No. 4 to the decision of the Board of Directors of PJSC IDGC of Centre. Protocol No. 19/21 dated 05/25/2021.).
2. Sharygin M.V., Kulikov A.L. Elektricheskie stantsii – in Russ. (Power Plants), 2018, No. 2 (1039), pp. 32–39.
3. Loskutov A.A., Mitrovich M., Osokin V.Yu. Releynaya zashchita i avtomatizatsiya – in Russ. (Relay Protection and Automation), 2020, No. 4 (41), pp. 26–34.
4. Loskutov A.A., Pelevin P.S., Mitrovich M. Elektrichestvo – in Russ. (Electricity), 2020, No. 5. pp. 12–18.
5. Kulikov A.L., Loskutov A.A., Sovina A.N. Elektrichestvo – in Russ. (Electricity), 2022, No. 10, pp. 34–44.
6. Ribeyro P.F. et al. Obrabotka signalov v intellektual'nyh setyah energosistem (Signal Processing in Intelligent Power Grid Networks). М.: Tekhnosfera, 2020, 496 p.
7. Rebizant W., Szafran J., Wiszniewski A. Digital Signal Processing in Power System Protection and Control. London: Springer, 2011, 316 p.
8. Hasan A.N., Pouabe P.S., Twala B. The Use of Machine Learning Techniques to Classify Power Transmission Line Fault Types and Locations. – International Conference on Optimization of Electrical and Electronic Equipment, 2017, pp. 221–226, DOI:10.1109/OPTIM.2017.7974974.
9. Witten I.H., Frank E. Data Mining: Practical Machine Learning Tools and Techniques. Amsterdam: Elsevier, 2005, 525 p.
10. Michie D., Spiegelhalter D., Taylor C. Machine Learning, Neural and Statistical Classification. Ellis Horwood, 1994, 290 p.
11. Bishop C.M. Pattern Recognition and Machine Learning. Berlin: Springer, 2006, 738 p.
12. Breiman L. et al. Classification and Regression Trees. New York: Routledge, 1984, 368 p.
13. Yongli Z., Limin H., Jinling L. Bayesian Networks-Based Approach for Power Systems Fault Diagnosis. – IEEE Transactions on Power Delivery, 2006, No. 21, pp. 636–369, DOI: 10.1109/TPWRD.2005.858774.
14. Ermakov S.M. Metod Monte-Karlo v vychislitel'noy matematike (Monte Carlo Method in Computational Mathematics). SPb., 2009, 192 p.
15. Shkaf differentsial'noy zashchity linii tipa SHE2607 091. Rukovodstvo po ekspluatatsii. EKRA.656453.126 RE (Differential Protection Cabinet of the Line Type ShE2607 091. Operating Manual. EKRA.656453.126 RE). Cheboksary: OOO NPP «EKRA», 2008.
16. Lyamets Yu.Ya. et al. Elektrichestvo – in Russ. (Electricity), 2011, No. 9, pp. 48–54.
17. Andreev V.А. Releynaya zashchita i avtomatika sistem elektrosnabzheniya (Relay Protection and Automation of Power Supply Systems). М.: Vysshaya shkola, 2006, 639 p.
18. Fawcett T. An Introduction to ROC Analysis. – Pattern Recognition Letters, 2006, No. 8, pp. 861–874, DOI:10.1016/j.patrec.2005.10.010.
19. Hastie T., Tibshirani R., Friedman J. The Elements of Statistical Learning. Berlin: Springer, 2001, 745 p.
20. Shirman Ya.D., Manzhos V.N. Teoriya i tekhnika obrabotki radiolokatsionnoy informatsii na fone pomekh (Theory and Technique of Radar Information Processing Against the Background of Interference). М.: Radio i svyaz', 1981, 416 p.
21. Kulikov A., Loskutov A., Bezdushniy D. Relay Protection and Automation Algorithms of Electrical Networks Based on Simulation and Machine Learning Methods. – Energies, 2022, vol. 15, No. 18, p. 6525, DOI:10.3390/en15186525.
22. Xia Y.Q., Li K.K., David A.K. Adaptive Relay Setting for Stand-Alone Digital Distance Protection. – IEEE Transactions on Power Delivery, 1994, vol. 9, No.1. pp. 480–491, DOI: 10.1109/61.277720.
23. Qi W., Swift G., McLaren P. Distance Protection Using an Artificial Neural Network. – Sixth International Conference on Developments in Power System Protection (Conf. Publ. No. 434). Nottingham, UK, 1997. pp. 286–290, DOI: 10.1049/cp:19970083.
24. Hutter F., Kotthoff L., Vanschoren J. Automated Machine Learning. Cham, Switzerland: Springer, 2019, 219 p.
25. Mueller A.S., Guido S. Introduction to Machine Learning with Python. Sebastopol, CA: O’Reilly, 2016, 338 p.
---
The research was carried out within the framework of the state assignment in the field of scientific activity (topic no. FSWE-2022-0005)
Published
2023-05-25
Issue
Section
Article
