Prediction of user outage under typhoon disaster based on multi-algorithm Stacking integration

Abstract Prediction of user outage under typhoon disaster is of great significance for power grid disaster prevention and mitigation. Based on the idea of Stacking integration in machine learning, this paper constructs a forecasting model of user outage under typhoon disaster. It includes base learner layer and meta learner layer. In the base learner layer, random forest, adaptive boosting, extremely tree, gradient boosting decision tree, support vector machine and logistic regression are selected. Then the XGBoost algorithm is selected in the meta learner layer. Taking one of the most frequently struck area Xuwen County of Guangdong, China as the research object, the model is verified by typhoon “Rammasun(2014)”,“Kalmaegi(2014)” and “Mujigae(2015)”. The results show that the accuracy and recall of the prediction model based on multi-algorithm Stacking integration can reach 0.7678 and 0.9059 respectively. It can well realize the prediction of user outage under typhoon disaster.

[2]  Yoav Freund,et al.  Experiments with a New Boosting Algorithm , 1996, ICML.

[3]  Bin Chen,et al.  Early Warning Method of Transmission Tower Considering Plastic Fatigue Damage Under Typhoon Weather , 2019, IEEE Access.

[4]  Li Yanguo.  Research on Impact Model of Meteorological Factors on the Power Accidents , 2013 .

[5]  Yacine Rezgui,et al.  Predictive modelling for solar thermal energy systems: A comparison of support vector regression, random forest, extra trees and regression trees , 2018, Journal of Cleaner Production.

[6]  Ross Baldick,et al.  Research on Resilience of Power Systems Under Natural Disasters—A Review , 2016, IEEE Transactions on Power Systems.

[7]  Yong Huang,et al.  Research on Early Warning Method of Overhead Transmission Line Damage Caused by Typhoon Disaster , 2018, ANT/SEIT.

[8]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[9]  Seth D. Guikema,et al.  Importance of soil and elevation characteristics for modeling hurricane-induced power outages , 2011 .

[10]  Seth D. Guikema,et al.  Predicting Hurricane Power Outages to Support Storm Response Planning , 2014, IEEE Access.

[11]  Xu Liang.  Prediction of original reliability parameters of power system based on fuzzy clustering and similarity , 2011 .

[12]  JinShan Yang,et al.  Use GBDT to Predict the Stock Market , 2020 .

[13]  S. S. Venkata,et al.  Predicting vegetation-related failure rates for overhead distribution feeders , 2002 .

[14]  D. Wanik,et al.  Storm outage modeling for an electric distribution network in Northeastern USA , 2015, Natural Hazards.

[15]  Seth D Guikema,et al.  Improving the Predictive Accuracy of Hurricane Power Outage Forecasts Using Generalized Additive Models , 2009, Risk analysis : an official publication of the Society for Risk Analysis.

[16]  Yuanqing Xia,et al.  A new sampling method in particle filter based on Pearson correlation coefficient , 2016, Neurocomputing.

[17]  Seth D. Guikema,et al.  Multi-Stage Prediction for Zero-Inflated Hurricane Induced Power Outages , 2018, IEEE Access.

[18]  Jery R. Stedinger,et al.  Negative Binomial Regression of Electric Power Outages in Hurricanes , 2005 .

[19]  S. Quiring,et al.  Development of a Typhoon Power Outage Model in Guangdong, China , 2020 .

[20]  HongFang Zhou,et al.  A feature selection algorithm of decision tree based on feature weight , 2021, Expert Syst. Appl..

[21]  Seth D. Guikema,et al.  Hybrid data mining-regression for infrastructure risk assessment based on zero-inflated data , 2012, Reliab. Eng. Syst. Saf..

[22]  Di Wu,et al.  Prediction of the spatial distribution of Alternanthera philoxeroides in China based on ArcGIS and MaxEnt , 2020 .

[23]  Zhi-Hua Zhou,et al.  Ensemble Methods: Foundations and Algorithms , 2012 .

[24]  Haibin Liu,et al.  Spatial generalized linear mixed models of electric power outages due to hurricanes and ice storms , 2008, Reliab. Eng. Syst. Saf..