Forecasting hurricane-induced power outage durations
- 621 Downloads
Accurate estimates of the duration of power outages caused by hurricanes prior to landfall are valuable for utility companies and government agencies that wish to plan and optimize their restoration efforts. Accurate pre-storm estimates are also important information for customers and operators of other infrastructures systems, who rely heavily on electricity. Traditionally, utilities make restoration plans based on managerial judgment and experience. However, skillful outage forecast models are conducive to improved decision-making practices by utilities and can greatly enhance storm preparation and restoration management procedures of power companies and emergency managers. This paper presents a novel statistical approach for estimating power outage durations that is 87 % more accurate than existing models in the literature. The power outage duration models are developed and carefully validated for outages caused by Hurricanes Dennis, Katrina, and Ivan in a central Gulf Coast state. This paper identifies the key variables in predicting hurricane-induced outage durations and their degree of influence on predicting outage restoration for the utility company service area used as our case study.
KeywordsData mining Hurricanes Power outages Random forests Power restoration
We gratefully acknowledge the funding sources for this work from the National Science Foundation (CMMI 0968711 and 1149460 and SEES 1215872) and the U.S. Department of Energy (BER-FG02-08ER64644). However, all opinions in this paper are those of the authors and do not necessarily reflect the views of the sponsors.
- Friedman JH (2001) Greedy function approximation: a gradient boosting machine. Ann Stat 29(5):1189–1232Google Scholar
- Hastie T, Tibshirani R, Friedman J (2011) The elements of statistical learning; data mining, inference and prediction, 2nd edn. Springer, New YorkGoogle Scholar
- Impact Weather: www.impactweather.com. Last accessed 28 June 2010 at 12:00 pm
- Joshi NN, Lambert JH (2011) Diversification of engineering infrastructure investments for emergent and unknown non-systematic risks. J Risk Res 14(4):1466–4461Google Scholar
- Lubkeman D, Julian DE (2004) Large scale storm outage management. IEEE Power Eng Soc Gen Meet 1:16–22Google Scholar
- Nateghi R (2012) Modeling hurricane activity in the Atlantic Basin and reliability of power distribution systems impacted by hurricanes in the U.S. Ph.D. thesis, Johns Hopkins University, Department of Geography and Environmental Engineering, 2012Google Scholar
- NLCD (2001) http://www.epa.gov/mrlc/nlcd-2001.html. Last accessed in 29 Jan 2010
- Reed DA, Nojima N, Park J (2003) Performance assessment of lifelines. 16th ASCE Engineering Mechanics Conference, 16–18 July, Washington, SeattleGoogle Scholar
- Shortridge JE, Guikema SD (2014) Public health and pipe breaks in water distribution systems: analysis with internet search volume as a proxy. Water Res 53:26–34Google Scholar
- Yule E, Kendall M (1950) An introduction to the theory of statistics, 14th edn. Charles Griffin, LondonGoogle Scholar