Predicting Storm Outages Through New Representations of Weather and Vegetation

This paper introduces new developments in an outage prediction model (OPM) for an electric distribution network in the Northeastern United States and assesses their significance to the OPM performance. The OPM uses regression tree models fed by numerical weather prediction outputs, spatially distributed information on soil, vegetation, electric utility assets, and historical power outage data to forecast the number and spatial distribution of outages across the power distribution grid. New modules introduced hereby consist in 1) a storm classifier based on weather variables; 2) a multimodel optimization of regression tree output; and 3) a post-processing routine for more accurately describing tree-leaf conditions. Model implementations are tested through leave-one-storm-out cross-validations performed on 120 storms of varying intensity and characteristics. The results show that the median absolute percentage error of the new OPM version decreased from 130% to 59% for outage predictions at the service territory level, and the OPM skills for operational forecasts are consistent with the skills based on historical storm analyses.

[1]  Seymour Geisser,et al.  The Predictive Sample Reuse Method with Applications , 1975 .

[2]  Richard J. Campbell,et al.  Weather-Related Power Outages and Electric System Resiliency , 2012 .

[3]  J. Wallace,et al.  Atmospheric Science: An Introductory Survey , 1977 .

[4]  G. Grell.  Prognostic evaluation of assumptions used by cumulus parameterizations , 1993 .

[5]  D. Wanik,et al.  Nonparametric Tree‐Based Predictive Modeling of Storm Outages on an Electric Distribution Network , 2017, Risk analysis : an official publication of the Society for Risk Analysis.

[6]  Seth D. Guikema,et al.  Incorporating Hurricane Forecast Uncertainty into a Decision-Support Application for Power Outage Modeling , 2014 .

[7]  V. Murray,et al.  Power Outages, Extreme Events and Health: a Systematic Review of the Literature from 2011-2012 , 2014, PLoS currents.

[8]  D. Wanik,et al.  A Case Study on Power Outage Impacts from Future Hurricane Sandy Scenarios , 2018 .

[9]  Karl Pearson F.R.S..  LIII. On lines and planes of closest fit to systems of points in space , 1901 .

[10]  Xin-Zhong Liang,et al.  A Thermal Infrared Radiation Parameterization for Atmospheric Studies , 2001 .

[11]  Ismael Sánchez,et al.  Short-term prediction of wind energy production , 2006 .

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

[13]  Nicolai Meinshausen,et al.  Quantile Regression Forests , 2006, J. Mach. Learn. Res..

[14]  J. Shukla,et al.  On the Strategy of Combining Coarse and Fine Grid Meshes in Numerical Weather Prediction , 1973 .

[15]  C. Paulson.  The Mathematical Representation of Wind Speed and Temperature Profiles in the Unstable Atmospheric Surface Layer , 1970 .

[16]  G. Grell,et al.  A generalized approach to parameterizing convection combining ensemble and data assimilation techniques , 2002 .

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

[18]  David W. Wanik,et al.  Agent Based Model to Estimate Time to Restoration of Storm-Induced Power Outages , 2018, Infrastructures.

[19]  Michael Schmidthaler,et al.  Assessing the socio-economic effects of power outages ad hoc , 2014, Computer Science - Research and Development.

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

[21]  A. Sanghvi,et al.  Reliability of Electricity Supply, Outage Costs and Value of Service: An Overview , 1988 .

[22]  T. Clark,et al.  Severe Downslope Windstorm Calculations in Two and Three Spatial Dimensions Using Anelastic Interactive Grid Nesting: A Possible Mechanism for Gustiness , 1984 .

[23]  E. K. Webb.  Profile relationships: The log‐linear range, and extension to strong stability , 1970 .

[24]  Olivier Pannekoucke,et al.  A benchmark of statistical regression methods for short-term forecasting of photovoltaic electricity production, part I: Deterministic forecast of hourly production , 2014 .

[25]  Seth D. Guikema,et al.  Estimating the spatial distribution of power outages during hurricanes in the Gulf coast region , 2009, Reliab. Eng. Syst. Saf..

[26]  P. McSharry,et al.  A comparison of univariate methods for forecasting electricity demand up to a day ahead , 2006 .

[27]  Pu Wang,et al.  Weather station selection for electric load forecasting , 2015 .

[28]  J. W. Taylor,et al.  Short-term electricity demand forecasting using double seasonal exponential smoothing , 2003, J. Oper. Res. Soc..

[29]  Jimy Dudhia,et al.  Implementation and verification of the unified Noah land-surface model in the WRF model [presentation] , 2004 .

[30]  Brian A. Colle,et al.  Evaluation of a Mesoscale Short-Range Ensemble Forecast System over the Northeast United States , 2007 .

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

[32]  R. Targosz,et al.  Cost of Poor Power Quality , 2008 .

[33]  D. Legates,et al.  Evaluating the use of “goodness‐of‐fit” Measures in hydrologic and hydroclimatic model validation , 1999 .

[34]  Max J. Suarez,et al.  A Solar Radiation Parameterization for Atmospheric Studies , 2013 .

[35]  Ronald Gelaro,et al.  Initial Condition Sensitivity and Error Growth in Forecasts of the 25 January 2000 East Coast Snowstorm , 2002 .

[36]  H. Chipman,et al.  BART: Bayesian Additive Regression Trees , 2008, 0806.3286.

[37]  Da‐Lin Zhang,et al.  A High-Resolution Model of the Planetary Boundary Layer—Sensitivity Tests and Comparisons with SESAME-79 Data , 1982 .

[38]  H. Kaiser.  The varimax criterion for analytic rotation in factor analysis , 1958 .

[39]  David A. Jones.  Electrical engineering: the backbone of society , 1991 .

[40]  M. Stone.  Cross‐Validatory Choice and Assessment of Statistical Predictions , 1976 .

[41]  Emmanouil N. Anagnostou,et al.  Evaluation of PBL Parameterizations for Modeling Surface Wind Speed during Storms in the Northeast United States , 2016 .

[42]  R. Tibshirani,et al.  Bayesian backfitting (with comments and a rejoinder by the authors , 2000 .

[43]  B. Hicks,et al.  Flux‐gradient relationships in the constant flux layer , 1970 .

[44]  W.-T Paul Wang,et al.  A More Resilient Grid: The U.S. Department of Energy Joins with Stakeholders in an R&D Plan , 2015, IEEE Power and Energy Magazine.

[45]  J. Dudhia,et al.  A New Vertical Diffusion Package with an Explicit Treatment of Entrainment Processes , 2006 .

[46]  D. Lubkeman,et al.  Large scale storm outage management , 2004, IEEE Power Engineering Society General Meeting, 2004..

[47]  Ying-Hwa Kuo,et al.  Semiprognostic Tests of Cumulus Parameterization Schemes in the Middle Latitudes , 1988 .

[48]  E. Mlawer,et al.  Radiative transfer for inhomogeneous atmospheres: RRTM, a validated correlated-k model for the longwave , 1997 .

[49]  Kit Po Wong,et al.  Probabilistic Forecasting of Wind Power Generation Using Extreme Learning Machine , 2014, IEEE Transactions on Power Systems.

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

[51]  A. Beljaars.  The parametrization of surface fluxes in large-scale models under free convection , 1995 .

[52]  Leo Breiman,et al.  Classification and Regression Trees , 1984 .

[53]  Da‐Lin Zhang,et al.  A two-way interactive nesting procedure with variable terrain resolution , 1986 .

[54]  David M. Allen,et al.  The Relationship Between Variable Selection and Data Agumentation and a Method for Prediction , 1974 .

[55]  P. Nurmi,et al.  Overview of methods for the verification of quantitative precipitation forecasts , 2008 .

[56]  Anna Ghelli,et al.  Verification of Precipitation Forecasts over the Alpine Region Using a High-Density Observing Network , 2002 .

[57]  J. McBride,et al.  Verification of precipitation in weather systems: determination of systematic errors , 2000 .

[58]  Efi Foufoula-Georgiou,et al.  Space‐time rainfall organization and its role in validating quantitative precipitation forecasts , 2000 .

[59]  J. Nash,et al.  River flow forecasting through conceptual models part I — A discussion of principles☆ , 1970 .

[60]  Seth D Guikema,et al.  Improving Hurricane Power Outage Prediction Models Through the Inclusion of Local Environmental Factors , 2018, Risk analysis : an official publication of the Society for Risk Analysis.

[61]  Tao Hong,et al.  Probabilistic electric load forecasting: A tutorial review , 2016 .

[62]  Daniel T. Larose,et al.  Data Mining and Predictive Analytics , 2015 .

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

[64]  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.

[65]  K. Taylor.  Summarizing multiple aspects of model performance in a single diagram , 2001 .

[66]  D. Wanik,et al.  Estimated Time of Restoration (ETR) Guidance for Electric Distribution Networks , 2018 .

[67]  E. Lorenz.  Deterministic nonperiodic flow , 1963 .

[68]  J. Friedman.  Greedy function approximation: A gradient boosting machine. , 2001 .

[69]  Michelle L Bell,et al.  Lights Out: Impact of the August 2003 Power Outage on Mortality in New York, NY , 2011, Epidemiology.

[70]  D. Watson.  Comparative Physiological Studies on the Growth of Field Crops: I. Variation in Net Assimilation Rate and Leaf Area between Species and Varieties, and within and between Years , 1947 .

[71]  Roshanak Nateghi,et al.  Power Outage Estimation for Tropical Cyclones: Improved Accuracy with Simpler Models , 2014, Risk analysis : an official publication of the Society for Risk Analysis.

[72]  G. Powers,et al.  A Description of the Advanced Research WRF Version 3 , 2008 .

[73]  D. Wanik,et al.  Using vegetation management and LiDAR-derived tree height data to improve outage predictions for electric utilities , 2017 .