Tashchilin V.A., Gubin P.Yu., Shakirov M.M. Review of Machine Learning Based on PMU Application in Terms of Power System Emergency Control

download PDF

Abstract

Wide penetration of phasor measurement systems in electrical power industry provides new opportunities in terms of bulk power systems control as well as distribution and microgrids. Possible applications of PMU are not limited to the state estimation problem and cover problems of transient conditions analysis. This fact lays the basis for further development of remedial action schemes, which use not only local measurements from an installation point, but also global ones, covering a part of a system or even the system totally. This review observes the existing approaches to integration of PMU to the following emergency control schemes and problems: automatic frequency load shedding, out-of-step conditions liquidation automation, islanding control, controlled emergency islanding automation, state and stability control schemes, identification and damping of electromechanical oscillations, identification, failure state classification and system conditions. It is shown that significant attention is being paid to different machine learning algorithms. There are two primary barriers to further development of remedial action schemes based on PMU. Firstly, it is assumed that there is information redundancy from measurement units. This does not completely correspond to the existing situation, because the number of installed units is still relatively small. Secondly, widely proposed machine learning algorithms still find very limited or almost no application in power system control because of general subjective attitude and difficulties connected with training process and lack of real PMU data for testing algorithms proposed. In particular, as it is shown in this work, real PMU data was used to implement and analyze the effectiveness of identification and classification of failure states procedure only.

Keywords

phasor measurement system, emergency control, automatic frequency load shedding, out-of-step conditions, liquidation automation, stability control scheme, machine learning, artificial neural networks.

Valeriy A. Tashchilin Ph.D. (Engineering), Leading Engineer, Associate Professor, Department of Automated Electrical Systems, Ural Power Engineering Institute, Ural Federal University, Yekaterinburg, Russia, This email address is being protected from spambots. You need JavaScript enabled to view it., https://orcid.org/0000-0001-8763-3705

Pavel Yu. Gubin Postgraduate Student, Teaching Assistant, Department of Automated Electrical Systems, Ural Power Engineering Institute, Ural Federal University, Yekaterinburg, Russia, This email address is being protected from spambots. You need JavaScript enabled to view it., https://orcid.org/0000-0002-3736-652X

Mikhail M. Shakirov Master’s Degree Student, Department of Automated Electrical Systems, Ural Power Engineering Institute, Ural Federal University, Yekaterinburg, Russia, This email address is being protected from spambots. You need JavaScript enabled to view it., https://orcid.org/0000-0002-8192-8112

  1. Mokeev A.V. PMU-based improvement of the reliability and efficiency of power systems. Elektrichestvo [Electricity], 2018, no. 4, pp. 4–10. doi: 10.24160/0013-5380-2018-3-4-10 (In Russian)
  2. Mokeev A.V., Bovykin V.N., Khromtsov E.I., Miklashevich A.V., Popov A.I., Rodionov A.V., Ulyanov D.N. Application of synchronized vector measurement technology for control, protection and automation. Releyshchik [Protection engineer], 2019, no. 3, pp. 32–37. (In Russian)
  3. Klimova T.G., Maksimov B.K. PMU devices: characteristics, testing and application. Releyshchik [Protection engineer], 2018, no. 2, pp. 32–39. (In Russian)
  4. Klimova T.G., Revyakin V.A. Possible directions for application of PMU devices in distribution grids. Elektroenergiya. Peredacha i raspredelenie [Electric power. Transmission and distribution], 2020, no. 6, pp. 110–115. (In Russian)
  5. Dusabimana E, Yoon S-G. A Survey on the Micro-Phasor Measurement Unit in Distribution Networks. Electronics. 2020. No. 9(2). 305. doi: 10.3390/electronics9020305
  6. Boussadia, F., Belkhiat, S. A new adaptive underfrequency load shedding scheme to improve frequency stability in electric power system. Journal Européen des Systèmes Automatisés. 2021, vol. 54(2), pp. 263-271. doi: 10.18280/jesa.540208
  7. Eissa M.M., Ali A.A., Abdel-Latif K., Al-Kady A.F. A frequency control technique based on decision tree concept by managing thermostatically controllable loads at smart grids. International Journal of Electrical Power & Energy Systems, 2019, vol. 108, pp. 40–51. doi: 10.1016/j.ijepes.2018.12.037
  8. Shekari T., Gholami A., Aminifar F., Sanaye-Pasand M. An Adaptive Wide-Area Load Shedding Incorporating Power System Real-Time Limitations. IEEE Systems Journal. 2018, vol. 12(1), pp. 759–767. doi: 10.1109/JSYST.2016.2535170
  9. Hong Q. A New Load Shedding Scheme with Consideration of Distributed Energy Resources’ Active Power Ramping Capability. IEEE Transactions on Power Systems. 2022, vol. 37(1), pp. 81–93. doi: 10.1109/TPWRS.2021.3090268
  10. Zhu Q. A Deep End-to-End Model for Transient Stability Assessment with PMU Data. IEEE Access, 2018, vol. 6, pp. 65474–65487. doi: 10.1109/ACCESS.2018.2872796
  11. ZhangY., ZhangS., WangJ.A power system out-of-step splitting control system based on wide area information and an online searching scheme of optimal splitting section // Interna-tional Journal of Electrical Power & Energy Systems, 2021, vol. 126, pp. 106587. doi:10.1016/j.ijepes.2020.106587
  12. Zhang S., Zhang Y. A Novel Out-of-Step Splitting Protection Based on the Wide Area Information. IEEE Transactions on Smart Grid, 2017, vol. 8, iss. 1, pp. 41–51. doi: 10.1109/TSG.2016.2593908
  13. Aghamohammadi M., Abedi M. DT based intelligent predictor for out of step condition of generator by using PMU data. International Journal of Electrical Power & Energy Systems. 2018. Vol. 99. Pp. 95–106. doi: 10.1016/j.ijepes.2018.01.001
  14. Ivankovi I., Kuzle I., Holjevac N. Wide Area Information-Based Transmission System Centralized Out-of-Step Protection Scheme. Energies, 2017, vol. 10(5), pp. 1-28. doi: 10.3390/en10050633
  15. Tealane M., Kilter J., Popov M., Bagleybter O., Klaar D. Online Detection of Out-of-Step Condition Using PMU-Determined System Impedances. IEEE Access, 2022, vol. 10, pp. 14807–14818. doi: 10.1109/ACCESS.2022.3149103
  16. Desai J.P., Makwana V.H. Phasor Measurement Unit Incorporated Adaptive Out-of-step Protection of Synchronous Generator. Journal of Modern Power Systems and Clean Energy, 2021, vol. 9(5), pp. 1032–1042. doi: 10.35833/MPCE.2020.000277
  17. Zare H., Alinejad-Beromi Y., Yaghobi H. Intelligent prediction of out-of-step condition on synchronous generators because of transient instability crisis. International Transactions on Electrical Energy Systems, 2018, vol. 29, p. 2686. doi: 10.1002/etep.2686
  18. Elkin S.V., Koloborodov E.N., Klimova T.G. PMU data application to choose out-of-step control system settings. Releynaya zashchita i avtomatizatsiya [Relay protection and automation], 2019, no. 2(35), pp. 28-31. (In Russian)
  19. Mahdi M., Genc V.M.I.A Real-Time Self-Healing Methodology Using Model- and Measurement-Based Islanding Algorithms. IEEE Transactions on Smart Grid, 2019, vol. 10(2), pp. 1195-1204. doi: 10.1109/TSG.2017.2760698
  20. Shukla A., Dutta S., Sadhu P.K. An island detection approach by μ-PMU with reduced chances of cyber-attack. International Journal of Electrical Power and Energy Systems, 2021, vol. 126(A), p. 106599. doi: 10.1016/j.ijepes.2020.106599
  21. Chatterjee S., Roy B. Bagged tree based anti-islanding scheme for multi-DG microgrids. Journal of Ambient Intelligence and Humanized Computing, 2021, vol. 12, pp. 2273-2284. doi: 10.1007/s12652-020-02324-0
  22. Tang Y., Li F., Zheng C., Wang Q., Wu Y. PMU Measure-ment-Based Intelligent Strategy for Power System Controlled Islanding. Energies, 2018, vol. 11, p. 143. doi: 10.1007/s12652-020-02324-0. doi: 10.3390/en11010143
  23. Gotman N.E., Shumilova G.P., Startseva T.B. PMU-based identification of the topology of an electrical network based on artificial neural networks using vector measurements. Metodicheskie voprosy issledovaniya nadezhnosti bolshikh sistem energetiki: aktualnye problemy nadezhnosti sistem energetiki: sbornik dokladov Mezhdunarodnyy nauchnyy seminar im. Yu.N. Rudenko [Methodological Issues of Researching the Reliability of Large Energy Systems: Actual Problems of Reliability of Energy Systems. Collection of Papers International Scientific Seminar named after V.I. Yu.N. Rudenko]. Minsk, Belarusian National Technical University Publ., 2015, pp. 251–257. (In Russian)
  24. Gotman N.E., Shumilova G.P. Neural network method for determining the topology of an electrical network in transient conditions. Izvestiya RAN. Energetika [Proceedings of the Russian Academy of Sciences. Energy], 2021, no. 1, pp. 92–100. doi: 10.31857/S0002331021010076 (In Russian)
  25. Vukolov V.Yu., Kulikov A.L., Trapeznikov I.F., Sharygin M.V. Development of algorithms for the configuration management system of distribution electrical networks for agricultural purposes. Vestnik NGIEI [Bulletin of NGIEI], 2017, no. 12, pp. 64–77. (In Russian)
  26. Meng Y., Yu Z., Lu N., Shi D. Time Series Classification for Locating Forced Oscillation Sources. IEEE Transactions on Smart Grid, 2021, vol. 12(2), pp. 1712–1721. doi: 10.1109/TSG.2020.3028188
  27. Baltas G., Lai N.-B., Tarraso A., Marin L., Blaabjerg F., Rodriguez P. AI-Based Damping of Electromechanical Oscillations by Using Grid-Connected Converter. Frontiers in Energy Research, 2021, vol. 9, p. 598436. doi: 10.3389/fenrg.2021.598436
  28. Mukherjee S., Chakrabortty A., Bai H., Darvishi A., Fardanesh B. Scalable Designs for Reinforcement Learning-Based Wide-Area Damping Control. IEEE Transactions on Smart Grid, 2021, vol. 12(3), pp. 2389–2401. doi: 10.1109/TSG.2021.3050419
  29. Abdulrahman I., Radman G. Wide-Area-Based Adaptive Neuro-Fuzzy SVC Controller for Damping Interarea Oscillations. Canadian Journal of Electrical and Computer Engineering, 2018, vol. 41(3), pp. 133–144. doi: 10.1109/CJECE.2018.2868754
  30. Mejia-Ruiz G.E., Cárdenas-Javier R., Paternina M.R.A., Rodríguez-Rodríguez J.R., Ramirez J.M., Zamora-Mendez A. Coordinated Optimal Volt/Var Control for Distribution Net-works via D-PMUs and EV Chargers by Exploiting the Eigensystem Realization. IEEE Transactions on Smart Grid, 2021, vol. 12(3), pp. 2425–2438. doi: 10.1109/TSG.2021.3050443
  31. Liu H., Su J., Yang Y., Qin Z., Li C. Compatible Decentral-ized Control of AVR and PSS for Improving Power System Stability. IEEE Systems Journal, 2021, vol. 15(2), pp. 2410–2419. doi: 10.1109/JSYST.2020.3001429
  32. Nikolaeva O.O., Klimova T.G. Identification of synchronous generator AVR parameters using neural networks and optimization algorithms. Releyshchik [Protection engineer], 2020, no. 2, pp. 16–23. (In Russian)
  33. Berdin A.S., Gerasimov A.S., Zakharov Yu.P., Kovalenko P.Yu., Moyseychenkov A.N. PMU-based evaluation of the participation of a synchronous generator in the damping of low-frequency oscillations. Vestnik Yuzhno-Uralskogo Gosudarstvennogo Universiteta. Energetika [Bulletin of the South Ural State University. Series “Power Engineering”], 2013, no. 2, pp. 62–68. (In Russian)
  34. Pierrou G., Wang X. An Online Network Model-Free Wide-Area Voltage Control Method Using PMUs. IEEE Transactions on Power Systems, 2021, vol. 36(5), pp. 4672–4682. doi: 10.1109/TPWRS.2021.3058642
  35. Huang Q., Huang R., Hao W., Tan J., Fan R., Huang Z. Adaptive Power System Emergency Control Using Deep Reinforcement Learning. IEEE Transactions on Smart Grid, 2020, vol. 11, iss. 2, pp. 1171–1182. doi: 10.1109/TSG.2019.2933191
  36. Bartolomey P.I., Semenenko S.I. Development of remedial action schemes algorithms based on PMU data. Effektivnoe i kachestvennoe snabzhenie i ispolzovanie elektroenergii: sbornik dokladov 4-y mezhdunarodnoy nauchno-prakticheskoy konferentsii v ramkakh vystavki «Energosberezhenie. Otoplenie. Ventilyatsiya. Vodosnabzhenie» [Materials of the 4th international conference "Effective high-quality electrical energy supply and distribution "]. Yekaterinburg, UMTs UPI Publ., 2015, pp. 38–41. (In Russian)
  37. Chusovitin P.V., Pazderin A.V. Power system stability monitoring based on dynamic equivalent determined from PMU data. Elektrichestvo [Electricity], 2013, no. 2, pp. 2–10. (In Russian)
  38. Batseva N.L., Foos Y.A. Increasing the accuracy of state estimation control actions determination in a centralized system of emergency automation. Vestnik Chuvashskogo Universiteta [Bulletin of the Chuvash University], 2021, no. 3, pp. 5–20. doi: 10.47026/1810-1909-2021-3-5-20 (In Russian)
  39. Aprosin K.I., Khokhrin A.A., Ivanov Y.V. PMU based estimation of control actions needed to avoid loss of stability in power system. Releyshchik [Protection engineer], 2021, no. 3, pp. 26–31. doi: 10.18503/2311-8318-2021-4(53)-4-12 (In Russian)
  40. Senyuk M.D., Dmitrieva A.A., Dmitriev S.A. Investigation of the characteristics of the method for express assessment of the parameters of the power system state in stationary and dynamic processes. Elektrotekhnicheskie sistemy i kompleksy [Electrotechnical Systems and Complexes], 2021, no. 4, pp. 4–12. doi: 10.18503/2311-8318-2022-2(55)-4-9 (In Russian)
  41. Senyuk M.D., Dmitrieva A.A. Approbation of the algorithm for transient stability analysis and emergency control of the mode of a synchronous generator on a multi-machine model of a power system. Elektrotekhnicheskie sistemy i kompleksy [Electrotechnical Systems and Complexes], 2022, no. 1, pp. 46–53. doi: 10.18503/2311-8318-2022-1(54)-46-53 (In Russian)
  42. Berdin A.S., Lisitsyn A.A., Moyseychenkov A.N., Senyuk M.D. Development of an PMU-based algorithm for automatic unloading of a power unit in case of close short circuits. Izvestiya NTTs edinoy energeticheskoy sistemy [Proceedings of the Scientific and Technical Center of the Unified Energy System], 2021, no. 2, pp. 76–89. (In Russian)
  43. Pavlovski M., Alqudah M., Dokic T., Hai A.A., Kezunovic M., Obradovic Z. Hierarchical Convolutional Neural Networks for Event Classification on PMU Measurements. IEEE Transactions on Instrumentation and Measurement, 2021, vol. 70, Pp. 1–13. doi: 10.1109/TIM.2021.3115583
  44. Hai A.A., Dokic T., Pavlovski M., Mohamed T., Saranov-ic D., Alqudah M., Kezunovic M., Obradovic Z. Transfer Learning for Event Detection From PMU Measurements With Scarce Labels. IEEE Access, 2021, vol. 9, pp. 127420–127432. doi: 10.1109/ACCESS.2021.3111727
  45. Shahsavari A., Farajollahi M., Stewart E.M., Cortez E., Mohsenian-Rad H. Situational Awareness in Distribution Grid Using Micro-PMU Data: A Machine Learning Ap-proach. IEEE Transactions on Smart Grid, 2019, vol. 10(6), pp. 6167-6177. doi: 10.1109/TSG.2019.2898676
  46. Shi J., Foggo B., Yu N. Power System Event Identification Based on Deep Neural Network with Information Loading. IEEE Transactions on Power Systems, 2021, vol. 36(6), pp. 5622-5632. doi: 10.1109/TPWRS.2021.3080279
  47. Duan N., Stewart E.M. Frequency Event Categorization in Power Distribution Systems Using Micro PMU Measurements// IEEE Transactions on Smart Grid, 2020, vol. 11(4), pp. 3043-3053. doi: 10.1109/TSG.2020.2967641
  48. Grando F.L., Lazzaretti A.E., Moreto M., Lopes H.S. Fault Classification in Power Distribution Systems using PMU Data and Machine Learning. 20th International Conference on Intelligent System Application to Power Systems (ISAP). IEEE, 2019, pp. 1–6. doi: 10.1109/ISAP48318.2019.9065966
  49. Ahmed A., Sajan K.S., Srivastava A., Wu Y. Anomaly Detection, Localization and Classification Using Drifting Synchrophasor Data Streams. IEEE Transactions on Smart Grid, 2021, vol. 12(4), pp. 3570-3580. doi: 10.1109/TSG.2021.3054375
  50. Shrivastava D., Siddiqui S., Verma K. A new synchronized data‐driven‐based comprehensive approach to enhance real‐time situational awareness of power system. International Transactions on Electrical Energy Systems, 2021, vol. 31. p. 12887. doi: 10.1002/2050-7038.12887
  51. Huang T., Freris N.M., Kumar P.R., Xie L. A Synchrophasor Data-Driven Method for Forced Oscillation Localization Under Resonance Conditions. IEEE Transactions on Power Systems, 2020, vol. 35(5), pp. 3927-3939. doi: 10.1109/TPWRS.2020.2982267
  52. Papadopoulos P. N., Papadopoulos T.A., Chrysochos A.I., Milanović J.V. Measurement Based Method for Online Characterization of Generator Dynamic Behaviour in Systems with Renewable Generation. IEEE Transactions on Power Systems, 2018, vol. 33(6), pp. 6466-6475. doi: 10.1109/TPWRS.2018.2830817
  53. Kim D.-I., Wang L., Shin Y.-J. Data Driven Method for Event Classification via Regional Segmentation of Power Systems. IEEE Access, 2020, vol. 8, pp. 48195–48204. doi: 10.1109/ACCESS.2020.2978518
  54. Li H., Ma Z., Weng Y. A Transfer Learning Framework for Power System Event Identification. IEEE Trans. on Power Systems, 2022, p. 9721668. doi: 10.1109/TPWRS.2022.3153445
  55. Lebedev A.A., Klimova T.G., Dubinin D.M. PMU-based identification of emergency situations in the electric power system according to the PMU data. Releyshchik [Protection engineer], 2019, no.1, pp. 10–16. (In Russian)
  56. Elizarova A.S., Zapasova I.S., Klimova T.G. PMU-based identification of emergency situations and abnormal modes. Releyshchik [Protection engineer], 2019, no. 3, pp. 44–51. (In Russian)

Tashchilin V.A., Gubin P.Yu., Shakirov M.M. Review of Machine Learning Based on PMU Application in Terms of Power System Emergency Control. Elektrotekhnicheskie sistemy i kompleksy [Electrotechnical Systems and Complexes], 2022, no. 3(56), pp. 12-27. (In Russian). https://doi.org/10.18503/2311-8318-2022-3(56)-12-27

Details
Hits: 351