Based on the comparison presented in Table 1, it can be concluded that the integration of analytical method and traditional DT model enhances the performance of both methods. Specifically, the proposed method has achieved a 24.7% improvement in the accuracy of the traditional DT method and a 20.1% improvement in the accuracy of the improved DT method, as demonstrated by the MAE index. On the one hand, overvoltage peak values calculated by theoretical analysis method are adopted as the input features for the DT-based error correction part. On the other hand, considering the advantages of DT model in mapping relationship revealing, the error of the analytical method caused by model simplification can be reduced by the data-driven error correction part. The integration of model-driven method helps enhance the robustness of the integrated method to insufficient training sample and the inappropriate input feature selection.

Conclusion

This paper proposes an improved DT-based overvoltage level prediction method integrating the model-driven scheme for hybrid AC/DC power grids. A main factor that directly affects the performance of overvoltage analysis method is the adaptability to operational scenarios. To address the above key issue, an improved DT algorithm is proposed to predict the overvoltage level considering the advantages in mapping relationship revealing, and the prediction accuracy in high-risk scenarios is enhanced by modifying the splitting rules in the DT training process. In addition, a theoretical analysis method for evaluating the overvoltage peak value of converter buses is proposed with an acceptable calculation accuracy and the potential for online application, and the mathematical relationship between the reactive power consumed by the rectifier and AC voltage is derived. On this basis, an overvoltage analysis method integrating the model-driven and data-driven techniques is proposed to enhance the robustness to insufficient training sample and inappropriate input feature selection, and the DT algorithm is adopted to reveal the association pattern between theoretical analysis results and true values, improving the interpretability of regression prediction results. Simulations on a simplified hybrid AC/DC actual power grid have been performed to verify the effectiveness of improved integrated method.
Ongoing research is focused on the extraction of input features for the DT-based integrated method. As described in section 3, the input features of DT model are comprised of the power system operation information and voltage dynamic characteristic information. However, as power grid scale expands and operation complexity increases, the original input features may contain redundant information, which can affect the model training time and evaluation accuracy. Consequently, feature dimensionality reduction technology, such as feature selection or transformation, should be adopted to obtain more expressive new features, thereby improving the model training speed and the evaluation accuracy.

Acknowledgments

This work was supported by the National Key R&D Program of China (No. 2021YFB2400800). The authors are with State Key Laboratory of Electrical Insulation and Power Equipment, and school of Electrical Engineering, Xi’an Jiaotong University, Xi’an 710049, Shaanxi Province, China.

References

  1. Yamashita, K., Tsukamoto, G., Nishikata, S.: ’Steady-state characteristics of a line-commutated converter-based high-voltage direct current transmission system for series-connected wind power plants’. IEEE Trans. Ind. Appl., 2020, 56, (4), pp. 3932–3939.
  2. Xue, Y., Zhang, X., Yang. C.: ’Commutation failure elimination of LCC HVDC systems using thyristor-based controllable capacitors’. IEEE Trans. Power Del., 2018, 33, (3), pp. 1448–1458.
  3. Gu, M., Meegahapola, L., Wong, K. L.: ’Coordinated voltage and frequency control in hybrid AC/MT-HVDC power grids for stability improvement’. IEEE Trans. Power Syst., 2021, 36, (1), pp. 635-647.
  4. Dong, X., Guan, E., Jing, L., et al.: ’Simulation and analysis of cascading faults in hybrid AC/DC power grids’. Int. J. Elect. Power Energy Syst., 2020, 115, pp. 105492.
  5. Zhu, Y., Zhang, S., Liu, D., et al.: ’Prevention and mitigation of high-voltage direct current commutation failures: a review and future directions’. IET Gener. Transm. Distrib., 2019, 13: 5449-5456.
  6. Xie, Q., Zheng, Z., Wang, Y., et al.: ’Analysis of transient voltage disturbances in LCC-HVDC sending systems caused by commutation failures’. IEEE Trans. Power Del., 2022, 37, (5), pp. 4370-4381.
  7. Zheng, Z., Ren, J., Xiao, X., et al.: ’Response mechanism of DFIG to transient voltage disturbance under commutation failure of LCC-HVDC system’. IEEE Trans. Power Del., 2020, 35, (6), pp. 2972-2979.
  8. Zhang, T., Yao, J., Sun, P., et al.: ’Improved continuous fault ride through control strategy of DFIG-based wind turbine during commutation failure in the LCC-HVDC transmission system’. IEEE Trans. Power Electron., 2021, 36, (1), pp. 459-473.
  9. Mirsaeidi, S., Dong, X.: ’An integrated control and protection scheme to inhibit blackouts caused by cascading fault in large-scale hybrid AC/DC power grids’. IEEE Trans. Power Electron., 2019, 34, (8), pp. 7278-7291.
  10. Yin, C., Li, F.: ’Reactive power control strategy for inhibiting transient overvoltage caused by commutation failure’. IEEE Trans. Power Syst., 2021, 36, (5), pp. 4764-4777.
  11. Zhang, T., Yao, J., Sun P., et al.: ’Improved continuous fault ride through control strategy of DFIG-based wind turbine during commutation failure in the LCCHVDC transmission system’. IEEE Trans. Power Electr ., 2021, 36, (1), pp. 459-473.
  12. Guo, C., Zhang, Y., Gole, A. M., et al.: ’Analysis of dual-infeed HVDC with LCC–HVDC and VSC–HVDC’. IEEE Trans. Power Del., 2012, 27, (3), pp. 1529-1537.
  13. Zheng, Z., Ren, J., Xiao, X., et al.: ’Response mechanism of DFIG to transient voltage disturbance under commutation failure of LCC-HVDC system’. IEEE Trans. Power Del., 2020, 35, (6), pp. 2972-2979.
  14. Wang, F., Liu, T., Ding Y., et al.: ’Calculation method and influencing factors of transient overvoltage caused by HVDC block’. Power Syst. Technol., 2016, 40, (10), pp. 3059-3065.
  15. He, J., Tang, Y., Zhang J., et al.: ’Fast calculation of power oscillation peak value on AC tie-line after HVDC commutation failure’. IEEE Trans. Power Syst., 2015, 30, (4), pp. 2194-2195.
  16. Li, H., Qin, B., Jiang Y., et al.: ’Data-driven optimal scheduling for underground space based integrated hydrogen energy system’. IET Renew. Power Gener., 2022, 16, (12), pp. 2521-2531.
  17. Lagos, D. T., Hatziargyriou N. D.: ’Data-driven frequency dynamic unit commitment for island systems with high res penetration’. IEEE Trans. Power Syst., 2021, 36, (5), pp. 4699-4711.
  18. Cremer, J. L., Konstantelos, I., Tindemans, S. H., et al.: ’Data-driven power system operation: Exploring the balance between cost and risk’. IEEE Trans. Power Syst., 2019, 34, (1), pp. 791-801.
  19. Chen, H., Assala, P. D. S., Cai, Y., et al.: ’Intelligent Transient Overvoltages Location in Distribution Systems Using Wavelet Packet Decomposition and General Regression Neural Networks’. IEEE Trans. Ind. Informat., 2016, 12, (5), pp. 1726-1735.
  20. Tang, W., Gu, Y., Xin, Y., et al.: ’Classification for Transient Overvoltages in Offshore Wind Farms Based on Sparse Decomposition’. IEEE Trans. Power Del., 2022, 37, (3), pp. 1974-1985.
  21. Wang, B., Fang, B., Wang, Y., et al.: ’Power system transient stability assessment based on big data and the core vector machine’. IEEE Trans. Smart Grid, 2016, 7, (5), pp. 2561-2570.
  22. Li, B., Wu, J., Hao, L., et al. ’Anti-Jitter and refined power system transient stability assessment based on long-short term memory network’. IEEE Access, 2020, 8, pp. 35231-35244.
  23. Tan, B., Yang, J., Tang, Y., et al.: ’A deep imbalanced learning framework for transient stability assessment of power system’. IEEE Access, 2019, 7, pp. 81759-81769.
  24. Zhang, J., Jia, H. Zhang, N. ’Alternate support vector machine decision trees for power systems rule extractions’. IEEE Trans. Power Syst., 2023, 38, (1), pp. 980-983.
  25. Hou, Q., Zhang, N., Kirschen, D. S., et al.: ’Sparse oblique decision tree for power system security rules extraction and embedding’. IEEE Trans. Power Syst., 2021, 36, (2), pp. 1605-1615.
  26. Wang, T., Bi, T., Wang, H., et al.: ’Decision tree based online stability assessment scheme for power systems with renewable generations’. CSEE J. Power Energy Syst., 2015, 1, (2), pp. 53-61.
  27. Jia, H., Hou, Q., Liu, Y., et al.: ’Extraction of static voltage stability rule based on oblique regression tree and its ensemble algorithm’. Automat. Electric Power Syst., 2022, 46, (1), pp. 51-59.
  28. Yin, C., Li, F.: ’Analytical expression on transient overvoltage peak value of converter bus caused by DC faults’. IEEE Trans. Power Syst., 2021, 36, (3), pp. 2741-2744.
  29. Jin, X., Nian, H.: ’Overvoltage suppression strategy for sending AC grid with high penetration of wind power in the LCC-HVDC system under commutation failure’. IEEE Trans. Power Electron., 2021, 36, (9), pp. 10265-10277.
  30. Wang, T., Pei, L., Wang, J., et al.: ’Overvoltage suppression under commutation failure based on improved voltage-dependent current order limiter control strategy’. IEEE Trans. Ind. Appl., 2022, 58, (4), pp.4914-4922.
  31. Xiao, J., Heng, N., Chen Z., et al.: ’Optimal power coordinated control strategy for dfig-based wind farm to increase transmission capacity of the LCC-HVDC system considering commutation failure’. IEEE J. Emerg. Sel. Top. Power Electron., 2022, 10, (3), pp. 3129-3139.
  32. Li, F., Wang, Q., Tang, Y., et al.: ’An integrated method for critical clearing time prediction based on a model-driven and ensemble cost-sensitive data-driven scheme’. Int. J. Electr. Power Energy Syst., 2021, 125, pp, 106513.