Typhoons have substantial impacts on power systems and may result in major power outages for distribution network users. Developing prediction models for the number of users going through typhoon power outages is a high priority to support restoration planning. This study proposes a data-driven model to predict the number of distribution network users that may experience power outages when a typhoon passes by. To improve the accuracy of the prediction model, twenty six explanatory variables from meteorological factors, geographical factors and power grid factors are considered. In addition, the authors compared the application effect of five different machine learning regression algorithms, including linear regression, support vector regression, classification and regression tree, gradient boosting decision tree and random forest (RF). It turns out that the RF algorithm shows the best performance. The simulation indicates that the accuracy of the optimal model error within ±30% can reach up to 86%. The proposed method can improve the prediction accuracy through continuous learning on the existing basis. The prediction results can provide efficient guidance for emergency preparedness during typhoon disaster, and can be used as a basis to notify the distribution network users who are likely to lose power.

References

1. 1)
  - 23. Radmer, D.T., Kuntz, P.A., Christie, R.D., et al: ‘Predicting vegetation-related failure rates for overhead distribution feeders’, IEEE Trans. Power Deliv., 2002, 17, (4), pp. 1170–1175.
2. 2)
  - 18. Xue, Y., Wu, Y., Xie, Y., et al: ‘The extension of power failure prevention framework to early warning of natural disasters’, Power Syst. Autom., 2013, 37, (16), pp. 1–9.
3. 3)
  - 20. Yin, Z., Ji, X., Zhang, Y., et al: ‘Data-driven approach for real-time distribution network reconfiguration’, IET Gener. Transm. Distrib., 2020, 14, (13), pp. 2450–2463.
4. 4)
  - 19. Hou, H., Yu, S., Wang, H., et al: ‘Risk assessment and its visualization of power tower under typhoon disaster based on machine learning algorithms’, Energies, 2019, 12, (2), pp. 1–23.
5. 5)
  - 13. Chen, Y., Wang, S., Chen, B., et al: ‘Failure probability assessment method of transmission channel structure considering geographic elevation information in typhoon environment’, Power Grid Technol., 2018, 42, (7), pp. 2295–2302.
6. 6)
  - 24. Zhang, W., Sheng, W., Liu, Y., et al: ‘Forecasting method of distribution network fault risk level considering the correlation of weather factors’, Power Grid Technol., 2018, 42, (8), pp. 2391–2398.
7. 7)
  - 32. Hou, H., Geng, H., Xiao, X., et al: ‘Forecast and evaluation of power outage areas of distribution network users under typhoon disasters’, Power Grid Technol., 2019, 43, (6), pp. 1948–1954.
8. 8)
  - 10. Weng, S.: ‘Research on early warning methods of gale disasters on overhead transmission lines’. MS thesis, Chongqing University, 2015.
9. 9)
  - 25. Sun, C., Wang, X., Zheng, Y., et al: ‘Early warning system for spatiotemporal prediction of fault events in a power transmission system’, IET Gener. Transm. Distrib., 2019, 13, (21), pp. 4888–4899.
10. 10)
  - 14. Liu, H., Davidson, R.A., Rosowsky, D.V., et al: ‘Negative binomial regression of electric power outages in hurricanes’, J. Infrastruct. Syst., 2005, 11, (4), pp. 258–267.
11. 11)
  - 28. Liang, J., Chen, J., Zhang, X., et al: ‘Anomaly detection based on one-hot encoding and convolutional neural network’, J. Tsinghua Univ., Nat. Sci. Ed., 2019, 59, (7), pp. 523–529.
12. 12)
  - 5. Yao, K.: ‘Method for generating dynamic accident set caused by tropical cyclones in group grid faults’. MS thesis, Harbin Institute of Technology, 2013.
13. 13)
  - 33. ‘sklearn’, available at http://scikit-learn.org/stable/modules/generated/sklearn.linear_model.
14. 14)
  - 17. Liu, H., Davidson, R.A., Apanasovich, T.V.: ‘Statistical forecasting of electric power restoration times in hurricanes and ice storms’, IEEE Trans. Power Syst., 2007, 22, (4), pp. 2270–2279.
15. 15)
  - 1. Zarakas, W.P., Sergici, S., Bishop, H., et al: ‘Utility investments in resiliency: balancing benefits with cost in an uncertain environment’, Electr. J., 2014, 27, (5), pp. 31–41.
16. 16)
  - 31. Yuan, S., Quiring, S.M., Zhu, L., et al: ‘Development of a typhoon power outage model in Guangdong, China’, Electr. Power Energy Syst.2020, 117, pp. 1–12.
17. 17)
  - 16. Quiring, S.M., Zhu, L., Guikema, S.D.: ‘Importance of soil and elevation characteristics for modeling hurricane-induced power outages’, Nat. Hazard, 2011, 58, pp. 365–390.
18. 18)
  - 30. Vapnik, V.N.: ‘Statistical learning theory’ (Wiley-Interscience Press, USA, 1998).
19. 19)
  - 11. Xie, Y., Xue, Y., Wen, F., et al: ‘Spatio-temporal assessment of the impact of ice disaster on transmission line failure rate’, Power Syst. Autom., 2013, 37, (18), pp. 32–41.
20. 20)
  - 6. Kavousi-Fard, A., Wang, M., Su, W.: ‘Stochastic resilient post-hurricane power system recovery based on Mobile emergency resources and reconfigurable networked microgrids’, IEEE Access, 2018, 6, pp. 72311–72326.
21. 21)
  - 7. Mohammad, M.H., Masood, P.: ‘Quantifying impacts of automation on resilience of distribution systems’, IET Gener. Transm. Distrib., 2020, 3, (2), pp. 144–152.
22. 22)
  - 29. Li, H.: ‘Statistical learning method’ (Tsinghua University Press, People's Republic of China, 2012).
23. 23)
  - 9. Bao, B., Cheng, R., Xiong, X., et al: ‘A warning method for transmission line typhoon risk taking into account micro-topography correction’, Power Syst. Prot. Control, 2014, 42, (14), pp. 79–86.
24. 24)
  - 21. Guikema, S.D., Nateghi, R., Quiring, S.M., et al: ‘Predicting hurricane power outages to support storm response planning’, IEEE Access, 2014, 2, pp. 1364–1373.
25. 25)
  - 2. Masoud, S.K., Kamran, J., Meghdad, T.K., et al: ‘Bi-level network reconfiguration model to improve the resilience of distribution systems against extreme weather events’, IET Gener. Transm. Distrib., 2019, 13, (15), pp. 3302–3310.
26. 26)
  - 3. Xiong, J., Lin, H., Wang, Q., et al: ‘Research on GIS-based early warning model of wind disaster in regional power grid’, East China Electr. Power, 2011, 39, (8), pp. 1248–1252.
27. 27)
  - 27. Wanik, D.W., Anagnostou, E.N., Hartman, B.M., et al: ‘Storm outage modeling for an electric distribution network in northeastern USA’, Nat. Hazards, 2015, 79, (2), pp. 1359–1384.
28. 28)
  - 26. Zhang, Y., Chen, C., Xu, L.: ‘Power system reliability original parameter estimation based on fuzzy clustering and similarity’, Power Syst. Prot. Control, 2011, 39, (8), pp. 1–5.
29. 29)
  - 15. Liu, H., Davidson, R.A., Apanasovich, T.V.: ‘Spatial generalized linear mixed models of electric power outages due to hurricanes and ice storms’, Rel. Eng. Syst. Saf., 2008, 93, (6), pp. 897–912.
30. 30)
  - 4. Gao, W., Zhou, R., Zhao, D.: ‘Heuristic failure prediction model of transmission line under natural disasters’, IET Gener. Transm. Distrib., 2017, 11, (4), pp. 935–942.
31. 31)
  - 12. Wu, Y., Xue, Y., Lu, J., et al: ‘Spatiotemporal impact of mountain fire disaster on power grid failure rate’, Power Syst. Autom., 2016, 40, (3), pp. 14–20.
32. 32)
  - 34. Zhao, H., Zhang, D., Huang, S., et al: ‘Analysis of the relationship between ground flash density and lightning strike failure in Hainan province based on Pearson correlation coefficient’, High Volt. Electr. Appl., 2019, 55, (8), pp. 186–192.
33. 33)
  - 22. Guikema, S.D., Quiring, S.M.: ‘Hybrid data mining-regression for infrastructure risk assessment based on zero-inflated data’, Reliablity Eng. Sys. Saf., 2012, 99, pp. 178–182.
34. 34)
  - 8. Huang, Y., Wei, R., Zhou, E., et al: ‘Early warning method of transmission line damage under typhoon disaster’, Power Syst. Autom., 2018, 42, (23), pp. 142–150.

Data-driven prediction for the number of distribution network users experiencing typhoon power outages

References

Related content