Outage prediction models for snow and ice storms

被引:48
作者
Cerrai, Diego [1 ]
Koukoula, Marika [1 ]
Watson, Peter [1 ]
Anagnostou, Emmanouil N. [1 ]
机构
[1] Univ Connecticut, Dept Civil & Environm Engn, 261 Glenbrook Rd, Storrs, CT 06269 USA
关键词
Outage Prediction Model; Extreme events; Electric grid; Snow storms; Ice storms; ELECTRIC-POWER OUTAGES; PRECIPITATION-TYPE; ACCRETION; FORECASTS; UNCERTAINTY; REGRESSION; HURRICANES; ACCURACY; ENSEMBLE; RANGE;
D O I
10.1016/j.segan.2019.100294
中图分类号
TE [石油、天然气工业]; TK [能源与动力工程];
学科分类号
0807 ; 0820 ;
摘要
This paper describes the development of two Outage Prediction Models (OPMs) for power outages caused by snow and ice storms on electric distribution networks, and their performance evaluation in the Northeastern United States. The first is a Machine Learning (ML) based model that is set up to predict power outages on a regular grid (4-km grid spacing). The second is a Generalized Linear Model (GLM) that is set up to predict total power outages at the town level. Both models are fed with Numerical Weather Prediction (NWP) outputs, satellite-derived leaf area index (LAI) and land cover data, and utility specified infrastructure and historical outage data. For both models the most important variables are the amount of assets on the territory, LAI, snow density, and-for the ice model -the amount of freezing rain. Results from cross-validation experiments based on 54 outage events spanning three orders of magnitude show median absolute percentage errors around 70% for both models. The GLM is able to predict extreme events (such as the devastating October 2011 nor'easter) better than ML models do, while ML models have better performance for lower impact events and present better characterization of the spatial distribution of power outages. (c) 2019 Elsevier Ltd. All rights reserved.
引用
收藏
页数:12
相关论文
共 106 条
[1]  
Admirat P., 2008, ATMOSPHERIC ICING PO, P119, DOI [10.1007/978-1-4020-8531-4_4, DOI 10.1007/978-1-4020-8531-4_4]
[2]  
[Anonymous], 9 INT WORKSH ATM IC
[3]  
[Anonymous], AFWA DIAGNOSTICS WRF
[4]  
[Anonymous], 21 C WEATH AN FOR 17
[5]  
[Anonymous], 2018, Surveyweighted generalized linear mixed models
[6]  
[Anonymous], 16 C NUM WEATH PRED
[7]  
[Anonymous], SOIL SURV GEOGR DAT
[8]  
[Anonymous], 98SC3 ISOTC
[9]  
[Anonymous], TECH REP
[10]  
[Anonymous], 1994, NEURAL NETWORKS